Menu
SkillsMP a collecté 107 skills depuis muratovv/ai-hats. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 40 skills collectés sur 107.
Backlog lifecycle on the `rack` CLI — create / ls / context / transition / plan-extract, with field edits via `--set` and hypotheses/proposals on the `rack hyp` / `rack proposal` groups. Use for any task lifecycle transition, backlog read, field edit,…
Langue du texte source : anglais
Maintainer-only quality gates — pre-push e2e+smoke to master, plus the ->merge and ->done gates on the two roads a card takes into it
Langue du texte source : anglais
Isolated development using git worktrees so the main branch stays clean. Use when starting any non-trivial task (execute state), doing parallel work on multiple tasks, making risky changes you might want to discard, or delegating to a sub-agent (automatic via…
Langue du texte source : anglais
PreToolUse hooks enforcing global_rule_destructive_actions, rule_pause_before_shared_state_write and rule_backlog_discipline. Prevents destructive commands like in-place sed edits, deletion of protected data, and disk-formatting binaries, holds the pause…
Langue du texte source : anglais
Advanced git operations covering branches, conventional commits, worktrees, and rebasing. Use for any git operation beyond basic add/commit/push, for branch management, rebasing, and conflict resolution, or when setting up commit conventions for a project.
Langue du texte source : anglais
Provisions a Python venv inside every freshly created worktree — infrastructure only, no agent-side decision logic
Langue du texte source : anglais
Choose between Bash and dedicated Claude Code tools (Grep/Glob/Read/Edit) and edit files efficiently. Triggers on intent to grep/find/cat/sed/rg, multiple sequential reads, session-start context restore, codebase discovery, or multiple sequential Edits to one…
Langue du texte source : anglais
Triple-perspective code review (architect, security, quality). Use before finalizing any non-trivial code change, for self-review when no human reviewer is available, or when evaluating third-party code or pull requests.
Langue du texte source : anglais
Narrow shim for filing tasks via `rack create` from roles that mutate the backlog only at L1 (task-create only). Use when your role's mutation policy permits filing new tasks but forbids state transitions, hypothesis/proposal mutations, or direct backlog…
Langue du texte source : anglais
Pre-commit check that staged trait/role injections never point `see rule X` at a rule the agent cannot read. Use when composing the maintainer or role-curator role, when a commit touches a library/**/config.yaml injection, or when diagnosing why a commit was…
Langue du texte source : anglais
E2E fixture skill (HATS-823). Declares worktree wt_in/wt_out lifecycle hooks so the worktree-hook e2e can prove the materialize → create/teardown → live-script chain through the real ai-hats binary. Not shipped.
Langue du texte source : anglais
PostToolUse hook — flags oversized comment blocks and docstrings on every `.py` you Edit/Write and forwards them non-blockingly; fail-open, no manual invocation.
Langue du texte source : anglais
PostToolUse hook — runs ruff security rules (`--select S`) on every `.py` you Edit/Write and forwards findings non-blockingly; fail-open, no manual invocation.
Langue du texte source : anglais
Pre-commit gate for staged library SKILL.md — a license/provenance regression-guard plus agnix spec validation, for skill-authoring roles. Use when composing the maintainer or role-curator role, when a commit touches a library/**/SKILL.md, or when diagnosing…
Langue du texte source : anglais
Get a plan into its one canonical home — the tracker plan.md — never .claude/plans. Run this skill when you enter plan mode (EnterPlanMode), when you have a plan draft (incl. plan-mode / ExitPlanMode output), or when a task enters brainstorm→plan. It walks…
Langue du texte source : anglais
E2E fixture skill (HATS-1147). Declares the RETIRED lifecycle_hooks channel so the retirement e2e can prove that composition fails loudly through the real ai-hats binary instead of silently ignoring the declaration. Not shipped.
Langue du texte source : anglais
Plan-stage style forks, scope triage, and pre-commit artifact verification for documentation tasks. Use when a task changes any docs/*.md, README.md, or CONTRIBUTING.md, lifts structure from a precedent doc, enumerates six or more items to document, or…
Langue du texte source : anglais
HITL dialogue + CLI ops contract for role-judge — file-fix tasks instead of editing role/skill/rule sources
Langue du texte source : anglais
Audit a composed role against the user's project context for contradictions and interference, producing free-form findings with proposed fixes. Use when launched as a role-auditing role (role-auditor, role-judge, or sibling) whose first user message contains…
Langue du texte source : anglais
HITL protocol for the judge role (Phase 2 of the two-phase judge split) — discuss the Phase 1 draft with the supervisor, ack and execute proposed mutations via CLI, write the final report.
Langue du texte source : anglais
Triage one improvement opportunity — vote on an existing PROP or create a novel one via `rack proposal`. Use when you spot an improvement (rule/skill/code/process/doc) during a session review, or are sweeping the open proposal inbox for triage.
Langue du texte source : anglais
Canonical template and validation guide for ai-hats skills. Use when creating a new skill, reviewing an existing one for structural compliance, or deciding which pattern fits a new behavior.
Langue du texte source : anglais
Shell scripting, Makefile conventions, and modern CLI tooling. Use when writing or reviewing shell scripts, creating or modifying Makefiles, or choosing CLI tools for automation tasks.
Langue du texte source : anglais
Read-only audit protocol for the judge-auditor role (Phase 1 of the two-phase judge split) — produces a draft report with proposed verdicts and mutations for the HITL judge to consume.
Langue du texte source : anglais
Vote on one active hypothesis (HYP-NNN) against session evidence — pick confirmed/refuted/inconclusive/n-a + a recommendation and persist via `rack hyp`. Use when sweeping active hypotheses during a session review (reflect-session, session-reviewer, or judge).
Langue du texte source : anglais
Single-pass review of one session run, producing a hats-reflect-session/v1 document (summary, observations, one hypothesis verdict per active HYP, proposal actions). Use when running as reflect-session or session-reviewer over a specific session id.
Langue du texte source : anglais
Convert project retrospective findings into framework-level improvements (rules, skills, skill updates). Use after a retrospective identifies problems that are not project-specific, when CLAUDE.md band-aids accumulate (more than 3 per-project rules that could…
Langue du texte source : anglais
Advanced rack beyond day-to-day lifecycle: authoring a new custom backlog, and cross-project work. Use when defining a backlog beyond the built-in tasks/HYP/PROP, or registering and searching backlogs across several projects.
Langue du texte source : anglais
Clean context reset protocol covering commit work, write handoff, update task card, and inform supervisor. Use when the context window is approaching its limit (system signals compression), when switching to a fundamentally different task domain, or when…
Langue du texte source : anglais
The single entry point for the brainstorm→plan quality gate — a table of contents mapping each required plan section to the skill that fills it. Use when a task enters brainstorm→plan or when drafting/revising plan.md, to route each section to its owning…
Langue du texte source : anglais
The Requirements stage of the plan-gate — fills plan.md's Requirements section via structured Q&A where the agent proposes a cited best-guess per question and the supervisor reviews. Reached through plan-gate (which owns the brainstorm→plan entry), not as an…
Langue du texte source : anglais
Audit a role composition for coherence — injection/skill/rule mismatches and composer gaps
Langue du texte source : anglais
Post-work analysis to identify systemic improvements (5 Whys, classify, archive). Use when the supervisor asks to "write a retro" / "do a retrospective", at the end of a multi-task work session (wrap-up across several closed tasks), after task completion…
Langue du texte source : anglais
Wire a work breakdown into the tracker — depends_on edges, frontier, expand–contract for wide refactors. Use when filling plan.md's Steps section (routed from plan-gate), decomposing an epic into child tasks, or carving a mid-execute remainder into successor…
Langue du texte source : anglais
Focused post-task summary covering architectural decisions, decision forks, pitfalls, and plan deviations. Use after the backlog manager transitions a task to done or failed, when handing off a completed task for review, or when the supervisor asks what…
Langue du texte source : anglais
Compare implementation diff against task acceptance criteria and ADRs to surface drift. Use when a task is in review state before transitioning to done, when integrating a worktree spanning two or more sessions, during a pre-merge audit when the diff exceeds…
Langue du texte source : anglais
After execute-stage commits land (diff finalized) and BEFORE the task transitions to done, file a companion HYP with an explicit verification_protocol — or record an explicit "no behavior change" note for refactors at plan-stage. NEVER file the HYP at…
Langue du texte source : anglais
Backlog lifecycle on the rack CLI (hatrack) — create / ls / context / transition, with field edits and hyp/proposal staying on `ai-hats task`. Use when a session composes the `hatrack-trait` (rack is the selected backlog manager) for any task lifecycle…
Langue du texte source : anglais
Backlog lifecycle on the rack CLI (hatrack) — create / ls / context / transition, with field edits and hyp/proposal staying on `ai-hats task`. Use when a session composes the `hatrack-trait` (rack is the selected backlog manager) for any task lifecycle…
Langue du texte source : anglais
Backlog lifecycle on the rack CLI (hatrack) — create / ls / context / transition, with field edits and hyp/proposal staying on `ai-hats task`. Use when a session composes the `hatrack-trait` (rack is the selected backlog manager) for any task lifecycle…
Langue du texte source : anglais