akshay-na
182 verified skills728 total stars
skill-validation
Defines input/output schema validation for skills. Use when creating or validating skills, composing skill chains, or checking skill contracts. Agents load this skill to understand how to validate skill I/O.
testing4
failure-engineering
Use when designing for graceful degradation, implementing retry or circuit breaker logic, handling partial failures, evaluating idempotency, setting up dead-letter queues, or when a system lacks resilience under dependency failure or network instability.
testing4
agent-observability
Track agent decisions, metrics, token costs, and generate reports. Use when logging task execution, tracking agent performance, or generating observability reports.
testing4
agent-observability
Track agent decisions, metrics, token costs, and generate reports. Use when logging task execution, tracking agent performance, or generating observability reports.
testing4
brain-memory-kb
Unified ai-brain skill combining memory operations and KB query operations with promotion flow.
data-ai4
meta-learning-engineering-retrospection
Use after completing major features, recovering from incidents, making architectural decisions that turned out wrong, or when repeated mistakes suggest stagnant mental models and missing feedback loops.
testing4
failure-engineering
Use when designing for graceful degradation, implementing retry or circuit breaker logic, handling partial failures, evaluating idempotency, setting up dead-letter queues, or when a system lacks resilience under dependency failure or network instability.
testing4
closed-loop-execution
Generate → execute → fail → analyze → fix → repeat cycle with failure pattern recognition. Use when implementing changes that need verification and automatic recovery.
data-ai4
failure-engineering
Use when designing for graceful degradation, implementing retry or circuit breaker logic, handling partial failures, evaluating idempotency, setting up dead-letter queues, or when a system lacks resilience under dependency failure or network instability.
testing4
n8n-builder-execution-gate
Standardizes how `n8n-builder` enters and runs Stage C (implementation) with worker fan-out, group checkpoints, and gated progression. Use when n8n-builder transitions from CRO `approved`/`degraded_skip` to execution.
development4
kb-query
Token-efficient query protocol for Knowledge Base. Provides tiered access to project documentation with staleness detection and budget-aware responses.
testing4
context-cache-discipline
Token and prompt-cache discipline — lean always-on rules, stable prefixes, skill indirection, minimal Task payloads, bounded reads.
testing4
swarm-critic-validation
Post-merge critic pass — schema + policy-only feedback; no direct code edits.
development4
swarm-deterministic-merge
Deterministic aggregation of shard results — lexical ordering + schema-checked bundle merges.
testing4
swarm-task-decomposition
CTO/tech-lead helper — split work into disjoint shard briefs with caps (instance_cap, partition_basis, determinism keys).
tools4
abstraction-judgment
Use when deciding whether to extract a shared utility, create a base class, build a framework layer, or generalize a pattern -- especially when the pattern has fewer than three concrete instances or the abstraction adds cognitive overhead without clear payoff.
tools4
clarity-technical-communication
Use when writing architecture decision records, documenting trade-offs, drafting design proposals, writing postmortems, summarizing technical reasoning, or when a decision lacks documented context and clear justification.
testing4
security-threat-modeling
Use when designing authentication or authorization flows, handling sensitive data, mapping trust boundaries, reviewing secret management, evaluating dependency supply chain risks, or when a feature introduces new public exposure or privilege escalation paths.
development4
agent-observability
Track agent decisions, metrics, token costs, and generate reports. Use when logging task execution, tracking agent performance, or generating observability reports.
testing4
ai-orchestration-prompt-engineering
Use when delegating tasks to AI agents, designing prompts for structured output, validating AI-generated code or reasoning, detecting hallucination, or when AI output needs constraint checking and human oversight before integration.
development4
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full, ultra. Defaults: main chat = lite, subagents = ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
testing4
kb-identity
Agent-based project identity derivation for Knowledge Base. Reads git config directly without shell commands. Worktree-safe — all worktrees of the same repo derive the same identity.
data-ai4
pipeline-executor
Declarative pipeline execution with stages, conditions, data passing, and rollback. Use when executing multi-stage workflows.
devops4
rule-enforcement
Programmatic rule enforcement with glob patterns, priority resolution, and pre/post validation. Use when checking compliance before or after agent actions.
testing4
task-orchestration
Automated task classification, agent selection, and state tracking. Use when routing tasks to agents, selecting pipelines, or managing task state.
devops4
clarity-technical-communication
Use when writing architecture decision records, documenting trade-offs, drafting design proposals, writing postmortems, summarizing technical reasoning, or when a decision lacks documented context and clear justification.
testing4
ai-orchestration-prompt-engineering
Use when delegating tasks to AI agents, designing prompts for structured output, validating AI-generated code or reasoning, detecting hallucination, or when AI output needs constraint checking and human oversight before integration.
development4
atlassian-hierarchy-discovery
Bootstraps a Jira hierarchy snapshot before any multi-issue create / edit session. Disambiguates the parent input (issue key, spec URL, Confluence page URL, or `greenfield`), walks parents up (depth-cap 4), walks children down via JQL recursion (depth-cap 4, max 50 children per node), and returns a structured tree alongside the issue-type scheme and link-type metadata the caller needs to render a draft. Used primarily by `atlassian-pm`; secondary consumers (after the G2.5 retrofit) are the upstream Atlassian plugin skills `spec-to-backlog` and `capture-tasks-from-meeting-notes`. The skill **does not render**; rendering belongs to the caller (typically `atlassian-pm` rendering a markdown tree to chat).
tools4
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full, ultra. Defaults: main chat = lite, subagents = ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
testing4
cross-stage-feedback
Structured feedback propagation between pipeline stages. Use when review stages produce findings that should trigger re-implementation.
devops4
dev-reviewer-qa-loop
Dev–Reviewer–QA closed-loop orchestration for implementation tasks — sequence, escalation, retries, merged-diff fan-in, loop state tracking. Invoke when coordinating tech-lead or code-reviewer workflows that chain dev-, reviewer-, and qa-* agents or senior-dev fallback.
development4
engineering-economics
Use when estimating infrastructure costs, comparing architectural approaches by cost, evaluating managed service trade-offs, reviewing cloud pricing models, or when a design decision has unclear cost implications or vendor lock-in risk.
testing4
kb-identity
Agent-based project identity derivation for Knowledge Base. Reads git config directly without shell commands. Worktree-safe — all worktrees of the same repo derive the same identity.
data-ai4
meta-learning-engineering-retrospection
Use after completing major features, recovering from incidents, making architectural decisions that turned out wrong, or when repeated mistakes suggest stagnant mental models and missing feedback loops.
testing4
n8n-builder-execution-gate
Standardizes how `n8n-builder` enters and runs Stage C (implementation) with worker fan-out, group checkpoints, and gated progression. Use when n8n-builder transitions from CRO `approved`/`degraded_skip` to execution.
development4
n8n-builder-planning-gate
Standardizes how `n8n-builder` performs planning triage, specialist consultation, and produces plan v0 plus post–v0 edit round; mandatory `cro-loop` runs at execution intent before Stage C. Use when n8n-builder is in Stage A (planning).
development4
observability-as-design
Use when defining metrics before implementation, designing structured logging, setting SLO targets, instrumenting tracing boundaries, building health checks, or when an outage reveals missing signals and blind spots in operational visibility.
development4
performance-runtime-literacy
Use when debugging latency issues, evaluating concurrency models, reviewing connection pooling, investigating memory growth, analyzing queue backpressure, or when services degrade under load and the root cause is unclear.
development4
pipeline-executor
Declarative pipeline execution with stages, conditions, data passing, and rollback. Use when executing multi-stage workflows.
devops4
pre-execution-validation
Validates generated output before writing to disk. Use when implementing changes that need pre-write verification to catch errors early.
testing4
remotion-builder-planning-gate
Standardizes how `remotion-builder` performs planning triage, specialist consultation, and produces plan v0; mandatory tech `cro-loop` at execution intent before Stage C. Use when remotion-builder is in Stage A (planning).
development4
rule-enforcement
Programmatic rule enforcement with glob patterns, priority resolution, and pre/post validation. Use when checking compliance before or after agent actions.
testing4
security-threat-modeling
Use when designing authentication or authorization flows, handling sensitive data, mapping trust boundaries, reviewing secret management, evaluating dependency supply chain risks, or when a feature introduces new public exposure or privilege escalation paths.
development4
skill-validation
Defines input/output schema validation for skills. Use when creating or validating skills, composing skill chains, or checking skill contracts. Agents load this skill to understand how to validate skill I/O.
testing4
swarm-critic-validation
Post-merge critic pass — schema + policy-only feedback; no direct code edits.
development4
swarm-deterministic-merge
Deterministic aggregation of shard results — lexical ordering + schema-checked bundle merges.
testing4
swarm-task-decomposition
CTO/tech-lead helper — split work into disjoint shard briefs with caps (instance_cap, partition_basis, determinism keys).
tools4
team-discovery
Discovery + naming convention reference for typed dev/SME/QA/devops team members in any workspace folder. Primary consumer: `tech-lead` (org-tier).
development4
parallel-dispatch
Three-level parallelism (phase group → phase-task → intra-role fan-out), parallelize-by-default stance, disjoint-touches pre-flight, merge/rollback for horizontal fan-out, failure semantics, and dynamic concurrency caps for orchestrators consuming a cto plan.
data-ai4
performance-runtime-literacy
Use when debugging latency issues, evaluating concurrency models, reviewing connection pooling, investigating memory growth, analyzing queue backpressure, or when services degrade under load and the root cause is unclear.
development4
systems-design-depth
Use when designing scalable systems, evaluating consistency models, planning state management, making architectural decisions, or when trade-offs around coupling, failure isolation, and reversibility need explicit reasoning before implementation.
testing4
remotion-builder-execution-gate
Standardizes how `remotion-builder` runs Stage C (implementation) after tech CRO approval — remotion CLI, browser ensure, Skia smoke, ffmpeg from approved recipes, group checkpoints.
tools4
agent-observability
Track agent decisions, metrics, token costs, and generate reports. Use when logging task execution, tracking agent performance, or generating observability reports.
testing4
content-git-workflow
Git pull, commit (~/.gitmessage), push for content-repo automation. SSH pre-provisioned; fail-closed on conflicts. Emits stages for agent-observability.
tools4
context-cache-discipline
Token and prompt-cache discipline — lean always-on rules, stable prefixes, skill indirection, minimal Task payloads, bounded reads.
testing4
video-editor-handoff
Structured handoff from content org to tech remotion-builder for programmatic video; Task payload, workspace_root, Remotion paths, composition id, output basename, aspect ratio, audio policy, handoff_schema_version 2 synthetic audio fields, ffmpeg recipe id.
development4
task-orchestration
Automated task classification, agent selection, and state tracking. Use when routing tasks to agents, selecting pipelines, or managing task state.
devops4
remotion-builder-planning-gate
Standardizes how `remotion-builder` performs planning triage, specialist consultation, and produces plan v0; mandatory tech `cro-loop` at execution intent before Stage C. Use when remotion-builder is in Stage A (planning).
development4
ai-orchestration-prompt-engineering
Use when delegating tasks to AI agents, designing prompts for structured output, validating AI-generated code or reasoning, detecting hallucination, or when AI output needs constraint checking and human oversight before integration.
development4
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full, ultra. Defaults: main chat = lite, subagents = ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
testing4
chief-visual-handoff
Structured handoff to org singleton chief-visual-officer for corpus image generation; Task payload, workspace_root, paths.
content-media4
content-git-workflow
Git pull, commit (~/.gitmessage), push for content-repo automation. SSH pre-provisioned; fail-closed on conflicts. Emits stages for agent-observability.
tools4
context-cache-discipline
Token / cache discipline for Gemini content pack — pointer to canonical tech skill + Gemini dispatch semantics.
testing4
cross-stage-feedback
Structured feedback propagation between pipeline stages. Use when review stages produce findings that should trigger re-implementation.
devops4
kb-identity
Agent-based project identity derivation for Knowledge Base. Reads git config directly without shell commands. Worktree-safe — all worktrees of the same repo derive the same identity.
data-ai4
pipeline-executor
Declarative pipeline execution with stages, conditions, data passing, and rollback. Use when executing multi-stage workflows.
devops4
pre-execution-validation
Validates generated output before writing to disk. Use when implementing changes that need pre-write verification to catch errors early.
testing4
skill-validation
Defines input/output schema validation for skills. Use when creating or validating skills, composing skill chains, or checking skill contracts. Agents load this skill to understand how to validate skill I/O.
testing4
task-orchestration
Automated task classification, agent selection, and state tracking. Use when routing tasks to agents, selecting pipelines, or managing task state.
devops4
content-team-discovery
Discovery + naming for project agents under each workspace root. Primary consumer: `content-lead` (content org). Content lane: no org `qa-*` assumption — patterns may still list dev-*, sme-*, editor-* per project.
development4
generate-content-pipeline
Declarative stages for content automation — optional git_sync, plan, generate_content, git_commit_push; n8n correction branch with target_paths[].
tools4
brain-memory-kb
Unified ai-brain skill combining memory operations and KB query operations with promotion flow.
data-ai4
task-orchestration
Automated task classification, agent selection, and state tracking. Use when routing tasks to agents, selecting pipelines, or managing task state.
devops4
n8n-builder-planning-gate
Standardizes how `n8n-builder` performs planning triage, specialist consultation, and produces plan v0 plus post–v0 edit round; mandatory `cro-loop` runs at execution intent before Stage C. Use when n8n-builder is in Stage A (planning).
development4
context-cache-discipline
Token / prompt-cache discipline for content org — points to canonical tech-pack skill + JSON subagent envelope reminder.
testing4
brain-memory-kb
Unified ai-brain skill combining memory operations and KB query operations with promotion flow.
data-ai4
agent-observability
Track agent decisions, metrics, token costs, and generate reports. Use when logging task execution, tracking agent performance, or generating observability reports.
testing4
generate-content-pipeline
Declarative stages for content automation — optional git_sync, plan, generate_content, git_commit_push; n8n correction branch with target_paths[].
tools4
subagent-response-protocol
Content org: subagent → parent is one JSON object (no YAML). Validate against contracts/schemas/subagent-response.schema.json. Applies to every Task child.
testing4
rule-enforcement
Programmatic rule enforcement with glob patterns, priority resolution, and pre/post validation. Use when checking compliance before or after agent actions.
testing4
editorial-cro-loop
Two-pass CCO plan-critic loop owned by editorial-cro; ledger schema, editorial bounce rubric, caps, observability stages. Content org only — no Atlassian.
content-media4
content-plan-intake
Mandatory planner intake — brain-memory-kb + kb-query, repo/workdir corpus scan, merge into brief for CCO plans.
data-ai4
content-team-discovery
Discovery + naming for project agents under each workspace root. Primary consumer: `content-lead` (content org). Content lane: no org `qa-*` assumption — patterns may still list dev-*, sme-*, editor-* per project.
development4
editorial-cro-loop
Two-pass editorial plan-critic loop (`editorial-cro`); ledger schema, adversarial rubric, bounce rubric, caps, observability. Content org only — no Atlassian.
content-media4
video-editor-handoff
Structured handoff to Cursor remotion-builder for programmatic video; payload contract with Remotion paths, composition id, output basename, aspect ratio, audio; Gemini prepares briefs — execution in Cursor when remotion-builder is available.
development4
remotion-builder-execution-gate
Standardizes how `remotion-builder` runs Stage C (implementation) after tech CRO approval — remotion CLI, browser ensure, Skia smoke, ffmpeg from approved recipes, group checkpoints.
tools4
agent-observability
Track agent decisions, metrics, token costs, and generate reports. Use when logging task execution, tracking agent performance, or generating observability reports.
testing4
parallel-dispatch
Three-level parallelism (phase group → phase-task → intra-role fan-out), parallelize-by-default stance, disjoint-touches pre-flight, merge/rollback for horizontal fan-out, failure semantics, and dynamic concurrency caps for orchestrators consuming a cto plan.
data-ai4
failure-engineering
Use when designing for graceful degradation, implementing retry or circuit breaker logic, handling partial failures, evaluating idempotency, setting up dead-letter queues, or when a system lacks resilience under dependency failure or network instability.
testing4
closed-loop-execution
Generate → execute → fail → analyze → fix → repeat cycle with failure pattern recognition. Use when implementing changes that need verification and automatic recovery.
data-ai4
failure-engineering
Use when designing for graceful degradation, implementing retry or circuit breaker logic, handling partial failures, evaluating idempotency, setting up dead-letter queues, or when a system lacks resilience under dependency failure or network instability.
testing4
closed-loop-execution
Generate → execute → fail → analyze → fix → repeat cycle with failure pattern recognition. Use when implementing changes that need verification and automatic recovery.
data-ai4
task-orchestration
Automated task classification, agent selection, and state tracking. Use when routing tasks to agents, selecting pipelines, or managing task state.
devops4
context-cache-discipline
Token and prompt-cache discipline — lean always-on rules, stable prefixes, skill indirection, minimal Task payloads, bounded reads.
testing4
engineering-economics
Use when estimating infrastructure costs, comparing architectural approaches by cost, evaluating managed service trade-offs, reviewing cloud pricing models, or when a design decision has unclear cost implications or vendor lock-in risk.
testing4
context-memory
File-based Markdown memory at ~/.cursor/memory/. Any agent can read/write directly using this skill. No external dependencies.
testing4
kb-generation
Core generation protocol for Knowledge Base documents. Analyzes project structure, generates Obsidian-compatible markdown with mermaid diagrams, builds relationship graphs, and tracks manifests for incremental updates.
development4
cross-stage-feedback
Structured feedback propagation between pipeline stages. Use when review stages produce findings that should trigger re-implementation.
devops4
pre-execution-validation
Validates generated output before writing to disk. Use when implementing changes that need pre-write verification to catch errors early.
testing4
cro-loop
Two-pass plan-critic loop (`cro`); ledger schema, adversarial rubric, bounce rubric, caps, observability stages.
databases4
context-budget-guard
Heuristic context budget checks using file-size and count proxies — integrates with context-cache-discipline; no tokenizer introspection claims.
testing4
subagent-response-protocol
Protocol for subagent → parent responses: single fenced YAML envelope, strict caveman-ultra for compressed fields, verbatim for paths/errors/code. Applies to every `Task` invocation. Use when spawning subagents or parsing their output.
development4
kb-identity
Agent-based project identity derivation for Knowledge Base. Reads git config directly without shell commands. Worktree-safe — all worktrees of the same repo derive the same identity.
data-ai4
cross-stage-feedback
Structured feedback propagation between pipeline stages. Use when review stages produce findings that should trigger re-implementation.
devops4
ai-orchestration-prompt-engineering
Use when delegating tasks to AI agents, designing prompts for structured output, validating AI-generated code or reasoning, detecting hallucination, or when AI output needs constraint checking and human oversight before integration.
development4
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full, ultra. Defaults: main chat = lite, subagents = ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
testing4
pre-execution-validation
Validates generated output before writing to disk. Use when implementing changes that need pre-write verification to catch errors early.
testing4
rule-enforcement
Programmatic rule enforcement with glob patterns, priority resolution, and pre/post validation. Use when checking compliance before or after agent actions.
testing4
ai-orchestration-prompt-engineering
Use when delegating tasks to AI agents, designing prompts for structured output, validating AI-generated code or reasoning, detecting hallucination, or when AI output needs constraint checking and human oversight before integration.
development4
brain-memory-kb
Unified ai-brain skill combining memory operations and KB query operations with promotion flow.
data-ai4
clarity-technical-communication
Use when writing architecture decision records, documenting trade-offs, drafting design proposals, writing postmortems, summarizing technical reasoning, or when a decision lacks documented context and clear justification.
testing4
cross-stage-feedback
Structured feedback propagation between pipeline stages. Use when review stages produce findings that should trigger re-implementation.
devops4
engineering-economics
Use when estimating infrastructure costs, comparing architectural approaches by cost, evaluating managed service trade-offs, reviewing cloud pricing models, or when a design decision has unclear cost implications or vendor lock-in risk.
testing4
meta-learning-engineering-retrospection
Use after completing major features, recovering from incidents, making architectural decisions that turned out wrong, or when repeated mistakes suggest stagnant mental models and missing feedback loops.
testing4
observability-as-design
Use when defining metrics before implementation, designing structured logging, setting SLO targets, instrumenting tracing boundaries, building health checks, or when an outage reveals missing signals and blind spots in operational visibility.
development4
performance-runtime-literacy
Use when debugging latency issues, evaluating concurrency models, reviewing connection pooling, investigating memory growth, analyzing queue backpressure, or when services degrade under load and the root cause is unclear.
development4
pre-execution-validation
Validates generated output before writing to disk. Use when implementing changes that need pre-write verification to catch errors early.
testing4
rule-enforcement
Programmatic rule enforcement with glob patterns, priority resolution, and pre/post validation. Use when checking compliance before or after agent actions.
testing4
security-threat-modeling
Use when designing authentication or authorization flows, handling sensitive data, mapping trust boundaries, reviewing secret management, evaluating dependency supply chain risks, or when a feature introduces new public exposure or privilege escalation paths.
development4
subagent-response-protocol
Protocol for subagent → parent responses: single fenced YAML envelope, strict caveman-ultra for compressed fields, verbatim for paths/errors/code. Applies to every `Task` invocation. Use when spawning subagents or parsing their output.
development4
systems-design-depth
Use when designing scalable systems, evaluating consistency models, planning state management, making architectural decisions, or when trade-offs around coupling, failure isolation, and reversibility need explicit reasoning before implementation.
testing4
team-discovery
Discovery + naming convention reference for typed dev/SME/QA/devops team members in any workspace folder. Primary consumer: `tech-lead` (org-tier).
development4
cco-orchestration
Executable checklist for one cco pipeline run (parallel groups, METRICS_READ, audit NDJSON, n8n gates).
testing4
project-identity
Derive ai-brain project name and KB path from git remote or folder name — same algorithm as Cursor kb-identity (worktree-safe). Use before resolving content-brain paths.
development4
subagent-observability
Format one NDJSON audit line per inter-persona event (hashes, paths — no raw secrets or full draft bodies).
development4
closed-loop-execution
Generate → execute → fail → analyze → fix → repeat cycle with failure pattern recognition. Use when implementing changes that need verification and automatic recovery.
data-ai4
skill-validation
Defines input/output schema validation for skills. Use when creating or validating skills, composing skill chains, or checking skill contracts. Agents load this skill to understand how to validate skill I/O.
testing4
parallel-dispatch
Three-level parallelism (phase group → phase-task → intra-role fan-out), parallelize-by-default stance, disjoint-touches pre-flight, merge/rollback for horizontal fan-out, failure semantics, and dynamic concurrency caps for orchestrators consuming a cto plan.
data-ai4
subagent-response-protocol
Content org: subagent → parent is one JSON object (no YAML). Validate against contracts/schemas/subagent-response.schema.json. Applies to every Task child.
testing4
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full, ultra. Defaults: main chat = lite, subagents = ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
testing4
pipeline-executor
Declarative pipeline execution with stages, conditions, data passing, and rollback. Use when executing multi-stage workflows.
devops4
chief-visual-handoff
Structured handoff to org singleton chief-visual-officer for corpus image generation; Task payload, workspace_root, paths.
content-media4
parallel-dispatch
Three-level parallelism (phase group → phase-task → intra-role fan-out), parallelize-by-default stance, disjoint-touches pre-flight, merge/rollback for horizontal fan-out, failure semantics, and dynamic concurrency caps for orchestrators consuming a cto plan.
data-ai4
pipeline-executor
Declarative pipeline execution with stages, conditions, data passing, and rollback. Use when executing multi-stage workflows.
devops4
skill-validation
Defines input/output schema validation for skills. Use when creating or validating skills, composing skill chains, or checking skill contracts. Agents load this skill to understand how to validate skill I/O.
testing4
content-plan-intake
Mandatory planner intake — brain-memory-kb + kb-query, repo/workdir corpus scan, merge into brief for CCO plans.
data-ai4
abstraction-judgment
Use when deciding whether to extract a shared utility, create a base class, build a framework layer, or generalize a pattern -- especially when the pattern has fewer than three concrete instances or the abstraction adds cognitive overhead without clear payoff.
tools4
atlassian-hierarchy-discovery
Bootstraps a Jira hierarchy snapshot before any multi-issue create / edit session. Disambiguates the parent input (issue key, spec URL, Confluence page URL, or `greenfield`), walks parents up (depth-cap 4), walks children down via JQL recursion (depth-cap 4, max 50 children per node), and returns a structured tree alongside the issue-type scheme and link-type metadata the caller needs to render a draft. Used primarily by `atlassian-pm`; secondary consumers (after the G2.5 retrofit) are the upstream Atlassian plugin skills `spec-to-backlog` and `capture-tasks-from-meeting-notes`. The skill **does not render**; rendering belongs to the caller (typically `atlassian-pm` rendering a markdown tree to chat).
tools4
dev-reviewer-qa-loop
Dev–Reviewer–QA closed-loop orchestration for implementation tasks — sequence, escalation, retries, merged-diff fan-in, loop state tracking. Invoke when coordinating tech-lead or code-reviewer workflows that chain dev-, reviewer-, and qa-* agents or senior-dev fallback.
development4
cro-loop
Two-pass plan-critic loop (`cro`); ledger schema, adversarial rubric, bounce rubric, caps, observability stages.
databases4
kb-identity
Agent-based project identity derivation for Knowledge Base. Reads git config directly without shell commands. Worktree-safe — all worktrees of the same repo derive the same identity.
data-ai4
swarm-task-decomposition
CTO/tech-lead helper — split work into disjoint shard briefs with caps (instance_cap, partition_basis, determinism keys).
tools4
swarm-critic-validation
Post-merge critic pass — schema + policy-only feedback; no direct code edits.
development4
swarm-deterministic-merge
Deterministic aggregation of shard results — lexical ordering + schema-checked bundle merges.
testing4
abstraction-judgment
Use when deciding whether to extract a shared utility, create a base class, build a framework layer, or generalize a pattern -- especially when the pattern has fewer than three concrete instances or the abstraction adds cognitive overhead without clear payoff.
tools4
ai/cursor/tech-team/skills/entrypoint-clarification
# Entrypoint clarification Use when an **entrypoint** session needs requirements before delegating or mutating product repos. ## Triggers - Vague scope, missing success criteria, or unclear in/out boundaries - Ambiguous workspace root(s) (multi-root) - Conflicting mode signals (plan vs execute, builder mode, broker vs interactive) - Pre-delegate / pre-implementation phase (not mid-approved-plan execution) ## Router vs entrypoint | Actor | Policy | |-------|--------| | Generic parent/router
development4
remotion-builder-execution-gate
Standardizes how `remotion-builder` runs Stage C (implementation) after tech CRO approval — remotion CLI, browser ensure, Skia smoke, ffmpeg from approved recipes, group checkpoints.
tools4
rule-enforcement
Programmatic rule enforcement with glob patterns, priority resolution, and pre/post validation. Use when checking compliance before or after agent actions.
testing4
abstraction-judgment
Use when deciding whether to extract a shared utility, create a base class, build a framework layer, or generalize a pattern -- especially when the pattern has fewer than three concrete instances or the abstraction adds cognitive overhead without clear payoff.
tools4
context-budget-guard
Heuristic context budget checks using file-size and count proxies — integrates with context-cache-discipline; no tokenizer introspection claims.
testing4
cro-loop
Two-pass plan-critic loop (`cro`); ledger schema, adversarial rubric, bounce rubric, caps, observability stages.
databases4
n8n-builder-planning-gate
Standardizes how `n8n-builder` performs planning triage, specialist consultation, and produces plan v0 plus post–v0 edit round; mandatory `cro-loop` runs at execution intent before Stage C. Use when n8n-builder is in Stage A (planning).
development4
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full, ultra. Defaults: main chat = lite, subagents = ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
testing4
ai-orchestration-prompt-engineering
Use when delegating tasks to AI agents, designing prompts for structured output, validating AI-generated code or reasoning, detecting hallucination, or when AI output needs constraint checking and human oversight before integration.
development4
clarity-technical-communication
Use when writing architecture decision records, documenting trade-offs, drafting design proposals, writing postmortems, summarizing technical reasoning, or when a decision lacks documented context and clear justification.
testing4
cross-stage-feedback
Structured feedback propagation between pipeline stages. Use when review stages produce findings that should trigger re-implementation.
devops4
dev-reviewer-qa-loop
Dev–Reviewer–QA closed-loop orchestration for implementation tasks — sequence, escalation, retries, merged-diff fan-in, loop state tracking. Invoke when coordinating tech-lead or code-reviewer workflows that chain dev-, reviewer-, and qa-* agents or senior-dev fallback.
development4
kb-identity
Agent-based project identity derivation for Knowledge Base. Reads git config directly without shell commands. Worktree-safe — all worktrees of the same repo derive the same identity.
data-ai4
engineering-economics
Use when estimating infrastructure costs, comparing architectural approaches by cost, evaluating managed service trade-offs, reviewing cloud pricing models, or when a design decision has unclear cost implications or vendor lock-in risk.
testing4
meta-learning-engineering-retrospection
Use after completing major features, recovering from incidents, making architectural decisions that turned out wrong, or when repeated mistakes suggest stagnant mental models and missing feedback loops.
testing4
observability-as-design
Use when defining metrics before implementation, designing structured logging, setting SLO targets, instrumenting tracing boundaries, building health checks, or when an outage reveals missing signals and blind spots in operational visibility.
development4
n8n-builder-execution-gate
Standardizes how `n8n-builder` enters and runs Stage C (implementation) with worker fan-out, group checkpoints, and gated progression. Use when n8n-builder transitions from CRO `approved`/`degraded_skip` to execution.
development4
performance-runtime-literacy
Use when debugging latency issues, evaluating concurrency models, reviewing connection pooling, investigating memory growth, analyzing queue backpressure, or when services degrade under load and the root cause is unclear.
development4
pipeline-executor
Declarative pipeline execution with stages, conditions, data passing, and rollback. Use when executing multi-stage workflows.
devops4
remotion-builder-planning-gate
Standardizes how `remotion-builder` performs planning triage, specialist consultation, and produces plan v0; mandatory tech `cro-loop` at execution intent before Stage C. Use when remotion-builder is in Stage A (planning).
development4
security-threat-modeling
Use when designing authentication or authorization flows, handling sensitive data, mapping trust boundaries, reviewing secret management, evaluating dependency supply chain risks, or when a feature introduces new public exposure or privilege escalation paths.
development4
skill-validation
Defines input/output schema validation for skills. Use when creating or validating skills, composing skill chains, or checking skill contracts. Agents load this skill to understand how to validate skill I/O.
testing4
systems-design-depth
Use when designing scalable systems, evaluating consistency models, planning state management, making architectural decisions, or when trade-offs around coupling, failure isolation, and reversibility need explicit reasoning before implementation.
testing4
task-orchestration
Automated task classification, agent selection, and state tracking. Use when routing tasks to agents, selecting pipelines, or managing task state.
devops4
team-discovery
Discovery + naming convention reference for typed dev/SME/QA/devops team members in any workspace folder. Primary consumer: `tech-lead` (org-tier).
development4
parallel-dispatch
Three-level parallelism (phase group → phase-task → intra-role fan-out), parallelize-by-default stance, disjoint-touches pre-flight, merge/rollback for horizontal fan-out, failure semantics, and dynamic concurrency caps for orchestrators consuming a cto plan.
data-ai4
atlassian-hierarchy-discovery
Bootstraps a Jira hierarchy snapshot before any multi-issue create / edit session. Disambiguates the parent input (issue key, spec URL, Confluence page URL, or `greenfield`), walks parents up (depth-cap 4), walks children down via JQL recursion (depth-cap 4, max 50 children per node), and returns a structured tree alongside the issue-type scheme and link-type metadata the caller needs to render a draft. Used primarily by `atlassian-pm`; secondary consumers (after the G2.5 retrofit) are the upstream Atlassian plugin skills `spec-to-backlog` and `capture-tasks-from-meeting-notes`. The skill **does not render**; rendering belongs to the caller (typically `atlassian-pm` rendering a markdown tree to chat).
tools4
closed-loop-execution
Generate → execute → fail → analyze → fix → repeat cycle with failure pattern recognition. Use when implementing changes that need verification and automatic recovery.
data-ai4
pre-execution-validation
Validates generated output before writing to disk. Use when implementing changes that need pre-write verification to catch errors early.
testing4
ai/opencode/tech-team/skills/entrypoint-clarification
# Entrypoint clarification Use when an **entrypoint** session needs requirements before delegating or mutating product repos. ## Triggers - Vague scope, missing success criteria, or unclear in/out boundaries - Ambiguous workspace root(s) (multi-root) - Conflicting mode signals (plan vs execute, builder mode, broker vs interactive) - Pre-delegate / pre-implementation phase (not mid-approved-plan execution) ## Router vs entrypoint | Actor | Policy | |-------|--------| | Generic parent/router
development4
brain-memory-kb
Unified ai-brain skill combining memory operations and KB query operations with promotion flow.
data-ai4
subagent-response-protocol
Protocol for subagent → parent responses: single fenced YAML envelope, strict caveman-ultra for compressed fields, verbatim for paths/errors/code. Applies to every `Task` invocation. Use when spawning subagents or parsing their output.
development4
failure-engineering
Use when designing for graceful degradation, implementing retry or circuit breaker logic, handling partial failures, evaluating idempotency, setting up dead-letter queues, or when a system lacks resilience under dependency failure or network instability.
testing4
observability-as-design
Use when defining metrics before implementation, designing structured logging, setting SLO targets, instrumenting tracing boundaries, building health checks, or when an outage reveals missing signals and blind spots in operational visibility.
development4
project-agent-usage
Checklist for tech-lead and project agents on discovering and using typed dev/SME/QA team members with low-token, minimal-context behavior.
development4
systems-design-depth
Use when designing scalable systems, evaluating consistency models, planning state management, making architectural decisions, or when trade-offs around coupling, failure isolation, and reversibility need explicit reasoning before implementation.
testing4
closed-loop-execution
Generate → execute → fail → analyze → fix → repeat cycle with failure pattern recognition. Use when implementing changes that need verification and automatic recovery.
data-ai4