coalesce-labs

154 verified skills1,806 total stars

recovery-pass

Goal-driven senior-engineer pipeline-unstick sweep (CTL-1176 rung 3). Given the stuck/failed/needs-human set (or ONE ticket handed by the recovery router), its GOAL is to get the pipeline MOVING again — not to fix one ticket's review findings (that is phase-remediate). It runs AFTER the eyes (diagnostician evidence) and the hands (deterministic unstuck-sweep seams) have already tried, and it CONSUMES their output from a recovery-pass.json brief rather than re-diagnosing or redoing their narrow work. It acts like a senior engineer with full tool access — it resolves merge conflicts, rebases, force-pushes, merges green PRs, and re-dispatches stalled phases AUTONOMOUSLY — and escalates to the operator ONLY for a genuine value judgment / something that degrades other functionality / a real cost-benefit trade-off / a serious architecture change / an ADR conflict. On escalation it AUTHORS the operator inbox row + the push notification (executive-voiced). Dispatched as a `claude --bg` job by phase-agent-dispatch via slash command, AND invocable bare by the operator as a sweep — hence `user-invocable: true`. Ships behind CATALYST_RECOVERY_PASS (off by default — no live behavior change until shadow/enforce).

tools17

_phase-agent-template

Reference template every phase-agent skill copies (CTL-448). The leading underscore on the directory name prevents the skill loader from picking this up — it is NOT a runnable skill, only a structural template the nine real phase agents (phase-triage, phase-research, phase-plan, phase-implement, phase-verify, phase-review, phase-pr, phase-monitor-merge, phase-monitor-deploy) clone and specialize. The real phase skills MUST set `user-invocable: true` so `phase-agent-dispatch`'s `claude --bg "/catalyst-dev:phase-X ..."` slash command resolves (CTL-490).

development17

migrate-dual-harness

Migrate a single-harness repo to the dual-harness layout so both Claude Code and Codex load the same instructions and skills — AGENTS.md as the portable canonical doc, a thin CLAUDE.md `@AGENTS.md` bridge, and a `.agents/skills` dir with a `.claude/skills` symlink onto it. Use when asked to migrate to dual-harness, make this repo work in both Claude and Codex, or for agent metadata cleanup.

development17

agent-browser

Fast browser automation CLI for AI agents. **ALWAYS use instead of Playwright MCP tools** for web testing, screenshots, form filling, and UI verification. Use when user says "open in browser", "check the site", "take a screenshot", "fill the form", "test the UI", or any browser interaction. Also use as a fallback when a task requires visual browser interaction that CLIs and APIs cannot handle (e.g., OAuth flows, complex dashboards, visual verification).

tools17

setup-catalyst

Diagnose and fix Catalyst setup issues. Validates tools, database, config, OTel, direnv, and thoughts. Automatically fixes what it can — creates directories, initializes the database, sets WAL mode, runs migrations. Use for new installs, upgrades, or when something isn't working.

tools17

plugins/dev/skills/phase-triage

--- name: phase-triage description: Phase agent that triages a Linear ticket — expands acronyms, classifies (feature/bug/docs/refactor/chore), identifies genuine blockers (a semantic second-pass over the backlog — NOT a prose scrape; CTL-838), estimates scope, writes triage.json, and posts a triage analysis comment to Linear. Triage completion is signaled by that comment plus the local triage.json — there is no `triaged` label. Emits phase.triage.complete.<TICKET> on success and phase.triage.fai

tools17

review-comments

Systematically pull, categorize, and address all PR review comments — code change requests, questions, and suggestions. This skill fetches comments via gh api, groups them by file, implements fixes, handles disagreements diplomatically, and pushes a single commit. You should not try to handle PR review feedback manually — this skill ensures nothing gets missed. **ALWAYS consult this skill when** the user says 'address comments', 'fix review feedback', 'handle PR comments', 'respond to reviewers', 'address review', 'review feedback', or mentions that a PR has unresolved comments or review threads. Also used by /oneshot Phase 5 to process reviewer feedback before merging.

development17

morning-briefing

Generate a daily briefing markdown at thoughts/briefings/YYYY-MM-DD.md with six sections — Review yesterday, Surface decisions, Plan today, Suggest orchestrator runs, Friction since last briefing, and Learnings since last briefing — synthesized from Linear, GitHub, Granola, Google Drive, Google Calendar, and the compound-engineering stores (thoughts/shared/friction, thoughts/shared/learnings, thoughts/shared/compound/pending) in parallel. Then fans the briefing out to four destinations (Slack DM, Slack channel, Notion page, Loom script file). User-invoked from `/catalyst-dev:morning-briefing` for ad-hoc runs. The CMA Routine wraps the same skill on a weekday-morning schedule (Phase 5 of the parent plan).

development16

plugins/dev/skills/phase-teardown

--- name: phase-teardown description: Phase agent for the 10th/terminal step of the pipeline (CTL-703). Performs all terminal wrap-up after monitor-deploy — verifies the PR merged, posts a final Linear comment with per-phase timings, transitions Linear to Done (the sole Done writer now), archives the worker dir to ~/catalyst/archives/<TICKET>/, removes the local worktree + branch, then emits phase.teardown.complete.<TICKET>. Reads phase-monitor-deploy.json as its prior-phase artifact. Dispatched

tools16

plugins/dev/skills/phase-monitor-deploy

--- name: phase-monitor-deploy description: Phase agent that watches the post-merge deployment for a ticket. Reads the merge SHA from phase-monitor-merge.json (the signal file phase-monitor-merge writes after `gh pr merge` confirms via REST), subscribes via `catalyst-events wait-for` to deploy events on that SHA, then delegates a live verification check to the /canary skill (gstack). Emits phase.monitor-deploy.complete.<TICKET> on canary success, phase.monitor-deploy.failed.<TICKET> on deploy or

tools16

describe-pr

Generate or update PR description with incremental changes. **ALWAYS use when** the user says 'describe the PR', 'update PR description', 'generate PR description', or after pushing new commits to an existing PR. Supports incremental updates that preserve manual edits.

tools16

ticket-compound

Compound-engineering capture + curation for a finished ticket — the engineering feedback loop. Harvests the Friction sections that phase agents left in their artifacts plus the git diff, writes a structured entry to the shared learnings store (thoughts/shared/learnings/), prunes/amends stale notes there autonomously, captures new domain vocabulary to thoughts/shared/CONCEPTS.md, and PROPOSES (for human approval) any ADR change. Non-blocking — runs after a ticket ships or fails, never on the critical path. Use when the user says "compound this ticket", "capture learnings", "what did we learn", or run as /catalyst-dev:ticket-compound <TICKET> [mode:headless].

development16

broker

Protocol reference for the Catalyst event broker daemon. Covers agent identity (agent.checkin/ checkout), auto-correlation of ticket↔PR interests, ticket_lifecycle deterministic routing for Linear events, and the existing pr_lifecycle + Groq prose routing paths. Use when an agent needs to wait for events related to its own ticket/PR, watch another ticket's lifecycle, or register any semantic interest in the event stream.

testing16

linearis-cli

Linear access rule + Linearis CLI reference. READS → query the local replica by direct SQL (`~/catalyst/catalyst-replica.db`); WRITES and list/search → the `linearis` CLI. Use when working with Linear tickets, cycles, projects, milestones, or when the user mentions ticket IDs like TEAM-123, ENG-456, PROJ-789.

tools16

monitor-events

Reference for the canonical event-driven wait pattern in Catalyst skills. Use when a skill needs to block on a state change (PR merged, CI completed, push to branch, ticket transitioned) WITHOUT polling. Pairs the `catalyst-events` CLI with the Claude Code `Monitor` tool and `wait-for` for short-lived workers.

tools16

compound-estimate

Closing ritual for the AI-native estimation feedback loop. **ALWAYS use when** a ticket's PR has just merged (runs automatically per ticket: merge-pr step 12b / phase-monitor-merge, CTL-189/CTL-831), or when the user says 'compound-estimate', 'close the estimation loop', 'record actuals', 'compound-log', or wants to log post-merge actuals for a shipped Linear ticket. Writes a structured entry (linear.key, pr_number, merged_at, estimate_at_start, estimate_actual, cost_usd, wall_time_hours, what_worked, what_surprised_me) to `thoughts/shared/retros/estimate/YYYY-WW-compound-log.md` — one file per ISO week, appends.

documentation16

gherkin-ticket

Shape every ticket around a scannable use-case before it's filed. **ALWAYS use when** the user says 'file a ticket', 'create a ticket', 'file tickets for', 'open an issue', 'add a ticket', 'log a bug', or whenever drafting, titling, or rewriting a ticket. Turns vague, implementation-first tickets into an outcome title (`<actor> should <outcome> so that <benefit>`) plus tiered Gherkin (Given/When/Then) acceptance criteria — even for backend bugs and chores.

development16

linear

Manage Linear tickets with workflow automation. **ALWAYS use when** the user says 'create a ticket', 'update the ticket', 'move ticket to', 'search Linear', or wants to create tickets from thoughts documents, update ticket status, or manage the Linear workflow. Uses Linearis CLI.

tools16

orchestrate

Coordinate multiple tickets in parallel across worktrees with wave-based execution, worker dispatch, and adversarial verification

tools16

phase-research

Phase agent for the research step of the 9-phase orchestrator pipeline (CTL-450). Wraps /catalyst-dev:research-codebase and produces thoughts/shared/research/<date>-<ticket>.md, then emits phase.research.complete.<ticket>. Reads triage.json from the worker dir as its prior-phase artifact. Spawned via plugins/dev/scripts/phase-agent-dispatch, which invokes it via slash command — hence `user-invocable: true`.

tools16

research-codebase

Conduct comprehensive codebase research using parallel sub-agents. **ALWAYS use when** the user asks to 'research', 'investigate', 'explore the codebase', 'how does X work', 'find out about', or needs deep analysis of how existing code is structured. Produces a research document in thoughts/shared/research/ with file:line references.

development15

phase-plan

Phase agent for the plan step of the 9-phase orchestrator pipeline (CTL-450). Wraps /catalyst-dev:create-plan and produces thoughts/shared/plans/<date>-<ticket>.md, then emits phase.plan.complete.<ticket>. Reads the prior research document from thoughts/shared/research/ as its prior-phase artifact. Spawned via plugins/dev/scripts/phase-agent-dispatch, which invokes it via slash command — hence `user-invocable: true`.

tools15

create-plan

Create detailed implementation plans through an interactive process. **ALWAYS use when** the user says 'plan this', 'create a plan', 'let's plan the implementation', 'design the approach', or wants a structured TDD implementation plan before writing code. Works best after /research-codebase.

development15

implement-plan

Implement approved technical plans from thoughts/shared/plans/. **ALWAYS use when** the user says 'implement the plan', 'start implementing', 'build from the plan', or wants to execute a previously created implementation plan using TDD (Red-Green-Refactor). Supports team mode for parallel implementation.

development15

discover-workflows

Research and catalog workflows from external Claude Code repositories

development15

oneshot

End-to-end autonomous workflow — research, plan, implement, validate, ship, and merge in one command. **ALWAYS use when** the user says 'oneshot', 'do everything end to end', 'full workflow', or wants to go from ticket/idea to merged PR autonomously. All phases run sequentially in the current session, using agent teams for parallelism when needed.

development15

validate-frontmatter

Validate and fix frontmatter consistency across all workflows

testing15

import-workflow

Import and adapt a workflow from external repositories

tools15

sensing-substrate

Observability / sensing-substrate cookbook for the recovery-pass delegate (and humans). Copy-paste-runnable LogQL + PromQL against the live OTel stack (Loki/Prometheus/Grafana) to see what the control loop is doing, detect silent freezes, read wedge signals, and turn each into an unstick action + a finding. **ALWAYS consult this skill when** the recovery-pass delegate (or a human) needs to query daemon logs/metrics, suspects the fleet is wedged or silently frozen, wants to count/see a wedge signal, detect a silent daemon (no logs in N minutes), or read cost/token/host-pressure metrics. Use when the user says "is the fleet stuck", "why isn't anything dispatching", "check the daemon logs", "query Loki", "query Prometheus", "is the monitor alive", or "what is the control loop doing".

testing15

phase-review

Phase agent for the review step of the 9-phase orchestrator pipeline (CTL-450). Wraps the /review skill (gstack) — explicitly skips /ultrareview per user decision. Reads verify.json from the prior phase, runs /review against the diff, writes ${ORCH_DIR}/workers/<TICKET>/review.json, and creates a remediation commit for any HIGH-severity finding that has a deterministic fix. Emits phase.review.complete.<ticket>. Spawned via phase-agent-dispatch via slash command — hence `user-invocable: true`.

testing14

phase-verify

Phase agent for the verify step of the 9-phase orchestrator pipeline (CTL-450). NEW skill — has no canonical wrapper. Runs read-only adversarial verification against the implement-phase diff: tsc, tests, lint, security scan, reward-hacking scan, code review, test coverage, silent-failure hunt. Writes ${ORCH_DIR}/workers/<TICKET>/verify.json then emits phase.verify.complete.<ticket>. Reads phase-implement.json as its prior-phase artifact. NEVER writes application code — only test files allowed. Spawned via phase-agent-dispatch via slash command — hence `user-invocable: true`.

development14

phase-remediate

Phase-agent that fixes a failing verify verdict so the pipeline self-heals instead of stalling to needs-human (CTL-653). Reads `${ORCH_DIR}/workers/<ticket>/verify.json`, fixes the `findings[]` (every severity:"high" plus the regression_risk drivers) directly via Edit/Write, commits the remediation, and emits `phase.remediate.complete.<ticket>`. The scheduler's router then re-dispatches `verify` to re-check (the verify⇄remediate cycle, cap 3). Dispatched as a `claude --bg` job by `phase-agent-dispatch`, which invokes it via slash command — hence `user-invocable: true`.

testing14

create-pr

Create pull request with automatic Linear integration. **ALWAYS use when** the user says 'create a PR', 'open a pull request', 'ship this', 'ready for review', or wants to push changes and create a GitHub PR. Handles commit, rebase, push, PR creation, description generation, and Linear ticket update.

tools14

phase-monitor-merge

Phase-agent that watches the open PR through to merge (CTL-449 Initiative 1 Phase 3). Lifts the active listen loop from the legacy `oneshot` Phase 5 body: event-driven wait on `catalyst-events wait-for`, inline resolution of CI fix-ups, bot review threads, and BEHIND rebases, then `gh pr merge --squash --delete-branch` when the PR reaches CLEAN. Linear Done transition and worktree teardown are owned by phase-teardown (CTL-703). Dispatched as a `claude --bg` job by `phase-agent-dispatch`, which invokes it via slash command — hence `user-invocable: true`.

testing14

phase-implement

Phase-agent wrapper that drives TDD implementation from an approved plan (CTL-449 Initiative 1 Phase 3). Reads `thoughts/shared/plans/*-<ticket>.md`, delegates the red→green→refactor cycle to `/catalyst-dev:implement-plan`, commits each plan phase as it lands, and transitions the Linear ticket to `inProgress`. Dispatched as a `claude --bg` job by `phase-agent-dispatch`, which invokes it via slash command — hence `user-invocable: true`.

development14

phase-pr

Phase-agent wrapper that opens the pull request after implementation completes (CTL-449 Initiative 1 Phase 3). Delegates to `/catalyst-dev:create-pr` (which already auto-runs `describe-pr` and transitions Linear to `inReview`), then writes the PR number + URL into the phase signal file so the downstream `phase-monitor-merge` agent can read it without re-querying GitHub. Dispatched as a `claude --bg` job by `phase-agent-dispatch`, which invokes it via slash command — hence `user-invocable: true`.

development14

setup-catalyst

tools13

merge-pr

Safely merge PR with verification and Linear integration. **ALWAYS use when** the user says 'merge the PR', 'merge this', 'ship it', or wants to merge an approved pull request. Runs tests, checks CI, verifies approvals, squash merges, cleans up branches, and moves Linear ticket to Done.

testing13

ticket-retro

Cross-ticket retrospective VIEW (CTL-789 Loop C / CTL-814). **ALWAYS use when** a ticket's PR has just merged (the workflow's compound closing step — runs automatically per ticket, CTL-831), or when the user says 'ticket retro', 'run a retro', 'retrospective', 'what did we learn lately', or 'how are the estimates calibrating'. Synthesizes everything the compound loops captured since the last retro — friction logs, learnings, compound-log calibration, catalyst.db / merged-PR actuals — into thoughts/shared/retros/ticket/<date>.md with a persisted watch-items block, and surfaces top patterns in the morning briefing's Plan today.

databases13

plugins/dev/skills/briefing-followup

--- name: briefing-followup description: Interactive walk-through of today's morning briefing. Loads the briefing markdown at thoughts/briefings/YYYY-MM-DD.md (built by [[morning-briefing]]), parses the structured decisions: frontmatter, walks the user through each open decision, and executes the selected action via supported handlers — schedule calendar entry, file Linear ticket, dispatch orchestrator, draft email, ADR-drift-specific actions (update ADR / file code-drift ticket / de

tools13

god

Cross-project omniscient status view — like `top` for Catalyst work streams. **ALWAYS use when** the user says '/god', 'what's happening across projects', 'what's running', 'show me all active work', 'what orchestrators are active', 'what sessions are running', or asks a free-form question about cross-project Catalyst state (e.g. 'what PRs are open?', 'which workers are stuck?', 'what happened in the last hour?'). Shows orchestrators with wave/worker progress, active PM and oneshot sessions with recency, and recent event activity (last 30 min) from the event log. Encodes all data-source locations and naming conventions as skill knowledge.

development13

setup-orchestrate

Bootstrap an orchestrator worktree and print a ready-to-run command. Use when the user wants to start an orchestration run — creates the worktree, initializes global state, and outputs a single copy-paste command to launch the orchestrator in a new terminal.

tools13

teardown

Safely delete orchestrator runtime state — worktrees and ~/catalyst/runs/{orchId} — after archiving artifacts to ~/catalyst/archives/{orchId}. **ALWAYS use when** the user says 'teardown', 'delete orchestrator', 'cleanup orchestrator', or 'remove worktree' for a finished orchestrator. Refuses to delete unless the archive sweep succeeded; use --force to bypass.

tools13

research-curate

Walk thoughts/shared/research/ and thoughts/shared/plans/, score each doc's staleness, regenerate INDEX.md, and append LLM-surfaced contradictions to CONTRADICTIONS.md (append-only). Source docs are never modified. Classification: current (age<90d AND refs valid), needs-review (age>=90d OR broken refs), likely-stale (age>=180d AND no recent activity). Inventory is deterministic; contradiction detection runs one LLM call per cluster (CTL-467 + CTL-468 / Initiative 4 Phase 1+2).

documentation13

setup-warp

Interactively configure Warp terminal as a Catalyst launcher. Checks Warp install, detects projects, interviews the user for display details (name/emoji/color/variants) and generates ~/.warp/tab_configs/*.toml files with session-naming and remote-control wiring. Idempotent — re-run to add or update projects.

testing13

ci-describe-pr

Generate PR descriptions autonomously for CI/automation (no user interaction). Non-interactive variant of /describe-pr for use in CI pipelines and automated workflows. Auto-detects current PR, generates description, and updates GitHub.

tools13

create-tickets

Create tickets via Linear MCP or generate formatted ticket text

tools13

oneshot

development12

orchestrate

Coordinate multiple tickets in parallel across worktrees with wave-based execution, worker dispatch, and adversarial verification

tools12

catalyst-filter

Protocol reference for the catalyst-filter semantic event routing daemon. Use when an orchestrator needs to wait for relevant events using a natural-language intent description instead of a precise jq predicate. Covers registration, waiting, deregistration, the wake event structure, prompt writing, context fields, and the fallback path when the daemon is not running.

testing12

debug-production-error

Debug production errors using Sentry MCP tools. Searches issues, analyzes stack traces, identifies root causes, and suggests fixes. Use when the user mentions a Sentry error, production exception, stack trace, error monitoring, crash report, or unhandled exception.

tools12

research-curate

documentation12

resume-handoff

Resume work from a handoff document. **ALWAYS use when** the user says 'resume handoff', 'pick up where we left off', 'continue from handoff', or provides a handoff document path. Verifies current codebase state against handoff, validates changes, and creates an action plan.

development12

prd-draft

Create a PRD (product requirements document) for features and initiatives. Guides through clarifying questions, generates a structured draft with hypothesis, strategic fit, non-goals, success metrics, and rollout plan, then offers multi-agent review. Use when the user asks to create a PRD, product spec, feature spec, requirements doc, or product brief.

development12

segment-analysis

Analyze user segments, cohorts, and customer groups using PostHog data. Creates retention tables, compares segment behavior, and generates group breakdowns. Use when the user asks about customer segmentation, cohort retention, user group comparison, churn analysis, or funnel analysis by segment.

data-ai12

retention-analysis

Cohort analysis and retention optimization framework. Identifies retention drivers and churn factors.

development11

catalyst-comms

Protocol guide for the `catalyst-comms` file-based agent communication CLI. Use when agents need to coordinate across worktrees, sub-agents, teams, or orchestrators — e.g. orchestrator passes `CATALYST_COMMS_CHANNEL`, user asks to "coordinate with", "ask the other agent", or workers need to share state without HTTP.

tools11

catalyst-events-query

Reference for the natural-language query subcommand of `catalyst-events`. Translates English queries through Groq into a structured DSL, compiles to a jq predicate, and runs against the canonical event log. Also documents the `:` / `?` keys in `catalyst-hud` (TUI) that drive the same compiler. Use when an agent needs to triage events without composing jq predicates by hand, or when documenting how to surface event subsets in dashboards.

development11

weekly-review

Review week's progress, meetings, learnings

tools11

write-prod-strategy

Product strategy docs using 7-component framework

development11

define-north-star

Identify and validate your North Star Metric. Aligns product strategy with key business metric.

testing11

decision-doc

Document important product decisions. Creates decision logs with rationale, alternatives, and trade-offs.

testing11

feature-results

Post-launch analysis and results documentation. Document what shipped and what we learned.

documentation11

activation-analysis

Analyze user activation using Setup → Aha → Habit framework. Identifies activation bottlenecks.

development11

experiment-metrics

STEDII framework for selecting trustworthy experiment metrics. Ensures metric validity and reliability.

development11

interview-guide

Create JTBD-based interview guides for user research. Structured questions for discovery interviews.

documentation11

journey-map

Create user journey maps and customer journey maps (dual mode)

tools11

napkin-sketch

ASCII wireframes + browser capture for design matching

testing11

prototype-feedback

Build → review → iterate prototype workflow. Structured feedback collection and iteration.

development11

user-interview

Systematically process user interviews to extract actionable insights. Batch processes interviews and generates research reports.

business11

meeting-agenda

Create structured meeting agendas for effective collaboration

tools11

meeting-cleanup

Batch process multiple meetings from a single day. Consolidates action items and insights across meetings.

tools11

meeting-feedback

Post-meeting effectiveness feedback and continuous improvement

databases11

analyze-cycle

Analyze cycle health and generate comprehensive report with actionable insights, risk analysis, capacity assessment, and specific recommendations

testing11

groom-backlog

Groom Linear backlog to identify orphaned issues, incorrect project assignments, and health issues

tools11

report-daily

Generate daily status report showing yesterday's deliveries, current work, and team members needing assignments

data-ai11

slack-message

Draft team communications for Slack. Creates clear, actionable messages for different contexts.

business11

status-update

Generate stakeholder status updates. Creates clear, concise progress reports for different audiences.

testing11

weekly-plan

Set next week's priorities

tools11

prototype

Advanced prototyping (Artifacts/Lovable/v0/Bolt)

tools11

user-research-synthesis

Turn user interviews into actionable insights. Advanced synthesis techniques and frameworks.

development11

competitor-analysis

Deep competitive analysis + ongoing monitoring. Checks user research for competitor mentions, sales notes, existing analysis. Integrates with retention-analysis and user-research-synthesis.

development11

prioritize

Classify PM tasks using LNO Framework (Leverage/Neutral/Overhead) to focus on high-impact work.

development11

meeting-notes

Transform meeting transcripts into structured action items, decisions, and key insights. Processes raw notes, voice memos, or recordings.

testing11

daily-plan

Generate PM daily plan with context

data-ai11

launch-checklist

Comprehensive product launch planning

testing11

connect-mcps

Connect MCPs for real-time tool integration

tools11

expansion-strategy

Upsell, cross-sell, and account growth tactics. Framework for revenue expansion.

development11

sync-prs

Sync GitHub PRs with Linear issues and identify correlation gaps

tools11

analyze-milestone

Analyze project milestone health with actionable insights, target date assessment, risk analysis, and specific recommendations

testing11

feature-metrics

Define success metrics using the STEDII framework for trustworthy experiment metrics.

development11

metrics-framework

Set up leading vs lagging indicators for product decisions. Framework for metric selection and tracking.

development11

experiment-decision

Decide when to A/B test vs just ship. Framework for experiment planning and prioritization.

development11

wait-for-github

Reference for safe GitHub event waits. Preferred path uses broker auto-detect (broker_claim_pr + filter.wake) for deterministic routing; falls back to two-phase catalyst-events wait-for when the daemon is absent. Includes a 3-minute diagnostic checkpoint to catch silent filter mismatches before they cause multi-hour stalls. Not a slash command — reference doc for skill authors.

testing11

groom-backlog

Groom Linear backlog to identify orphaned issues, incorrect project assignments, and health issues

tools10

validate-type-safety

Run the full 5-step TypeScript validation gate: type check, reward hacking scan, test inclusion, tests, and lint. This skill provides a structured multi-step pipeline that you cannot replicate on your own — it detects the project's package manager and linter automatically, checks tsconfig strictness, and invokes /scan-reward-hacking internally. **ALWAYS consult this skill when** the user mentions 'validate types', 'check type safety', 'type validation', 'type safety gate', wants to verify TypeScript changes before a PR, after completing a plan phase, or says anything about running type checks + tests + lint together. Even if you think you can run tsc yourself, use this skill — it catches issues you'd miss (tsconfig strictness, test exclusions, reward hacking patterns).

development10

analyze-milestone

Analyze project milestone health with actionable insights, target date assessment, risk analysis, and specific recommendations

testing10

analyze-user-behavior

Analyze user behavior patterns and cohorts using PostHog

tools10

audit-references

Audit plugin health and find broken references in manifests, commands, agents, and skills

tools10

prd-review-panel

Multi-agent PRD review (7 perspectives)

data-ai10

add-changelog-media

Add screenshots, screencasts (GIFs), or other media to changelog entries. Supports both local files and externally-hosted assets on R2/CDN. Inserts markdown image references into CHANGELOG.md files so they render on the website.

development10

error-impact-analysis

Analyze the impact and scope of production errors

research10

connect-mcps

Connect MCPs for real-time tool integration

tools10

generate-ai-prototype

Generate v0.dev, Lovable, or Bolt.new prompts for AI-powered prototyping

development10

scan-reward-hacking

Scan TypeScript code for reward hacking patterns — shortcuts that make linters pass without actually fixing type safety. This skill has a comprehensive checklist of 8 forbidden patterns with severity tuning (libraries vs apps) that you cannot reliably check on your own. **ALWAYS consult this skill when** the user says 'scan for hacks', 'check for type cheats', 'reward hacking', 'verify no shortcuts', wants to check for `as any`, `as unknown as`, `@ts-ignore`, non-null assertions (`value!`), `forEach(async`, or void tricks after fixing TypeScript errors. Also use after /fix-typescript completes, or when verifying TypeScript changes before marking work done. Accepts optional file/directory arguments to scope the scan.

development10

interview-feedback

Post-PM-interview debrief and continuous improvement for job search

databases10

interview-prep

Pre-interview preparation for PM job interviews (Product Sense, Execution, Behavioral)

tools10

journey-map

Create user journey maps and customer journey maps (dual mode)

tools10

meeting-agenda

Create structured meeting agendas for effective collaboration

tools10

weekly-plan

Set next week's priorities

tools10

meeting-feedback

Post-meeting effectiveness feedback and continuous improvement

databases10

weekly-review

Review week's progress, meetings, learnings

tools10

create-worktree

Create a git worktree for parallel work and optionally launch implementation session. **ALWAYS use when** the user says 'create a worktree', 'work in parallel', 'start a worktree for', or needs to work on multiple features simultaneously without switching branches.

tools10

compound

Closing ritual for the AI-native estimation feedback loop. **ALWAYS use when** the user says 'compound', 'close the loop', 'record learnings', 'compound-log', or wants to log post-merge actuals for a shipped Linear ticket. Writes a structured entry (linear.key, pr_number, merged_at, estimate_at_start, estimate_actual, cost_usd, wall_time_hours, what_worked, what_surprised_me) to `thoughts/shared/pm/metrics/YYYY-WW-compound-log.md` — one file per ISO week, appends.

documentation10

commit

Automatically analyzes code changes and creates git commits with conventional commit messages when the user indicates they want to save their work, commit changes, or says 'commit this', 'save my changes', 'let's commit'. Auto-detects commit type, scope, and ticket reference from branch name.

development10

fix-typescript

Fix TypeScript errors with strict anti-reward-hacking rules. **ALWAYS use when** the user says 'fix type errors', 'fix typescript', 'type-check is failing', or when TypeScript compilation errors need to be resolved. Ensures runtime type safety — fixes root causes instead of silencing errors with casts.

development10

report-daily

Generate daily status report showing yesterday's deliveries, current work, and team members needing assignments

data-ai10

create-tickets

Create tickets via Linear MCP or generate formatted ticket text

tools10

create-workflow

Create new agents or commands using discovered patterns and templates

data-ai10

reorganize

Analyze and reorganize a directory structure with safe reference updates

tools10

context-daily

Generate daily context engineering adoption dashboard

data-ai10

product-metrics

View key product metrics, KPIs, and conversion rates from PostHog

tools10

setup-warp

testing10

sync-prs

Sync GitHub PRs with Linear issues and identify correlation gaps

tools10

napkin-sketch

ASCII wireframes + browser capture for design matching

testing10

code-first-draft

Initial feature implementation from a PRD or feature description. **ALWAYS use when** the user wants to build a new feature, implement a PRD, create a first draft of code, or says things like 'build this feature', 'implement this PRD', 'code this up', 'create the initial implementation'. Also use when there's no existing codebase and user needs a standalone reference prototype.

development10

god

development10

iterate-plan

Update existing implementation plans based on feedback or changed requirements. **ALWAYS use when** the user says 'update the plan', 'change the plan', 'the requirements changed', 'revise the approach', or wants to modify an existing plan in thoughts/shared/plans/ after review feedback or discovered issues.

databases10

create-handoff

Create handoff document for passing work to another session. **ALWAYS use when** the user says 'create a handoff', 'hand this off', 'save progress for later', 'I need to stop here', or when context usage is high (>60%) during implementation and work needs to continue in a fresh session.

documentation10

trace-analysis

Analyze distributed traces and performance issues with Sentry

research10

validate-plan

Validate that implementation plans were correctly executed. **ALWAYS use when** the user says 'validate the plan', 'check if the plan was implemented correctly', 'verify the implementation', or after completing /implement-plan to confirm all phases were properly executed and success criteria met.

testing10