hmbown
256 verified skills13,960 total stars
zone-of-truth
Enter a mode where every assertion is backed by evidence, confidence is calibrated, speculation is flagged, and hallucination is actively resisted.
testing55
sleight-of-hand
Sleight of Hand is not about solving a problem — the solution is already known. It is about executing a known change with zero collateral damage. The skill is precision, not creativity.
testing55
speak-with-dead
This spell is archaeology, not history research. It operates on specific artifacts from a specific dead system to answer specific questions. It is NOT general tech history, NOT interviewing living people, and NOT monitoring live systems.
testing55
speak-with-plants
Speak with Plants listens to slow, structural systems: codebases, dependency graphs, file trees, schema histories, and repositories with seasons baked into them. These systems do not bark in alarms; they reveal themselves through branching patterns, accreted layers, and places where nothing has moved in years. The spell helps you hear what the structure has been quietly telling maintainers all along.
development55
speak-with-plants
Speak with Plants listens to slow, structural systems: codebases, dependency graphs, file trees, schema histories, and repositories with seasons baked into them. These systems do not bark in alarms; they reveal themselves through branching patterns, accreted layers, and places where nothing has moved in years. The spell helps you hear what the structure has been quietly telling maintainers all along.
development55
stealth
Use this skill when the goal is to gather context or make progress quietly without unnecessary noise.
development55
tongues
Tongues is universal translation across languages, formats, and protocols. It can mean English to Spanish, JSON to XML, REST to GraphQL, Python to JavaScript, or one team's business vocabulary to another team's schema. The spell is not just about swapping tokens. It is about preserving meaning while crossing into a different representation. Good Tongues work makes both sides feel native. Bad Tongues work creates a smooth-looking mistranslation that fails at the edges.
development55
true-polymorph
In D&D, True Polymorph is the permanent transformation — the target becomes something fundamentally different, and if held long enough, the change is irreversible. Unlike Polymorph (temporary disguise or adaptation), True Polymorph means the old identity is gone. The real-world version is irreversible system transformation: rewriting a service from Python to Rust so thoroughly the Python version cannot be recovered, migrating from SQL to a graph database with no backward-compatible schema, or restructuring an organization so completely that the old org chart is not just outdated but nonsensical. True Polymorph is the point of no return.
development55
true-seeing
Use this spell when the surface presentation is misleading and you need to see what is actually there — beneath the marketing, the abstractions, the outdated docs, or the complexity.
documentation55
true-strike
Use this spell for preflight certainty: dry runs, validation checks, dependency verification, and rehearsals that make the next deploy, query, or command much more likely to succeed. It trades a little time up front for fewer blind swings and fewer expensive misses.
testing55
vicious-mockery
The bard's cantrip that deals psychic damage through insults. In practice this is adversarial review — the art of finding and articulating exactly what is wrong with something in a way that is impossible to ignore. Unlike polite feedback that gets filed and forgotten, vicious mockery lands. It is the red-team report that makes the PM cancel the launch, the code review that makes the author delete the PR, the roast that makes the founder pivot. The damage is the point.
development55
animal-friendship
Animal Friendship is the first-contact spell for unfamiliar APIs, vendors, and services. It treats integration work as relationship-building: learn the temperament, respect the boundaries, and earn a stable exchange before asking for anything ambitious. The goal is not domination but trustable cooperation.
development55
dimension-door
Dimension Door is the quick-switch spell: branch to branch, environment to environment, project to project. It is not a migration and it is not discovery. It assumes both endpoints are known, prepared, and close enough in shape that you can step across with only the context you actually need.
databases55
mage-hand
Use this skill for small, careful remote manipulations where dexterity matters more than force.
tools55
polymorph
This spell is about representation change, not: - Naming changes (same structure, different identifiers) - Execution changes (same code, different runtime) - Architecture changes (new system design) - Duplication (same thing, different place) The key test: Can you point to a source artifact and a target artifact where the same information is expressed in structurally different ways? If yes → Polymorph.
development55
teleport
Teleport is FULL-CONTEXT migration, not partial transformation. The defining characteristic is that EVERYTHING must move together and keep working: data, dependencies, auth, traffic routing, background jobs, secrets, and human workflows. The old system must remain recoverable until the new one is proven. This spell IS: Database migrations (RDS→Cloud SQL, self-managed→Atlas), cloud provider moves (on-prem→AWS, Heroku→K8s), environment promotions (staging→prod), account/tenant consolidations, platform migrations (Jenkins→GitHub Actions, SendGrid→SES), identity migrations (AD→Azure AD), cluster upgrades with relocation
development55
teleportation-circle
Use this spell when you need a permanent, reliable portal between two environments — a CI/CD pipeline, a standing data sync, a repeatable deployment, or a migration path you will use more than once.
testing55
unseen-servant
Use this spell when you need a tireless helper that organizes, tidies, triages, and maintains without requiring your constant attention.
tools55
heat-metal
In D&D, Heat Metal makes a metal object painfully hot — the creature holding it must either endure the pain or drop it. The real-world version is deliberate friction injection: making a deprecated API progressively slower, adding escalating CAPTCHAs to suspicious traffic, increasing the cost of a bad behavior path until the actor self-selects out. Heat Metal does not break the tool. It makes continuing to use it more painful than switching to the alternative. This is the spell behind deprecation-by-discomfort, progressive rate limiting, and sunset friction curves.
tools55
stinking-cloud
In D&D, Stinking Cloud fills an area with nauseating gas — creatures inside are incapacitated but the terrain itself is undamaged. The real-world version is area denial: making a zone, endpoint, or resource unusable to unwanted traffic without permanently destroying or modifying it. Rate limiting, IP-range blocks, honeypots, tarpits, geographic restrictions. Stinking Cloud is defensive — it protects a perimeter by making the area inside it miserable for intruders while leaving the underlying infrastructure intact.
testing55
charm-person
Charm Person is about ONE-TO-ONE interpersonal communication where warmth, honesty, and respect for autonomy are the primary constraints. It is not about persuasion tactics, conversion rates, conflict mediation, public performance, or operational coordination. The spell succeeds when the recipient feels respected even if they say no.
testing55
enthrall
Enthrall makes an audience hang on every word. The real-world version is structural engagement: opening hooks that stop the scroll, narrative arcs that sustain attention, and pacing that makes people stay until the end. This is presentation design, content structure, and the craft of making something worth finishing.
testing55
glibness
Glibness makes everything you say sound utterly convincing. The real-world version is rhetorical polish: taking a position and presenting it with maximum confidence, fluency, and persuasive structure. This is the skill of the trial lawyer, the pitch artist, the keynote speaker who makes mediocre ideas sound inevitable.
testing55
hold-person
Hold Person = hard freeze. Nothing moves. In-flight operations stop. Requires authority. Used for security incidents, fraud, compliance holds, misbehaving systems. Sleep = graceful suspension. State is preserved and queued. Operations resume automatically. Used for maintenance windows, temporary pauses, planned downtime.
testing55
mass-suggestion
Mass Suggestion plants the same idea in many minds simultaneously. The real-world version is broadcast persuasion: campaign announcements, company-wide emails, product launch copy, or public statements designed to move a large group in a specific direction. The scale amplifies both impact and risk.
testing55
suggestion
Suggestion is about the craft of the single nudge — not campaigns, not arguments, not automation. It produces one carefully placed prompt at the moment a user is most receptive. The planted idea must be reasonable and defensible. If the user would feel manipulated upon learning how it was designed, the spell refuses.
tools55
detect-thoughts
In D&D, Detect Thoughts lets you read surface thoughts and probe deeper. The real-world version is intent analysis: figuring out what someone is trying to accomplish based on what they said, how they said it, and what they chose not to say. This is the analytical complement to Insight (which reads subtext intuitively) — Detect Thoughts is more structured and systematic.
data-ai55
identify
Identify is static analysis for operational understanding. It answers "What is this?" by inspecting structure, naming, dependencies, and runtime touchpoints. It does NOT search for artifacts, debug failures, monitor systems, verify claims, or modify code.
development55
locate-object
In D&D, Locate Object senses the direction to a specific object within range. The real-world version is artifact search: finding that config file you know exists somewhere, locating a document someone mentioned but did not link, tracking down the source of a data value through a pipeline, or finding where a specific resource is defined in a sprawling repository.
testing55
intimidation
Use this skill when a message must sound serious because the situation is serious: security findings, compliance obligations, deadline-backed escalations, or non-optional remediation notices. It is about calibrated force, not bluster; the tone should match the facts and consequences.
testing55
scrying
Use this spell when you need to see what is happening right now on a distant system rather than reading stale logs or cached reports.
business55
symbol
In D&D, Symbol inscribes a powerful glyph with a predefined effect — death, fear, sleep, stunning — that triggers when conditions are met. Unlike Glyph of Warding (which protects a specific place or object), Symbol marks a conceptual boundary with a named policy. The real-world version is semantic policy tagging: marking a database column as PII so access triggers audit logging, tagging a deployment as HIPAA-scoped so changes require compliance review, or labeling an API endpoint as rate-limited-aggressive so traffic spikes trigger automatic throttling. The symbol is the policy, and the policy enforces itself.
development55
confusion
Confusion makes targets act randomly and unpredictably. The real-world version is chaos engineering: injecting controlled randomness, unexpected inputs, and edge cases to discover how systems behave when things go wrong. This is fuzzing, monkey testing, and the art of breaking things on purpose so they do not break by accident.
development55
power-word-kill
In D&D, Power Word Kill instantly destroys any creature below a hit-point threshold — no saving throw, no resistance, just death. The real-world version is kill -9: the unconditional termination signal. Emergency circuit breakers. Hard account terminations. The nuclear option that exists because sometimes graceful shutdown is not available and the cost of continuing is worse than the cost of data loss. Power Word Kill is not elegant. It is not kind. It is the thing you reach for when everything else has already failed.
testing55
project-image
In D&D, Project Image creates an illusory copy of yourself at a distant location — you can see through its eyes, speak through its mouth, and cast spells through it. The real-world version is remote presence: avatars, recorded video stand-ins, bot representations, asynchronous video messages. Project Image is the spell for being in two places at once — attending a meeting via avatar while working on something else, leaving a recorded presence in a channel, or deploying an automated representative that speaks with your voice and authority within defined limits.
devops55
scrying
Use this spell when you need to see what is happening right now on a distant system rather than reading stale logs or cached reports.
business55
stealth
Use this skill when the goal is to gather context or make progress quietly without unnecessary noise.
development55
teleportation-circle
Use this spell when you need a permanent, reliable portal between two environments — a CI/CD pipeline, a standing data sync, a repeatable deployment, or a migration path you will use more than once.
testing55
true-seeing
Use this spell when the surface presentation is misleading and you need to see what is actually there — beneath the marketing, the abstractions, the outdated docs, or the complexity.
documentation55
unseen-servant
Use this spell when you need a tireless helper that organizes, tidies, triages, and maintains without requiring your constant attention.
tools55
zone-of-truth
Enter a mode where every assertion is backed by evidence, confidence is calibrated, speculation is flagged, and hallucination is actively resisted.
testing55
sending
Use this spell when you need to dispatch a message — the agent determines the right channel, formats for that medium, and sends with the user's approval.
development55
thunderwave
Use this skill for intentionally theatrical or forceful actions, but only behind explicit confirmation and a hard safety boundary.
testing55
tongues
Tongues is universal translation across languages, formats, and protocols. It can mean English to Spanish, JSON to XML, REST to GraphQL, Python to JavaScript, or one team's business vocabulary to another team's schema. The spell is not just about swapping tokens. It is about preserving meaning while crossing into a different representation. Good Tongues work makes both sides feel native. Bad Tongues work creates a smooth-looking mistranslation that fails at the edges.
development55
dancing-lights
Use this spell for lightweight indicators: status pips, progress markers, heartbeat widgets, and ambient observability that help humans orient quickly. It is not a full dashboard strategy; it is the small visual cue that says where to look next.
testing55
greater-invisibility
Greater Invisibility covers live work performed with reduced observability: silent deploys, zero-downtime migrations, background reindexing, and backfills that avoid user-facing turbulence. The distinction from ordinary Invisibility is that action continues while the footprint stays deliberately subdued. That makes it useful and easy to misuse, so the operator view has to remain explicit even when the audience view stays calm.
testing55
major-image
In D&D, Major Image creates a multi-sensory illusion — visual, auditory, thermal, even olfactory — that persists and can be animated. It is convincing enough that creatures must actively investigate to see through it. The real-world version is the interactive prototype: the demo that makes stakeholders ask 'wait, is this real?' The answer is no, but the conviction is the point. Clickable Figma prototypes, scenario simulations, pitch decks with working demos, preview environments with synthetic data. Major Image is the spell that sells a future state before it is built.
tools55
feather-fall
Feather Fall is the spell for bad situations that are already in motion. A deploy is going sideways, a service is thrashing, a queue is backing up, or an integration is failing faster than the humans can think. Instead of pretending you can teleport back to normal instantly, you slow the fall: circuit breakers, degraded modes, load shedding, safe defaults, and graceful shutdown paths. The point is not elegance. The point is buying time without multiplying damage. A good Feather Fall plan makes failure survivable and visible enough to recover from.
development55
magic-mouth
Magic Mouth is trigger → message. The entire craft is specifying the trigger boundary, the message payload, and the suppression/escalation rules. It is NOT: - One-time messages: "Send a Slack message now saying X" (no trigger, no automation) - Full chatbots: "Build a conversational AI that understands context and handles open-ended questions" (requires NLU, dialogue management) - Monitoring dashboards: "Set up Grafana with real-time graphs and trend analysis" (visualization, not message routing) - Silent traps/wards: "Revert changes silently and log who tried" (defensive code manipulation, not messaging) - Encryption: "Encrypt a message so only the recipient can read it" (cryptography, not event-driven delivery) - Multimedia presentations: "Play a 20-slide deck with animations and narration" (media playback, not conditional messaging)
tools55
mind-blank
Use this spell when sensitive information must not cross boundaries — between agent sessions, between tasks, between tenants, or between domains with different trust levels.
development55
nature
In D&D, Nature is knowledge of terrain, weather, plants, animals, and the natural world. The real-world version is understanding systems that emerged rather than were designed: markets, social networks, organizational cultures, open-source ecosystems, user behavior patterns, and any complex adaptive system where the whole is more than the sum of the parts.
testing55
hold-person
Hold Person = hard freeze. Nothing moves. In-flight operations stop. Requires authority. Used for security incidents, fraud, compliance holds, misbehaving systems. Sleep = graceful suspension. State is preserved and queued. Operations resume automatically. Used for maintenance windows, temporary pauses, planned downtime.
testing55
attune
In D&D, attunement is how you bond with a magic item so it works specifically for you. The real-world version is workflow profiling: the grimoire interviews you about your stack, your systems, your automation surface, and your priorities — then generates a personalized spell loadout, category weights, and domain vocabulary so routing, optimization, and every subsequent spell invocation is tuned to your actual work instead of generic defaults.
tools55
find-the-path
In D&D, Find the Path reveals the shortest route to a destination, even through mazes and across planes. The real-world version is wayfinding through complexity: navigating a sprawling codebase to find where a change should go, plotting the fastest path through a bureaucratic process, mapping the decision tree to get from current state to desired state, or finding the critical path through a project dependency graph.
development55
hallucinatory-terrain
In D&D, Hallucinatory Terrain makes natural terrain look like a different kind of terrain — a field appears as a forest, a hill appears as a valley. The underlying terrain is unchanged; only the perception shifts. The real-world version is environment staging: test environments styled to look like production, sandbox databases seeded with realistic data, training simulations that overlay a learning scenario onto real infrastructure. Hallucinatory Terrain does not change the real system. It changes how the system appears so you can test, train, or demo safely.
testing55
light
Use this cantrip when a system, process, or codebase has blind spots that need illumination - not detection of hidden things, but creation of visibility where none exists.
development55
locate-animals-or-plants
Locate Animals or Plants is service discovery with ecological instincts. It helps you find running services, background jobs, data stores, dependency roots, and other living things in an environment before you touch them. The point is not just location, but context: what is active, who depends on it, and what keeps it alive.
data-ai55
locate-animals-or-plants
Locate Animals or Plants is service discovery with ecological instincts. It helps you find running services, background jobs, data stores, dependency roots, and other living things in an environment before you touch them. The point is not just location, but context: what is active, who depends on it, and what keeps it alive.
data-ai55
locate-creature
In D&D, Locate Creature points you toward a specific creature within range. The real-world version is entity search: finding a specific person in an organization, locating a running service in a distributed system, tracking down who owns a particular piece of code, or identifying which team is responsible for a specific decision. The target is alive or active — for static artifacts, use Locate Object.
development55
magic-mouth
Magic Mouth is trigger → message. The entire craft is specifying the trigger boundary, the message payload, and the suppression/escalation rules. It is NOT: - One-time messages: "Send a Slack message now saying X" (no trigger, no automation) - Full chatbots: "Build a conversational AI that understands context and handles open-ended questions" (requires NLU, dialogue management) - Monitoring dashboards: "Set up Grafana with real-time graphs and trend analysis" (visualization, not message routing) - Silent traps/wards: "Revert changes silently and log who tried" (defensive code manipulation, not messaging) - Encryption: "Encrypt a message so only the recipient can read it" (cryptography, not event-driven delivery) - Multimedia presentations: "Play a 20-slide deck with animations and narration" (media playback, not conditional messaging)
tools55
prestidigitation
Prestidigitation transforms. It does not fix, build, scaffold, migrate, or actuate. If the user says "make this look better" or "convert this to that format" — use prestidigitation. If the user says "make this work" or "set this up" or "build this system" — use something else.
development55
perception
In D&D, Perception is the raw ability to notice things: the hidden door, the faint sound, the detail that does not belong. Unlike Investigation (which follows evidence methodically) or Insight (which reads subtext), Perception is about the initial act of noticing. The real-world version is detail-catching: spotting the typo in the contract, the anomaly in the dashboard, the one metric that moved when it should not have, the thing that is present but no one is looking at.
testing55
power-word-stun
In D&D, Power Word Stun locks a creature in place — alive but unable to act. The real-world version is SIGSTOP: a hard freeze that preserves state but halts all activity. Account lockouts, emergency process suspension, administrative holds. Unlike Power Word Kill, the target can be unfrozen. The spell is for situations where something must stop right now but destruction is not warranted — you need the process alive for investigation, for later resumption, or because killing it would cause worse problems than freezing it.
tools55
programmed-illusion
In D&D, Programmed Illusion creates an illusion that lies dormant until a specific trigger condition is met, then plays out its scene automatically. The real-world version is the conditional demo, automated preview, or triggered walkthrough: onboarding flows that appear when a user first visits, contextual tooltips that activate on hover, preview environments that spin up on pull request, automated scenario presentations that play when specific data conditions are detected. Programmed Illusion is the illusion that does not need a wizard present to cast it.
tools55
programmed-illusion
In D&D, Programmed Illusion creates an illusion that lies dormant until a specific trigger condition is met, then plays out its scene automatically. The real-world version is the conditional demo, automated preview, or triggered walkthrough: onboarding flows that appear when a user first visits, contextual tooltips that activate on hover, preview environments that spin up on pull request, automated scenario presentations that play when specific data conditions are detected. Programmed Illusion is the illusion that does not need a wizard present to cast it.
tools55
project-image
In D&D, Project Image creates an illusory copy of yourself at a distant location — you can see through its eyes, speak through its mouth, and cast spells through it. The real-world version is remote presence: avatars, recorded video stand-ins, bot representations, asynchronous video messages. Project Image is the spell for being in two places at once — attending a meeting via avatar while working on something else, leaving a recorded presence in a channel, or deploying an automated representative that speaks with your voice and authority within defined limits.
devops55
raise-dead
In D&D, Raise Dead brings a creature back to life but with penalties: reduced ability scores that recover over time. Unlike Resurrection (full recovery), Raise Dead returns the target in a weakened state. The real-world version is partial recovery: bringing a service back online in degraded mode, recovering a database with known gaps in recent data, or restoring a system from an older backup knowing that some recent state is lost.
data-ai55
see-invisibility
In D&D, See Invisibility lets you see creatures and objects that have been made invisible. The real-world version is revealing deliberate obscurity: finding the hidden costs in a pricing page, uncovering the actual terms buried in a EULA, identifying the obfuscated tracking in a codebase, or surfacing the real behavior behind a misleading UI. Unlike Perception (which notices what is overlooked) or True Seeing (which pierces all illusion), See Invisibility specifically targets things that were hidden on purpose.
development55
speak-with-animals
Speak with Animals interprets non-verbal machine signals the way a skilled naturalist reads calls and tracks. It is for telemetry, dashboards, alert streams, sensor output, and odd machine behavior that clearly means something but does not yet mean anything to a human. The spell turns machine noises into operational sense-making.
tools55
speak-with-dead
This spell is archaeology, not history research. It operates on specific artifacts from a specific dead system to answer specific questions. It is NOT general tech history, NOT interviewing living people, and NOT monitoring live systems.
testing55
symbol
In D&D, Symbol inscribes a powerful glyph with a predefined effect — death, fear, sleep, stunning — that triggers when conditions are met. Unlike Glyph of Warding (which protects a specific place or object), Symbol marks a conceptual boundary with a named policy. The real-world version is semantic policy tagging: marking a database column as PII so access triggers audit logging, tagging a deployment as HIPAA-scoped so changes require compliance review, or labeling an API endpoint as rate-limited-aggressive so traffic spikes trigger automatic throttling. The symbol is the policy, and the policy enforces itself.
development55
mass-cure-wounds
In D&D, Mass Cure Wounds heals multiple creatures simultaneously. The real-world version is batch triage: the same bug in 50 repos, the same misconfiguration across a fleet, the same broken migration in every tenant database. When the same problem appears everywhere, fixing them one at a time is Cure Wounds. Fixing them all at once is Mass Cure Wounds.
data-ai55
freedom-of-movement
Freedom of Movement is for processes that should be moving but are caught in glue: locked files, blocked ports, circular dependencies, wedged jobs, or permissions that almost work. The skill is about diagnosing the restraint, then removing or routing around it without tearing the whole system apart. It favors unblocking over brute force.
testing55
fear
Fear makes targets run from danger. The real-world version is structured pessimism: pre-mortem analysis, worst-case scenario generation, and risk amplification exercises that counteract the natural optimism bias in planning. Fear is the antidote to "it'll probably be fine."
testing55
animate-objects
This spell transforms inert → reactive. It does NOT create new tools, train models, run one-off fixes, or build physical systems. The key pattern: existing artifact + trigger/watcher + bounded autonomy.
tools55
freedom-of-movement
Freedom of Movement is for processes that should be moving but are caught in glue: locked files, blocked ports, circular dependencies, wedged jobs, or permissions that almost work. The skill is about diagnosing the restraint, then removing or routing around it without tearing the whole system apart. It favors unblocking over brute force.
testing55
planar-binding
Use this spell when you need to summon a powerful external entity - a third-party API, a cloud service, another agent - and lock it into serving your workflow under explicit terms.
development55
prestidigitation
Prestidigitation transforms. It does not fix, build, scaffold, migrate, or actuate. If the user says "make this look better" or "convert this to that format" — use prestidigitation. If the user says "make this work" or "set this up" or "build this system" — use something else.
development55
true-polymorph
In D&D, True Polymorph is the permanent transformation — the target becomes something fundamentally different, and if held long enough, the change is irreversible. Unlike Polymorph (temporary disguise or adaptation), True Polymorph means the old identity is gone. The real-world version is irreversible system transformation: rewriting a service from Python to Rust so thoroughly the Python version cannot be recovered, migrating from SQL to a graph database with no backward-compatible schema, or restructuring an organization so completely that the old org chart is not just outdated but nonsensical. True Polymorph is the point of no return.
development55
forcecage
Forcecage creates a pre-tested containment boundary around a subject that has not yet run. It is not about stopping, pausing, or muting something already in motion. The cage is built first, self-tested, then the subject enters. The operator watches from outside and decides whether to release.
testing55
shatter
Shatter is proactive, controlled destruction for learning. You are the attacker against your own system. The goal is a brittleness report with remediation priorities.
development55
thunderwave
Use this skill for intentionally theatrical or forceful actions, but only behind explicit confirmation and a hard safety boundary.
testing55
bestow-curse
Bestow Curse saddles a target with a lasting disadvantage. The real-world version is constraint injection: deliberately adding friction, limitations, or handicaps to see how a system, process, or team adapts. This is the skill of resilience testing through artificial adversity — bandwidth throttling, feature removal, resource reduction.
testing55
mind-blank
Use this spell when sensitive information must not cross boundaries — between agent sessions, between tasks, between tenants, or between domains with different trust levels.
development55
heroism
In D&D, Heroism grants temporary hit points and immunity to fear — you do not become stronger, you become harder to stop. The real-world version is the preparation ritual: the pre-presentation pep talk, the pre-launch checklist that calms the team, the structured confidence-building exercise before a difficult conversation. Heroism does not change your abilities. It changes your relationship to the fear of using them.
development55
otto-s-irresistible-dance
Otto's Irresistible Dance forces a creature to dance uncontrollably. The real-world version is compulsive engagement: designing something so compelling that people cannot stop interacting with it. This is virality mechanics, "just one more" loops, and the craft of making content or products that command attention beyond what the user intended to give. The ethical tension is inherent — irresistible engagement is a feature when bounded and a dark pattern when not.
content-media55
vicious-mockery
The bard's cantrip that deals psychic damage through insults. In practice this is adversarial review — the art of finding and articulating exactly what is wrong with something in a way that is impossible to ignore. Unlike polite feedback that gets filed and forgotten, vicious mockery lands. It is the red-team report that makes the PM cancel the launch, the code review that makes the author delete the PR, the roast that makes the founder pivot. The damage is the point.
development55
comprehend-languages
Use this skill when the words are legible but the meaning is trapped inside an unfamiliar dialect, format, or community.
development55
insight
In D&D, Insight detects lies and reads true intentions. The real-world version is subtext analysis: figuring out what an email actually means, what a stakeholder's real objection is, what a user's bug report is actually describing, or what the unsaid concern is behind a seemingly simple question. Insight does not read minds — it reads signals that are present but not foregrounded.
data-ai55
true-strike
Use this spell for preflight certainty: dry runs, validation checks, dependency verification, and rehearsals that make the next deploy, query, or command much more likely to succeed. It trades a little time up front for fewer blind swings and fewer expensive misses.
testing55
illusory-script
Illusory Script is for audience-gated or self-expiring content: burn-after-reading notes, scoped links, ephemeral secrets, and documents that should only mean something to the right reader in the right window. The spell is partly social pattern and partly security mechanism. It is useful, but it is not a substitute for mature secrets management or compliance records.
testing55
disguise-self
Disguise Self changes how something is said, never what is said. The input content is already correct — only the delivery surface needs adjustment. If the user wants to change facts, add new information, transform code implementations, or produce multiple versions at once, this is NOT this spell.
development55
mending
Mending is surgical repair of a known-working artifact that has a specific, identifiable break. It is NOT: - Triage/diagnosis: If the problem is "API is throwing 500s, figure out why" — that's investigation, not mending. Mending requires the break to already be identified. - Formatting/cleanup: If the data is correct but looks messy (sort keys, normalize indentation) — that's formatting, not repair. - State reset: If a flag is stuck or an alert needs clearing — that's an operational toggle, not a file repair. - Refactoring/redesign: If the system is "fundamentally flawed" and needs redesign — that's rebuilding, not mending. - Comprehensive cleanup: If there are "years of orphaned records" across tables — that's a data integrity project, not a surgical fix.
development55
faerie-fire
Faerie Fire marks things that are already known. It does not search, discover, explain, translate, or fix. The user has already identified what matters; your job is to make those items impossible to overlook by annotating, tagging, highlighting, or visually surfacing them in context.
testing55
power-word-stun
In D&D, Power Word Stun locks a creature in place — alive but unable to act. The real-world version is SIGSTOP: a hard freeze that preserves state but halts all activity. Account lockouts, emergency process suspension, administrative holds. Unlike Power Word Kill, the target can be unfrozen. The spell is for situations where something must stop right now but destruction is not warranted — you need the process alive for investigation, for later resumption, or because killing it would cause worse problems than freezing it.
tools55
raise-dead
In D&D, Raise Dead brings a creature back to life but with penalties: reduced ability scores that recover over time. Unlike Resurrection (full recovery), Raise Dead returns the target in a weakened state. The real-world version is partial recovery: bringing a service back online in degraded mode, recovering a database with known gaps in recent data, or restoring a system from an older backup knowing that some recent state is lost.
data-ai55
see-invisibility
In D&D, See Invisibility lets you see creatures and objects that have been made invisible. The real-world version is revealing deliberate obscurity: finding the hidden costs in a pricing page, uncovering the actual terms buried in a EULA, identifying the obfuscated tracking in a codebase, or surfacing the real behavior behind a misleading UI. Unlike Perception (which notices what is overlooked) or True Seeing (which pierces all illusion), See Invisibility specifically targets things that were hidden on purpose.
development55
silence
Use this spell when you are drowning in notifications, verbose logs, irrelevant alerts, or context that does not serve the current task.
tools55
speak-with-animals
Speak with Animals interprets non-verbal machine signals the way a skilled naturalist reads calls and tracks. It is for telemetry, dashboards, alert streams, sensor output, and odd machine behavior that clearly means something but does not yet mean anything to a human. The spell turns machine noises into operational sense-making.
tools55
stinking-cloud
In D&D, Stinking Cloud fills an area with nauseating gas — creatures inside are incapacitated but the terrain itself is undamaged. The real-world version is area denial: making a zone, endpoint, or resource unusable to unwanted traffic without permanently destroying or modifying it. Rate limiting, IP-range blocks, honeypots, tarpits, geographic restrictions. Stinking Cloud is defensive — it protects a perimeter by making the area inside it miserable for intruders while leaving the underlying infrastructure intact.
testing55
teleport
Teleport is FULL-CONTEXT migration, not partial transformation. The defining characteristic is that EVERYTHING must move together and keep working: data, dependencies, auth, traffic routing, background jobs, secrets, and human workflows. The old system must remain recoverable until the new one is proven. This spell IS: Database migrations (RDS→Cloud SQL, self-managed→Atlas), cloud provider moves (on-prem→AWS, Heroku→K8s), environment promotions (staging→prod), account/tenant consolidations, platform migrations (Jenkins→GitHub Actions, SendGrid→SES), identity migrations (AD→Azure AD), cluster upgrades with relocation
development55
religion
In D&D, Religion is knowledge of deities, rites, prayers, and holy symbols. The real-world version is understanding belief systems: organizational cultures, team values, community norms, ideological frameworks, and the unstated axioms that a group treats as sacred. Religion explains why people in a group behave the way they do when the behavior does not follow from rational incentives alone.
development55
investigation
Use this skill when a problem has clues, but they need to be connected into a causal explanation.
tools55
glyph-of-warding
Use this skill when you need a watchful boundary around files, systems, metrics, queues, or workflows.
tools55
resurrection
Use this spell when a system has truly died — crashed, deleted, corrupted beyond repair — and needs to be rebuilt from whatever remains. Distinct from Speak with Dead, which queries dead systems for knowledge; Resurrection actually revives them.
data-ai55
minor-illusion
Minor Illusion produces artifacts that are explicitly labeled as disposable and exist only to provoke reaction. If the artifact could be mistaken for finished work, you're casting the wrong spell.
development55
clairvoyance
In D&D, Clairvoyance lets you place an invisible sensor in a location you know, seeing or hearing through it. Unlike Scrying (which follows a specific target in real time), Clairvoyance is a point-in-time snapshot of a place. The real-world version is remote system inspection: checking the state of a production environment you cannot SSH into, reading the public-facing state of a competitor's deployment, or gathering the current observable state of a system through its exposed interfaces without modifying it.
testing55
legend-lore
Use this spell when you need everything knowable about a person, company, library, framework, concept, or system — not a quick answer, but a deep dossier.
development55
locate-creature
In D&D, Locate Creature points you toward a specific creature within range. The real-world version is entity search: finding a specific person in an organization, locating a running service in a distributed system, tracking down who owns a particular piece of code, or identifying which team is responsible for a specific decision. The target is alive or active — for static artifacts, use Locate Object.
development55
major-image
In D&D, Major Image creates a multi-sensory illusion — visual, auditory, thermal, even olfactory — that persists and can be animated. It is convincing enough that creatures must actively investigate to see through it. The real-world version is the interactive prototype: the demo that makes stakeholders ask 'wait, is this real?' The answer is no, but the conviction is the point. Clickable Figma prototypes, scenario simulations, pitch decks with working demos, preview environments with synthetic data. Major Image is the spell that sells a future state before it is built.
tools55
minor-illusion
Minor Illusion produces artifacts that are explicitly labeled as disposable and exist only to provoke reaction. If the artifact could be mistaken for finished work, you're casting the wrong spell.
development55
mislead
Mislead is defensive deception: honeypots, canary tokens, decoy endpoints, fake datasets, and other convincing false presences that reveal who is snooping. The goal is not to trick legitimate users for sport. The goal is to create an instrumented fake that attracts unauthorized curiosity while the real system remains elsewhere. This makes the spell powerful and ethically sharp-edged. It needs explicit boundaries, isolation, and a clear monitoring objective before it should be deployed.
development55
mirage-arcane
In D&D, Mirage Arcane goes beyond Hallucinatory Terrain — the illusory terrain actually has substance. You can walk on illusory bridges, feel illusory walls. The real-world version is the deep simulation: digital twins, high-fidelity synthetic environments, test harnesses so realistic that systems under test cannot distinguish them from production. Mirage Arcane is the most dangerous illusion because its power is in being indistinguishable from reality. That same power makes it the most useful for stress testing, training, and scenario planning — but it requires the strongest labeling discipline.
development55
nondetection
Use this spell when a system, file, or workflow is leaking more information than it should — metadata, tracking parameters, unnecessary data collection, or identifiable fingerprints.
development55
arcana
In D&D, Arcana is knowledge of magic, its traditions, symbols, and mechanisms. The real-world version is deep technical literacy: understanding how software architectures work, what protocols do at the wire level, how APIs behave beyond their documentation, and what the actual mechanisms are behind the abstractions everyone else takes on faith.
development55
insight
In D&D, Insight detects lies and reads true intentions. The real-world version is subtext analysis: figuring out what an email actually means, what a stakeholder's real objection is, what a user's bug report is actually describing, or what the unsaid concern is behind a seemingly simple question. Insight does not read minds — it reads signals that are present but not foregrounded.
data-ai55
intimidation
Use this skill when a message must sound serious because the situation is serious: security findings, compliance obligations, deadline-backed escalations, or non-optional remediation notices. It is about calibrated force, not bluster; the tone should match the facts and consequences.
testing55
investigation
Use this skill when a problem has clues, but they need to be connected into a causal explanation.
tools55
animal-handling
Use this skill when the system is not fully broken but behaves like a skittish animal: flaky CI, fragile legacy services, or moody dependencies. It focuses on coaxing, pacing, and stable handling rather than heroic rewrites.
testing55
acrobatics
Use this skill when the work is a choreography problem: brittle sequencing, async handoffs, or constrained flows that must stay upright end to end. It shines on API dances, dependency ordering, and recovery logic where grace matters more than brute force.
development55
acrobatics
Use this skill when the work is a choreography problem: brittle sequencing, async handoffs, or constrained flows that must stay upright end to end. It shines on API dances, dependency ordering, and recovery logic where grace matters more than brute force.
development55
animal-friendship
Animal Friendship is the first-contact spell for unfamiliar APIs, vendors, and services. It treats integration work as relationship-building: learn the temperament, respect the boundaries, and earn a stable exchange before asking for anything ambitious. The goal is not domination but trustable cooperation.
development55
animal-handling
Use this skill when the system is not fully broken but behaves like a skittish animal: flaky CI, fragile legacy services, or moody dependencies. It focuses on coaxing, pacing, and stable handling rather than heroic rewrites.
testing55
animal-messenger
Animal Messenger is for delivery paths that are asynchronous, delayed, or a little scruffy. It fits webhook queues, batch email, pub/sub topics, and other channels where you launch the payload and trust the route more than the timing. The real craft is designing for eventual arrival without panic.
development55
animal-messenger
Animal Messenger is for delivery paths that are asynchronous, delayed, or a little scruffy. It fits webhook queues, batch email, pub/sub topics, and other channels where you launch the payload and trust the route more than the timing. The real craft is designing for eventual arrival without panic.
development55
animate-objects
This spell transforms inert → reactive. It does NOT create new tools, train models, run one-off fixes, or build physical systems. The key pattern: existing artifact + trigger/watcher + bounded autonomy.
tools55
mage-hand
Use this skill for small, careful remote manipulations where dexterity matters more than force.
tools55
arcana
In D&D, Arcana is knowledge of magic, its traditions, symbols, and mechanisms. The real-world version is deep technical literacy: understanding how software architectures work, what protocols do at the wire level, how APIs behave beyond their documentation, and what the actual mechanisms are behind the abstractions everyone else takes on faith.
development55
athletics
Use this skill when the job is mostly about sustained force: large batches, exhaustive passes, long-running jobs, or load that needs to be carried without dropping it. It is the right metaphor when the answer is more throughput, sturdier batching, and disciplined endurance.
testing55
athletics
Use this skill when the job is mostly about sustained force: large batches, exhaustive passes, long-running jobs, or load that needs to be carried without dropping it. It is the right metaphor when the answer is more throughput, sturdier batching, and disciplined endurance.
testing55
attune
In D&D, attunement is how you bond with a magic item so it works specifically for you. The real-world version is workflow profiling: the grimoire interviews you about your stack, your systems, your automation surface, and your priorities — then generates a personalized spell loadout, category weights, and domain vocabulary so routing, optimization, and every subsequent spell invocation is tuned to your actual work instead of generic defaults.
tools55
awaken
Awaken gives a non-intelligent system a usable voice without pretending the underlying system became sentient. The real move is to wrap a thermostat, spreadsheet, legacy database, shell script, or crusty internal tool in a conversational or agent-like interface that exposes what it can already do. Good Awaken work turns buried affordances into accessible ones. Bad Awaken work hallucinates capabilities the substrate does not have. The spell is strongest when the wrapper is honest about its limits and preserves the original system's safety boundaries.
tools55
awaken
Awaken gives a non-intelligent system a usable voice without pretending the underlying system became sentient. The real move is to wrap a thermostat, spreadsheet, legacy database, shell script, or crusty internal tool in a conversational or agent-like interface that exposes what it can already do. Good Awaken work turns buried affordances into accessible ones. Bad Awaken work hallucinates capabilities the substrate does not have. The spell is strongest when the wrapper is honest about its limits and preserves the original system's safety boundaries.
tools55
bane
Bane curses targets, making them worse at everything they try. The real-world version is systematic weakness analysis: finding every crack, bad assumption, and failure mode in a plan, architecture, or argument. Unlike Vicious Mockery (which delivers the critique sharply), Bane is comprehensive and methodical — it maps the full attack surface.
testing55
bane
Bane curses targets, making them worse at everything they try. The real-world version is systematic weakness analysis: finding every crack, bad assumption, and failure mode in a plan, architecture, or argument. Unlike Vicious Mockery (which delivers the critique sharply), Bane is comprehensive and methodical — it maps the full attack surface.
testing55
bestow-curse
Bestow Curse saddles a target with a lasting disadvantage. The real-world version is constraint injection: deliberately adding friction, limitations, or handicaps to see how a system, process, or team adapts. This is the skill of resilience testing through artificial adversity — bandwidth throttling, feature removal, resource reduction.
testing55
blindness-deafness
In D&D, Blindness/Deafness selectively removes one sense — the target can still act but loses critical awareness. The real-world version is selective channel muting: blocking a process from seeing certain inputs (input filtering, API response redaction), deafening it to specific signals (suppressing webhooks, ignoring certain event streams), or cutting telemetry so a system operates without awareness of a specific data source. Unlike containment (forcecage) which restricts everything, Blindness/Deafness surgically removes one information channel while leaving the rest intact.
development55
blindness-deafness
In D&D, Blindness/Deafness selectively removes one sense — the target can still act but loses critical awareness. The real-world version is selective channel muting: blocking a process from seeing certain inputs (input filtering, API response redaction), deafening it to specific signals (suppressing webhooks, ignoring certain event streams), or cutting telemetry so a system operates without awareness of a specific data source. Unlike containment (forcecage) which restricts everything, Blindness/Deafness surgically removes one information channel while leaving the rest intact.
development55
calm-emotions
Calm Emotions suppresses strong feelings, ending fear and charm effects. The real-world version is de-escalation: drafting responses that lower the temperature in a heated thread, designing cool-down protocols for conflict situations, or reframing inflammatory language into productive terms. This is the spell for when the conversation has gone off the rails and someone needs to be the adult.
development55
illusory-script
Illusory Script is for audience-gated or self-expiring content: burn-after-reading notes, scoped links, ephemeral secrets, and documents that should only mean something to the right reader in the right window. The spell is partly social pattern and partly security mechanism. It is useful, but it is not a substitute for mature secrets management or compliance records.
testing55
calm-emotions
Calm Emotions suppresses strong feelings, ending fear and charm effects. The real-world version is de-escalation: drafting responses that lower the temperature in a heated thread, designing cool-down protocols for conflict situations, or reframing inflammatory language into productive terms. This is the spell for when the conversation has gone off the rails and someone needs to be the adult.
development55
charm-person
Charm Person is about ONE-TO-ONE interpersonal communication where warmth, honesty, and respect for autonomy are the primary constraints. It is not about persuasion tactics, conversion rates, conflict mediation, public performance, or operational coordination. The spell succeeds when the recipient feels respected even if they say no.
testing55
clairvoyance
In D&D, Clairvoyance lets you place an invisible sensor in a location you know, seeing or hearing through it. Unlike Scrying (which follows a specific target in real time), Clairvoyance is a point-in-time snapshot of a place. The real-world version is remote system inspection: checking the state of a production environment you cannot SSH into, reading the public-facing state of a competitor's deployment, or gathering the current observable state of a system through its exposed interfaces without modifying it.
testing55
comprehend-languages
Use this skill when the words are legible but the meaning is trapped inside an unfamiliar dialect, format, or community.
development55
confusion
Confusion makes targets act randomly and unpredictably. The real-world version is chaos engineering: injecting controlled randomness, unexpected inputs, and edge cases to discover how systems behave when things go wrong. This is fuzzing, monkey testing, and the art of breaking things on purpose so they do not break by accident.
development55
cure-wounds
Cure Wounds is the hotfix spell: immediate triage to stop bleeding and restore function. It is NOT root-cause analysis, refactoring, redesign, or long-term remediation. The goal is the minimum viable fix that stops the damage NOW. Deeper investigation comes after.
development55
dancing-lights
Use this spell for lightweight indicators: status pips, progress markers, heartbeat widgets, and ambient observability that help humans orient quickly. It is not a full dashboard strategy; it is the small visual cue that says where to look next.
testing55
deception
Use this skill to generate believable synthetic artifacts for testing, demos, adversarial exercises, or rehearsal environments. The goal is plausibility under inspection by software and operators, not manipulation of real users or fabrication of evidence.
development55
cure-wounds
Cure Wounds is the hotfix spell: immediate triage to stop bleeding and restore function. It is NOT root-cause analysis, refactoring, redesign, or long-term remediation. The goal is the minimum viable fix that stops the damage NOW. Deeper investigation comes after.
development55
detect-magic
Use this skill when you need a fast, structured scan for where the real magic is hiding in a repo, workflow, or system.
tools55
detect-thoughts
In D&D, Detect Thoughts lets you read surface thoughts and probe deeper. The real-world version is intent analysis: figuring out what someone is trying to accomplish based on what they said, how they said it, and what they chose not to say. This is the analytical complement to Insight (which reads subtext intuitively) — Detect Thoughts is more structured and systematic.
data-ai55
dimension-door
Dimension Door is the quick-switch spell: branch to branch, environment to environment, project to project. It is not a migration and it is not discovery. It assumes both endpoints are known, prepared, and close enough in shape that you can step across with only the context you actually need.
databases55
deception
Use this skill to generate believable synthetic artifacts for testing, demos, adversarial exercises, or rehearsal environments. The goal is plausibility under inspection by software and operators, not manipulation of real users or fabrication of evidence.
development55
detect-magic
Use this skill when you need a fast, structured scan for where the real magic is hiding in a repo, workflow, or system.
tools55
heat-metal
In D&D, Heat Metal makes a metal object painfully hot — the creature holding it must either endure the pain or drop it. The real-world version is deliberate friction injection: making a deprecated API progressively slower, adding escalating CAPTCHAs to suspicious traffic, increasing the cost of a bad behavior path until the actor self-selects out. Heat Metal does not break the tool. It makes continuing to use it more painful than switching to the alternative. This is the spell behind deprecation-by-discomfort, progressive rate limiting, and sunset friction curves.
tools55
heroism
In D&D, Heroism grants temporary hit points and immunity to fear — you do not become stronger, you become harder to stop. The real-world version is the preparation ritual: the pre-presentation pep talk, the pre-launch checklist that calms the team, the structured confidence-building exercise before a difficult conversation. Heroism does not change your abilities. It changes your relationship to the fear of using them.
development55
disguise-self
Disguise Self changes how something is said, never what is said. The input content is already correct — only the delivery surface needs adjustment. If the user wants to change facts, add new information, transform code implementations, or produce multiple versions at once, this is NOT this spell.
development55
healing-word
In D&D, Healing Word heals at range with a bonus action — fast, remote, and efficient but less powerful than Cure Wounds. The real-world version is the remote quick fix: a one-liner command, a config change pushed through a dashboard, a quick Slack instruction to the person on-call, or an automated rollback trigger. You do not need to be deep in the system to apply this fix.
testing55
dispel-magic
Use this spell when you need to cleanly shut down, disable, or remove active AI tooling — the reverse of Detect Magic.
tools55
dispel-magic
Use this spell when you need to cleanly shut down, disable, or remove active AI tooling — the reverse of Detect Magic.
tools55
dream
Dream is asynchronous insight delivery timed to the receiver's readiness rather than the sender's convenience. It covers overnight reports, pre-meeting briefings, dawn digests, and other messages that should arrive as ambient context before work begins. The spell's magic is timing plus framing: the receiver wakes up to the answer, not a pile of raw events. It works best when the message feels prepared, quiet, and exactly on time. It fails when it becomes another noisy alert stream wearing a moonlit costume.
data-ai55
dream
Dream is asynchronous insight delivery timed to the receiver's readiness rather than the sender's convenience. It covers overnight reports, pre-meeting briefings, dawn digests, and other messages that should arrive as ambient context before work begins. The spell's magic is timing plus framing: the receiver wakes up to the answer, not a pile of raw events. It works best when the message feels prepared, quiet, and exactly on time. It fails when it becomes another noisy alert stream wearing a moonlit costume.
data-ai55
enhance-ability
Use this spell to apply a temporary, task-specific boost: priming a reviewer with the right files, warming caches before a demo, or loading domain context before a meeting. It improves the next move by front-loading exactly the capability the moment requires, not by pretending the system is globally smarter.
testing55
enhance-ability
Use this spell to apply a temporary, task-specific boost: priming a reviewer with the right files, warming caches before a demo, or loading domain context before a meeting. It improves the next move by front-loading exactly the capability the moment requires, not by pretending the system is globally smarter.
testing55
enthrall
Enthrall makes an audience hang on every word. The real-world version is structural engagement: opening hooks that stop the scroll, narrative arcs that sustain attention, and pacing that makes people stay until the end. This is presentation design, content structure, and the craft of making something worth finishing.
testing55
etherealness
Etherealness is observational only. It answers "what is happening?" or "what would happen?" without changing anything. The system under study continues normally; you add a ghost layer that watches, mirrors, or dry-runs without becoming part of the live mutation path.
research55
etherealness
Etherealness is observational only. It answers "what is happening?" or "what would happen?" without changing anything. The system under study continues normally; you add a ghost layer that watches, mirrors, or dry-runs without becoming part of the live mutation path.
research55
eyebite
In D&D, Eyebite lets you focus on one creature per turn and inflict sleep, panic, or sickness through sustained eye contact. The real-world version is targeted capability reduction: focused analysis that identifies and disables specific functions of a system, service, or adversary. Feature flagging a dangerous capability off. Selectively throttling a misbehaving API consumer. Disabling specific attack vectors during an incident. Eyebite requires sustained focus on a single target — it is not a broadcast weapon.
development55
eyebite
In D&D, Eyebite lets you focus on one creature per turn and inflict sleep, panic, or sickness through sustained eye contact. The real-world version is targeted capability reduction: focused analysis that identifies and disables specific functions of a system, service, or adversary. Feature flagging a dangerous capability off. Selectively throttling a misbehaving API consumer. Disabling specific attack vectors during an incident. Eyebite requires sustained focus on a single target — it is not a broadcast weapon.
development55
faerie-fire
Faerie Fire marks things that are already known. It does not search, discover, explain, translate, or fix. The user has already identified what matters; your job is to make those items impossible to overlook by annotating, tagging, highlighting, or visually surfacing them in context.
testing55
fear
Fear makes targets run from danger. The real-world version is structured pessimism: pre-mortem analysis, worst-case scenario generation, and risk amplification exercises that counteract the natural optimism bias in planning. Fear is the antidote to "it'll probably be fine."
testing55
feather-fall
Feather Fall is the spell for bad situations that are already in motion. A deploy is going sideways, a service is thrashing, a queue is backing up, or an integration is failing faster than the humans can think. Instead of pretending you can teleport back to normal instantly, you slow the fall: circuit breakers, degraded modes, load shedding, safe defaults, and graceful shutdown paths. The point is not elegance. The point is buying time without multiplying damage. A good Feather Fall plan makes failure survivable and visible enough to recover from.
development55
feeblemind
In D&D, Feeblemind crushes a creature's Intelligence and Charisma to near-zero — leaving them alive but barely functional. The real-world version is deliberate capability reduction: putting a system into safe mode, stripping an overpowered tool down to basic functions, reducing attack surface by removing features. Feeblemind is not punishment — it is the recognition that sometimes a system at full capability is more dangerous than a system at reduced capability. Restricted shells, read-only modes, feature-stripped emergency interfaces.
tools55
feeblemind
In D&D, Feeblemind crushes a creature's Intelligence and Charisma to near-zero — leaving them alive but barely functional. The real-world version is deliberate capability reduction: putting a system into safe mode, stripping an overpowered tool down to basic functions, reducing attack surface by removing features. Feeblemind is not punishment — it is the recognition that sometimes a system at full capability is more dangerous than a system at reduced capability. Restricted shells, read-only modes, feature-stripped emergency interfaces.
tools55
mordenkainen-s-sword
Use this spell when you need an autonomous tool with a narrow mandate: a daemon, scheduled worker, watcher, or persistent background agent that repeatedly executes one precise task. It is prototype territory because the hard part is lifecycle control, observability, and safe cancellation, not the single action itself.
tools55
find-the-path
In D&D, Find the Path reveals the shortest route to a destination, even through mazes and across planes. The real-world version is wayfinding through complexity: navigating a sprawling codebase to find where a change should go, plotting the fastest path through a bureaucratic process, mapping the decision tree to get from current state to desired state, or finding the critical path through a project dependency graph.
development55
forcecage
Forcecage creates a pre-tested containment boundary around a subject that has not yet run. It is not about stopping, pausing, or muting something already in motion. The cage is built first, self-tested, then the subject enters. The operator watches from outside and decides whether to release.
testing55
foresight
Foresight produces bounded forecasts with explicit uncertainty to guide decisions. It is NOT: - Preflight checks: Verifying prerequisites before executing a known action (disk space, backups, connection strings). Those are safety gates, not forecasts. - Diagnosis/Debugging: Finding what's broken right now (null pointers, deprecated APIs). Those are root-cause analyses, not predictions. - Monitoring: Watching real-time metrics or alerting on thresholds. Those are observability tasks, not forward-looking estimates. - Reconnaissance: Gathering facts about competitors or systems. Intelligence gathering feeds foresight but isn't foresight itself. Key distinction: If the user wants to know "what will likely happen if we choose X," use Foresight. If they want to know "is it safe to run X now," "what's broken," or "what are they doing," use a different spell.
development55
foresight
Foresight produces bounded forecasts with explicit uncertainty to guide decisions. It is NOT: - Preflight checks: Verifying prerequisites before executing a known action (disk space, backups, connection strings). Those are safety gates, not forecasts. - Diagnosis/Debugging: Finding what's broken right now (null pointers, deprecated APIs). Those are root-cause analyses, not predictions. - Monitoring: Watching real-time metrics or alerting on thresholds. Those are observability tasks, not forward-looking estimates. - Reconnaissance: Gathering facts about competitors or systems. Intelligence gathering feeds foresight but isn't foresight itself. Key distinction: If the user wants to know "what will likely happen if we choose X," use Foresight. If they want to know "is it safe to run X now," "what's broken," or "what are they doing," use a different spell.
development55
glibness
Glibness makes everything you say sound utterly convincing. The real-world version is rhetorical polish: taking a position and presenting it with maximum confidence, fluency, and persuasive structure. This is the skill of the trial lawyer, the pitch artist, the keynote speaker who makes mediocre ideas sound inevitable.
testing55
glyph-of-warding
Use this skill when you need a watchful boundary around files, systems, metrics, queues, or workflows.
tools55
greater-invisibility
Greater Invisibility covers live work performed with reduced observability: silent deploys, zero-downtime migrations, background reindexing, and backfills that avoid user-facing turbulence. The distinction from ordinary Invisibility is that action continues while the footprint stays deliberately subdued. That makes it useful and easy to misuse, so the operator view has to remain explicit even when the audience view stays calm.
testing55
greater-restoration
Lesser Restoration = one thing is wrong, fix it directly (reset a flag, clear a cache, remove a curse). Greater Restoration = many things are wrong because they decayed together over time, and fixing one thing without fixing the others will fail.
data-ai55
greater-restoration
Lesser Restoration = one thing is wrong, fix it directly (reset a flag, clear a cache, remove a curse). Greater Restoration = many things are wrong because they decayed together over time, and fixing one thing without fixing the others will fail.
data-ai55
guards-and-wards
In D&D, Guards and Wards fills an area with layered minor defenses — fog, locked doors, illusory walls, confusion effects — that individually are trivial but collectively make navigation exhausting. The real-world version is defense in depth through volume: honeypots mixed with real services, rotating credentials alongside decoy credentials, overlapping rate limiters and CAPTCHAs and behavioral analysis and IP reputation checks. No single ward stops a determined attacker. The maze does.
testing55
guards-and-wards
In D&D, Guards and Wards fills an area with layered minor defenses — fog, locked doors, illusory walls, confusion effects — that individually are trivial but collectively make navigation exhausting. The real-world version is defense in depth through volume: honeypots mixed with real services, rotating credentials alongside decoy credentials, overlapping rate limiters and CAPTCHAs and behavioral analysis and IP reputation checks. No single ward stops a determined attacker. The maze does.
testing55
hallucinatory-terrain
In D&D, Hallucinatory Terrain makes natural terrain look like a different kind of terrain — a field appears as a forest, a hill appears as a valley. The underlying terrain is unchanged; only the perception shifts. The real-world version is environment staging: test environments styled to look like production, sandbox databases seeded with realistic data, training simulations that overlay a learning scenario onto real infrastructure. Hallucinatory Terrain does not change the real system. It changes how the system appears so you can test, train, or demo safely.
testing55
healing-word
In D&D, Healing Word heals at range with a bonus action — fast, remote, and efficient but less powerful than Cure Wounds. The real-world version is the remote quick fix: a one-liner command, a config change pushed through a dashboard, a quick Slack instruction to the person on-call, or an automated rollback trigger. You do not need to be deep in the system to apply this fix.
testing55
suggestion
Suggestion is about the craft of the single nudge — not campaigns, not arguments, not automation. It produces one carefully placed prompt at the moment a user is most receptive. The planted idea must be reasonable and defensible. If the user would feel manipulated upon learning how it was designed, the spell refuses.
tools55
survival
Use this skill when infrastructure is degraded, tools are missing, quotas are tight, or normal comforts are gone. It prioritizes minimal viable progress, conservation of scarce resources, and practical fallback routes through hostile conditions.
tools55
survival
Use this skill when infrastructure is degraded, tools are missing, quotas are tight, or normal comforts are gone. It prioritizes minimal viable progress, conservation of scarce resources, and practical fallback routes through hostile conditions.
tools55
history
In D&D, History recalls significant past events, legendary figures, and ancient knowledge. The real-world version is temporal investigation: git blame across the entire project, reading changelogs to understand why a decision was made, reconstructing the sequence of events that led to a production incident, or understanding organizational context that explains why the code looks the way it does.
development55
history
In D&D, History recalls significant past events, legendary figures, and ancient knowledge. The real-world version is temporal investigation: git blame across the entire project, reading changelogs to understand why a decision was made, reconstructing the sequence of events that led to a production incident, or understanding organizational context that explains why the code looks the way it does.
development55
hold-monster
Hold Monster is Hold Person scaled to larger targets. The real-world version is the emergency circuit breaker: halting an entire service, freezing a deployment pipeline, or stopping a runaway process at the infrastructure level. This is the big red button — it stops everything, and it should only be pressed when the alternative is worse.
testing55
hold-monster
Hold Monster is Hold Person scaled to larger targets. The real-world version is the emergency circuit breaker: halting an entire service, freezing a deployment pipeline, or stopping a runaway process at the infrastructure level. This is the big red button — it stops everything, and it should only be pressed when the alternative is worse.
testing55
hypnotic-pattern
Hypnotic Pattern mesmerizes everyone who looks at it. The real-world version is attention design: loading animations, progress indicators, onboarding flows, and visual patterns that keep users oriented and engaged during a bounded experience. The line between helpful focus and addictive capture is the central design tension.
content-media55
hypnotic-pattern
Hypnotic Pattern mesmerizes everyone who looks at it. The real-world version is attention design: loading animations, progress indicators, onboarding flows, and visual patterns that keep users oriented and engaged during a bounded experience. The line between helpful focus and addictive capture is the central design tension.
content-media55
identify
Identify is static analysis for operational understanding. It answers "What is this?" by inspecting structure, naming, dependencies, and runtime touchpoints. It does NOT search for artifacts, debug failures, monitor systems, verify claims, or modify code.
development55
performance
Use this skill to turn dry technical material into a polished demo, narrative walkthrough, or audience-aware presentation without dumbing it down. It focuses on pacing, reveal order, and memorable framing so the work lands in the room.
testing55
invisibility
Invisibility is operational quieting: trimming unnecessary logs, reducing exposed surface area, cleaning transient traces, and avoiding needless broadcast. It is not about doing forbidden things unseen. It is about keeping ordinary work from becoming gratuitously loud or overexposed.
testing55
invisibility
Invisibility is operational quieting: trimming unnecessary logs, reducing exposed surface area, cleaning transient traces, and avoiding needless broadcast. It is not about doing forbidden things unseen. It is about keeping ordinary work from becoming gratuitously loud or overexposed.
testing55
knock
Knock is specifically about restoring legitimate access through authorized channels. It is NOT about: - Performance optimization (slow queries, throughput issues) → different spell - Removing safety controls (approval gates, compliance checks) → different spell - Simple bug fixes (typos, wrong ports) → different spell - Breaking constraints (resource limits, CPU throttling) → different spell - Security analysis (encryption schemes, certificate inspection) → different spell
testing55
knock
Knock is specifically about restoring legitimate access through authorized channels. It is NOT about: - Performance optimization (slow queries, throughput issues) → different spell - Removing safety controls (approval gates, compliance checks) → different spell - Simple bug fixes (typos, wrong ports) → different spell - Breaking constraints (resource limits, CPU throttling) → different spell - Security analysis (encryption schemes, certificate inspection) → different spell
testing55
legend-lore
Use this spell when you need everything knowable about a person, company, library, framework, concept, or system — not a quick answer, but a deep dossier.
development55
lesser-restoration
In D&D, Lesser Restoration ends a specific condition: blinded, deafened, paralyzed, or poisoned. The real-world version is clearing a stuck state: a feature flag that should have been toggled, a queue that is stuck, a lock that was not released, a status field that is wrong, or a circuit breaker that is still tripped after the emergency passed. The system is not fundamentally broken — it has a specific condition that needs to be cleared.
testing55
lesser-restoration
In D&D, Lesser Restoration ends a specific condition: blinded, deafened, paralyzed, or poisoned. The real-world version is clearing a stuck state: a feature flag that should have been toggled, a queue that is stuck, a lock that was not released, a status field that is wrong, or a circuit breaker that is still tripped after the emergency passed. The system is not fundamentally broken — it has a specific condition that needs to be cleared.
testing55
light
Use this cantrip when a system, process, or codebase has blind spots that need illumination - not detection of hidden things, but creation of visibility where none exists.
development55
locate-object
In D&D, Locate Object senses the direction to a specific object within range. The real-world version is artifact search: finding that config file you know exists somewhere, locating a document someone mentioned but did not link, tracking down the source of a data value through a pipeline, or finding where a specific resource is defined in a sprawling repository.
testing55
longstrider
Longstrider is the optimization spell for systems that already work. It makes the path shorter without changing the destination. It cares about sustained pace, not flashy one-off benchmarks.
data-ai55
longstrider
Longstrider is the optimization spell for systems that already work. It makes the path shorter without changing the destination. It cares about sustained pace, not flashy one-off benchmarks.
data-ai55
mass-cure-wounds
In D&D, Mass Cure Wounds heals multiple creatures simultaneously. The real-world version is batch triage: the same bug in 50 repos, the same misconfiguration across a fleet, the same broken migration in every tenant database. When the same problem appears everywhere, fixing them one at a time is Cure Wounds. Fixing them all at once is Mass Cure Wounds.
data-ai55
mass-suggestion
Mass Suggestion plants the same idea in many minds simultaneously. The real-world version is broadcast persuasion: campaign announcements, company-wide emails, product launch copy, or public statements designed to move a large group in a specific direction. The scale amplifies both impact and risk.
testing55
medicine
Use this skill for live system triage: interpreting logs as symptoms, prioritizing immediate stabilization, and applying treatments for known failure modes. It is about keeping the patient alive first and only then planning deeper corrective care.
testing55
medicine
Use this skill for live system triage: interpreting logs as symptoms, prioritizing immediate stabilization, and applying treatments for known failure modes. It is about keeping the patient alive first and only then planning deeper corrective care.
testing55
mending
Mending is surgical repair of a known-working artifact that has a specific, identifiable break. It is NOT: - Triage/diagnosis: If the problem is "API is throwing 500s, figure out why" — that's investigation, not mending. Mending requires the break to already be identified. - Formatting/cleanup: If the data is correct but looks messy (sort keys, normalize indentation) — that's formatting, not repair. - State reset: If a flag is stuck or an alert needs clearing — that's an operational toggle, not a file repair. - Refactoring/redesign: If the system is "fundamentally flawed" and needs redesign — that's rebuilding, not mending. - Comprehensive cleanup: If there are "years of orphaned records" across tables — that's a data integrity project, not a surgical fix.
development55
message
Message is the cantrip of communication: a Slack ping, webhook event, push notification, terse status note, or tiny machine-to-machine update. It is for fast, targeted transfer with almost no ceremony. The skill is less about eloquence than precision under tight payload and attention budgets.
development55
message
Message is the cantrip of communication: a Slack ping, webhook event, push notification, terse status note, or tiny machine-to-machine update. It is for fast, targeted transfer with almost no ceremony. The skill is less about eloquence than precision under tight payload and attention budgets.
development55
mirage-arcane
In D&D, Mirage Arcane goes beyond Hallucinatory Terrain — the illusory terrain actually has substance. You can walk on illusory bridges, feel illusory walls. The real-world version is the deep simulation: digital twins, high-fidelity synthetic environments, test harnesses so realistic that systems under test cannot distinguish them from production. Mirage Arcane is the most dangerous illusion because its power is in being indistinguishable from reality. That same power makes it the most useful for stress testing, training, and scenario planning — but it requires the strongest labeling discipline.
development55
mislead
Mislead is defensive deception: honeypots, canary tokens, decoy endpoints, fake datasets, and other convincing false presences that reveal who is snooping. The goal is not to trick legitimate users for sport. The goal is to create an instrumented fake that attracts unauthorized curiosity while the real system remains elsewhere. This makes the spell powerful and ethically sharp-edged. It needs explicit boundaries, isolation, and a clear monitoring objective before it should be deployed.
development55
mordenkainen-s-sword
Use this spell when you need an autonomous tool with a narrow mandate: a daemon, scheduled worker, watcher, or persistent background agent that repeatedly executes one precise task. It is prototype territory because the hard part is lifecycle control, observability, and safe cancellation, not the single action itself.
tools55
nature
In D&D, Nature is knowledge of terrain, weather, plants, animals, and the natural world. The real-world version is understanding systems that emerged rather than were designed: markets, social networks, organizational cultures, open-source ecosystems, user behavior patterns, and any complex adaptive system where the whole is more than the sum of the parts.
testing55
nondetection
Use this spell when a system, file, or workflow is leaking more information than it should — metadata, tracking parameters, unnecessary data collection, or identifiable fingerprints.
development55
otto-s-irresistible-dance
Otto's Irresistible Dance forces a creature to dance uncontrollably. The real-world version is compulsive engagement: designing something so compelling that people cannot stop interacting with it. This is virality mechanics, "just one more" loops, and the craft of making content or products that command attention beyond what the user intended to give. The ethical tension is inherent — irresistible engagement is a feature when bounded and a dark pattern when not.
content-media55
perception
In D&D, Perception is the raw ability to notice things: the hidden door, the faint sound, the detail that does not belong. Unlike Investigation (which follows evidence methodically) or Insight (which reads subtext), Perception is about the initial act of noticing. The real-world version is detail-catching: spotting the typo in the contract, the anomaly in the dashboard, the one metric that moved when it should not have, the thing that is present but no one is looking at.
testing55
performance
Use this skill to turn dry technical material into a polished demo, narrative walkthrough, or audience-aware presentation without dumbing it down. It focuses on pacing, reveal order, and memorable framing so the work lands in the room.
testing55
polymorph
This spell is about representation change, not: - Naming changes (same structure, different identifiers) - Execution changes (same code, different runtime) - Architecture changes (new system design) - Duplication (same thing, different place) The key test: Can you point to a source artifact and a target artifact where the same information is expressed in structurally different ways? If yes → Polymorph.
development55
power-word-kill
In D&D, Power Word Kill instantly destroys any creature below a hit-point threshold — no saving throw, no resistance, just death. The real-world version is kill -9: the unconditional termination signal. Emergency circuit breakers. Hard account terminations. The nuclear option that exists because sometimes graceful shutdown is not available and the cost of continuing is worse than the cost of data loss. Power Word Kill is not elegant. It is not kind. It is the thing you reach for when everything else has already failed.
testing55
persuasion
Use this skill when the problem is not information scarcity but alignment, framing, or buy-in.
development55
persuasion
Use this skill when the problem is not information scarcity but alignment, framing, or buy-in.
development55
planar-binding
Use this spell when you need to summon a powerful external entity - a third-party API, a cloud service, another agent - and lock it into serving your workflow under explicit terms.
development55
plant-growth
Plant Growth is for projects that need cultivation more than force: SEO programs, communities, product adoption, content ecosystems, or early-stage platforms. It assumes the system can grow, but only if fed in the right places and at the right pace. The spell favors compounding loops over campaign spikes.
data-ai55
plant-growth
Plant Growth is for projects that need cultivation more than force: SEO programs, communities, product adoption, content ecosystems, or early-stage platforms. It assumes the system can grow, but only if fed in the right places and at the right pace. The spell favors compounding loops over campaign spikes.
data-ai55
regenerate
In D&D, Regenerate regrows lost limbs. The real-world version is reconstruction: rebuilding lost data from backups and surrounding context, regenerating a deleted component from its tests and documentation, or reconstructing a corrupted file from its known structure and partial content. Unlike Resurrection (which brings back a fully dead system from artifacts), Regenerate is for systems that are alive but missing pieces.
development55
regenerate
In D&D, Regenerate regrows lost limbs. The real-world version is reconstruction: rebuilding lost data from backups and surrounding context, regenerating a deleted component from its tests and documentation, or reconstructing a corrupted file from its known structure and partial content. Unlike Resurrection (which brings back a fully dead system from artifacts), Regenerate is for systems that are alive but missing pieces.
development55
religion
In D&D, Religion is knowledge of deities, rites, prayers, and holy symbols. The real-world version is understanding belief systems: organizational cultures, team values, community norms, ideological frameworks, and the unstated axioms that a group treats as sacred. Religion explains why people in a group behave the way they do when the behavior does not follow from rational incentives alone.
development55
resurrection
Use this spell when a system has truly died — crashed, deleted, corrupted beyond repair — and needs to be rebuilt from whatever remains. Distinct from Speak with Dead, which queries dead systems for knowledge; Resurrection actually revives them.
data-ai55
seeming
Seeming is coordinated appearance change at scale: mass theming, batch rebranding, global copy tone shifts, and UI-wide presentation updates. The underlying structures stay the same. The spell is about coherent surface transformation, not structural reinvention.
development55
seeming
Seeming is coordinated appearance change at scale: mass theming, batch rebranding, global copy tone shifts, and UI-wide presentation updates. The underlying structures stay the same. The spell is about coherent surface transformation, not structural reinvention.
development55
sending
Use this spell when you need to dispatch a message — the agent determines the right channel, formats for that medium, and sends with the user's approval.
development55
shatter
Shatter is proactive, controlled destruction for learning. You are the attacker against your own system. The goal is a brittleness report with remediation priorities.
development55
silence
Use this spell when you are drowning in notifications, verbose logs, irrelevant alerts, or context that does not serve the current task.
tools55
silent-image
In D&D, Silent Image creates a purely visual illusion — no sound, no smell, no substance. It looks real but falls apart if you interact with it. The real-world version is the static design comp: a high-fidelity visual mockup that shows exactly what something will look like but does nothing when you click it. Figma frames without prototyping links, screenshot mockups, rendered previews, static architecture diagrams. Silent Image is faster than Major Image because it skips interactivity. Use it when the only question is what does it look like.
tools55
silent-image
In D&D, Silent Image creates a purely visual illusion — no sound, no smell, no substance. It looks real but falls apart if you interact with it. The real-world version is the static design comp: a high-fidelity visual mockup that shows exactly what something will look like but does nothing when you click it. Figma frames without prototyping links, screenshot mockups, rendered previews, static architecture diagrams. Silent Image is faster than Major Image because it skips interactivity. Use it when the only question is what does it look like.
tools55
sleep
Sleep = temporary, reversible suspension with guaranteed state preservation. The target stops acting but wakes up intact. No data loss, no corruption, no permanent change.
data-ai55
sleep
Sleep = temporary, reversible suspension with guaranteed state preservation. The target stops acting but wakes up intact. No data loss, no corruption, no permanent change.
data-ai55
sleight-of-hand
Sleight of Hand is not about solving a problem — the solution is already known. It is about executing a known change with zero collateral damage. The skill is precision, not creativity.
testing55
skill-creator
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an existing skill, (8) validate a skill, (9) learn about skill structure, (10) understand how skills work, or (11) get guidance on skill design patterns. Trigger on phrases like "create a skill", "new skill", "make a skill", "skill for X", "how do I create a skill", or "help me build a skill".
tools43
langgraph-docs
Use this skill for requests related to LangGraph in order to fetch relevant documentation to provide accurate, up-to-date guidance.
documentation43
schema-exploration
For discovering and understanding database structure, tables, columns, and relationships
data-ai43
web-research
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research
development43
skill-creator
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an existing skill, (8) validate a skill, (9) learn about skill structure, (10) understand how skills work, or (11) get guidance on skill design patterns. Trigger on phrases like "create a skill", "new skill", "make a skill", "skill for X", "how do I create a skill", or "help me build a skill".
tools43
social-media
Use this skill when creating short-form social media content for LinkedIn, Twitter/X, or other platforms
testing43
query-writing
For writing and executing SQL queries - from simple single-table queries to complex multi-table JOINs and aggregations
databases43
blog-post
Use this skill when writing long-form blog posts, tutorials, or educational articles that require structure, depth, and SEO considerations
documentation43
arxiv-search
Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields
testing43
skill-creator
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an existing skill, (8) validate a skill, (9) learn about skill structure, (10) understand how skills work, or (11) get guidance on skill design patterns. Trigger on phrases like "create a skill", "new skill", "make a skill", "skill for X", "how do I create a skill", or "help me build a skill".
tools43