handoff
Session handover: when context fills, a phase closes, or the topic changes, write an action-oriented handover to docs/SESSION_STATE.md, then recommend /clear.
38,472 Skills
Search uses this published catalog; rankings and counts are snapshots.
Session handover: when context fills, a phase closes, or the topic changes, write an action-oriented handover to docs/SESSION_STATE.md, then recommend /clear.
Translation integrity: every key present in every language, no hardcoded strings, consistent placeholders and plurals. Runs when user-facing text changes.
Production incident response: diagnose → mitigate → resolve, then a blameless postmortem and a repeatable runbook. Stop the impact first, root cause second. Use when production is degraded or broken, and again for the postmortem afterwards.
Refine-to-Done loop: repeat until tests green + review clean + nothing deferred; bounded. Not the harness /loop.
Stack-agnostic observability: structured logs, correlation ids, metrics and traces; no PII or secrets in logs. Makes a production issue traceable to why it happened. Use when adding a log line, an error path, a metric, or when an incident could not be traced.
Stack-agnostic performance: measure first, find the bottleneck, then optimise. N+1, needless allocation, wrong async boundary, missing index/cache, heavy payload. No premature optimisation. Use when something is slow, before optimising anything, and when a change touches a hot pa
Prepare a concise engineering incident handoff from supplied facts. Use when transferring an unresolved or recently mitigated incident between engineers, teams, or shifts, and the receiver needs the current state without re-reading the whole timeline.
Find breakage outside the diff and prove it with a repro or test. Use for fallout beyond changed lines; use adversarial-review to attack the diff itself or /review for routine review.
Model stateful flows, protocols, and state machines in TLA+. Use for new formal models of behavior tests rarely cover; use tla-check to re-check models or maintain-tla-model after code changes.
Explain code rationale from git, PRs, issues, and connected MCP sources with citations. Use for design rationale, regressions, and postmortems; use explain-how for current behavior or droid search for session history.
Update TLA+ models after changes to covered code, then run tla-check. Use create-tla-model for first models or tla-check to check unchanged models.
Refresh a drifted project verify-<app> skill after feature changes. Use create-verify-skill for the first skill, or agent-browser or tuistory for a one-time drive.
Race independent droid exec candidates in separate worktrees and combine their strongest parts. Use for competing designs; use Missions for multiple features or Spec mode for one plan.
Write a failing behavior test, make it pass, then refactor. Use for TDD, regression tests, or bugs with obvious repros; use eval-runs or eval-hillclimb for skill or prompt evals.
Find and remove AI-slop comments — ones that restate the code, describe another layer's behavior, or narrate planning that never shipped — while protecting the comments that carry real reasoning. Use when a reviewer calls a comment useless, unclear, or AI-written — including one
Format git commit messages following Conventional Commits 1.0.0 specification. Use when the user asks to commit changes, create a git commit, or mentions committing code. Ensures consistent, semantic commit messages that support automated changelog generation and semantic version
Catalog captured:2026-11-21