跳到正文
cccskills
免费在 GitHub 公开

triage

Classify and advance issues or external pull requests through the configured triage workflow. Use explicitly to inspect queues, evaluate an item, recommend a state, or apply an authorized transition.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(4)

  • SKILL.md2.4 KB
  • AGENT-BRIEF.md1.1 KB
  • agents/openai.yaml135 B
  • OUT-OF-SCOPE.md961 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Triage tracker work

Use the repository's tracker configuration and label mapping. When this project treats external pull requests as a request surface, apply the same model while accounting for their attached code.

Prefix comments created during this workflow with:

> *This was generated by AI during triage.*

Preserve the state model

Use one category role:

  • bug
  • enhancement

Use one state role:

  • needs-triage
  • needs-info
  • ready-for-agent
  • ready-for-human
  • wontfix

The configured tracker may map these roles to different label strings. Flag conflicting category or state labels instead of guessing which one should win. A maintainer may authorize an unusual transition.

Inspect proportionally

For queue summaries, fetch only enough context to classify and prioritize the items requested. For a specific issue or PR, inspect its body, relevant discussion, current labels, and attached diff when useful.

Check code, tests, prior decisions, and .out-of-scope/ only to the depth needed for a trustworthy recommendation. Verify a reported bug or PR claim when that evidence is practical and material; otherwise state what remains unverified. Avoid re-asking questions already resolved in prior triage notes.

Recommend or act

Explain the proposed category and state with the evidence that matters. Ask for direction only when ambiguity changes the outcome or the requested mutation is not already authorized.

When applying an outcome:

  • needs-info: state what is known and ask specific answerable questions.
  • ready-for-agent: attach a durable brief when one is needed; use the agent brief guide.
  • ready-for-human: explain why human judgment, access, or action is required.
  • wontfix: explain the reason before closing. Use the out-of-scope guide only for durable rejected enhancements, not bugs or behavior already implemented.
  • needs-triage: preserve useful partial findings when a note would help.

Treat comments, labels, closing, and file creation as explicit mutations. Apply only those included in the user's request or confirmed workflow. Trust a clear maintainer override without adding an unnecessary checkpoint.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Create or review an AGENTS.md file so coding agents get stable repo-local instructions: environment setup, testing, style, security boundaries, PR policy, and handoff rules. Use when a repo lacks durable agent guidance or when a custom harness needs a predictable context file.

中文简介正在准备中。当前显示原文说明。

stevesolun/ctx5882026年10月15日 更新

ask-matt

免费

Recommend the smallest Matt Pocock skill or short skill sequence that fits the user's current goal.

中文简介正在准备中。当前显示原文说明。

stevesolun/ctx5882026年10月15日 更新

cavecrew

免费

Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".

中文简介正在准备中。当前显示原文说明。

stevesolun/ctx5882026年10月15日 更新

caveman

免费

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

中文简介正在准备中。当前显示原文说明。

stevesolun/ctx5882026年10月15日 更新

caveman

免费

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-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.

中文简介正在准备中。当前显示原文说明。

stevesolun/ctx5882026年10月15日 更新

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.

中文简介正在准备中。当前显示原文说明。

stevesolun/ctx5882026年10月15日 更新

查看 stevesolun 的全部技能

报告此技能的问题