AGENT SKILL

ticket-id-gate

Pre-commit gate refusing a tracker id in staged library prose. Use when composing a role that authors the shipped library (the `ai-hats-dev` trait), or when diagnosing why the ticket-ids hook blocked a commit.

License 许可
MIT
所属仓库
muratovv/ai-hats
最近更新
2026-11-05
Stars
★ 3
Forks
1

01 前言 Front Matter

name
ticket-id-gate
ai_hats
{ "type": "skill", "schema_version": 1 }
license
MIT
description
Pre-commit gate refusing a tracker id in staged library prose. Use when composing a role that authors the shipped library (the `ai-hats-dev` trait), or when diagnosing why the ticket-ids hook blocked a commit.

02 资源文件 1

03 SKILL.md 正文

Ticket ID Gate

Pure-infrastructure hook-carrier skill. It contributes one git pre-commit hook and carries no agent-side decision logic — the value is delivered entirely through composition.

What it gates

A tracker id in prose the library ships. The library installs into other people's projects, where PROJ-1430 is a link into a tracker the reader does not have, and it costs context on every load. git log -S '<phrase>' finds the commit that introduced a line for anyone holding the repository; a tracker id travels nowhere.

Scope is staged files only, so the gate never retro-blocks a backlog it did not create.

The prefix is learned, never written down here

This script is itself shipped library content. Hardcoding one project's prefix in it would reproduce the exact leak it refuses. So it reads the prefix from the project's own card ids (shortest <prefix>-<digit> run, so MY-PROJ-42 yields MY-PROJ, matching how rack routes). AI_HATS_TICKET_PREFIX overrides it. No tracker and no override is a loud no-op: a project with no ids has none to leak.

What it does not judge

not judged why
<PREFIX>-NNN placeholders digits are required, so a CLI template teaching the shape is not a match
hooks/, git_hooks/, code a bare id there is often the whole comment — removing it is a rewrite
anything unstaged changed-files scope; the gate fires only on what this commit touches
another project's prefix only the ids this project mints are judged

When an id belongs

When prose names a string a machine prints, so the reader can recognise what appears on screen. Prefer quoting the message itself — a reader can grep that, and cannot grep a number. When the id really is the identifier, say so on the same line:

a wall of PROJ-1242 tripwire errors <!-- ticket-ids: allow the guard prints it -->

The reason is not decoration: the hook prints it back, and a marker without one is reported as (no reason given).

Relationship to the ticket-ids CI stage

Same invariant, two ranges. The hook is per-commit and staged-scope, so it catches an id at the keystroke. scripts/check_no_ticket_ids.py sweeps a wider corpus than the hook — the library, the docs a reader opens, and the project's own code — and runs inside merge-gate and push-gate, which is the one nothing lands on the base branch without. The hook shortens the loop; the stage is the boundary.

Override

After confirming the id belongs and the marker is wrong for the case, ask the supervisor for AI_HATS_TICKET_IDS_ACK=1, exported in the shell that runs the commit. Writing it onto your own command line is refused — see safety-guard.

The bypass is journalled, not merely printed to stderr.

04 同仓库更多 Skills

muratovv
muratovv/ai-hats

tool-evaluation-protocol

Time-bounded protocol for evaluating new tools, libraries, or methodologies before adoption. Use when evaluating a candidate dependency for the project, researching a methodology (e.g. ML/LLM frameworks, testing approaches), or following up on a hype-driven recommendation.

★ 3
muratovv
muratovv/ai-hats

systematic-debugging

4-phase bug-fix protocol (evidence, pattern, hypothesis, verify). Use when investigating any error, failure, or unexpected behavior, handling bug reports from users or monitoring, or diagnosing test failures with non-obvious causes.

★ 3
muratovv
muratovv/ai-hats

skill-template

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.

Skill与智能体开发
★ 3
muratovv
muratovv/ai-hats

skill-optimization

Audit and refactor library components to eliminate redundancy and staleness. Use during periodic library maintenance, after adding multiple new skills or rules, when a role's token budget is too high, or after retrospectives identify component issues.

Skill与智能体开发
★ 3
muratovv
muratovv/ai-hats

silent-fallback-gate

PreToolUse hook — refuses an Edit or Write that adds an inert broad except. Use when a Python edit was blocked for a silent fallback.

★ 3
muratovv
muratovv/ai-hats

retro-to-framework

Convert an observation about agent behavior — from a retrospective or from a single incident — into a framework-level change (hook, rule, skill, skill update). Use after a retrospective identifies problems that are not project-specific, after an incident where an agent misapplied a component it had read, when CLAUDE.md band-aids accumulate (more than 3 per-project rules that could be generic), or when the same problem recurs across multiple projects.

Skill与智能体开发
★ 3