本文へ移動
cccskills
無料GitHub で公開

github-project-triage

Triages GitHub issues and PRs into maintainer-facing cards: what each is, why it matters, author trust, risk, test and CI state, blockers, and next action. Use when the user says triage inside a repository or needs to work through an issue or PR queue.

インストール方法を見る

含まれるファイル(2)

  • SKILL.md4.5 KB
  • LICENSE1.0 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

GitHub Project Triage

Attribution: Sourced from steipete/agent-scripts by Peter Steinberger.

Use the current GitHub project by default when the user says triage from inside a repo. Triage means maintainer-facing item cards: what each issue/PR is about, why it matters, author trust, fit, risk, proof/test state, blockers, and next action. Never return only queue numbers or opaque refs.

Scope Rule

If the user says triage and the current working directory is a Git repo with a GitHub remote, triage only that project. Do not broaden to all org queues unless the user says broad, all, everything, names multiple owners/orgs, or asks for cross-repo triage.

Find the current project:

repo=$(gh repo view --json nameWithOwner --jq .nameWithOwner 2>/dev/null || true)
if [ -z "$repo" ]; then
  url=$(git remote get-url origin 2>/dev/null || true)
  repo=$(printf '%s\n' "$url" | sed -E 's#^git@github.com:##; s#^https://github.com/##; s#\\.git$##')
fi
printf '%s\n' "$repo"

Current-project triage starts with:

gh issue list --repo "$repo" --state open --limit 50 \
  --json number,title,author,labels,createdAt,updatedAt,url
gh pr list --repo "$repo" --state open --limit 50 \
  --json number,title,author,isDraft,reviewDecision,mergeStateStatus,createdAt,updatedAt,url

Before acting on any issue or PR, read the latest comments. For small queues (about 10 open items or fewer), inspect all items. For larger queues, inspect the top priority slice.

gh issue view <n> --repo "$repo" \
  --json number,title,author,body,comments,labels,createdAt,updatedAt,url
gh pr view <n> --repo "$repo" \
  --json number,title,author,body,comments,files,commits,isDraft,reviewDecision,mergeStateStatus,statusCheckRollup,createdAt,updatedAt,url
gh pr diff <n> --repo "$repo" --patch

Only comment, close, merge, rerun, or patch with strong evidence.

Item Evaluation

Classify each item:

  • bug: require repro/log/failing test/current-main proof; identify root cause before recommending fix/merge.
  • feature: require end-to-end test plan. State exactly what credential/access is missing before work can be considered complete.
  • dependency: explain package group, major/minor risk, failing checks, runtime/engine changes.
  • security: raise priority, require careful code-path proof, tests, and trust/context.
  • docs/internal: lower risk, but explain user-visible relevance.

Judge:

  • Fit: good / mixed / poor, with one reason.
  • Risk: low / medium / high, with blast radius.
  • Proof: current CI, local repro, failing test, live E2E, or missing proof.
  • Blocker: first-time contributor CI approval, failing check, missing key, unclear direction, stale branch, conflicts.
  • Next: approve CI, run test, request repro, split PR, patch locally, merge after green, close with proof, or defer.

Triage Heuristics

Prioritize:

  • PRs with green or nearly-green CI, recent maintainer activity, or low-risk dependency/docs/test changes.
  • Issues that are reproducible, recently reported, or block releases.
  • Security, release, auth, install, CI, and data-loss reports before cosmetic items.
  • Bugs with clear current-main reproduction and narrow owner path.

Deprioritize:

  • Old broad feature requests with no reproduction or owner signal.
  • Feature/provider PRs that need unavailable API keys or accounts for end-to-end proof.
  • Broad generated changes without a clear user problem, test plan, or trusted author signal.

Output Shape

Repo: owner/name
Source: gh list/view/diff/checks, local source/tests where inspected

Immediate:
- #123 PR: title
  What: one-line summary in plain words.
  Type/Fit/Risk: bug|feature|dependency; good|mixed|poor; low|medium|high because ...
  Trust: @login; acct date; repo/global activity; known/unknown/bot.
  Proof: CI/repro/test/e2e state.
  Blocker: none / missing key / first-time CI approval / failing lint / unclear direction.
  Next: exact maintainer action.

Needs judgment:
- #124 issue: ...

Defer/close:
- #125 issue: ...

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Use when long-lived agents, project memories, system prompts, or playbooks are repeatedly summarized, rewritten, or optimized and risk losing domain detail, provenance, or execution learnings.

日本語の概要は準備中です。原文の説明を表示しています。

mouadja02/skills102026年10月16日 更新

Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.

日本語の概要は準備中です。原文の説明を表示しています。

mouadja02/skills102026年10月16日 更新

Adds educational comments to a code file so it becomes a learning resource, asking for the file (with a list of close matches) if none is given. Use when preparing code for learners, onboarding, or teaching.

日本語の概要は準備中です。原文の説明を表示しています。

mouadja02/skills102026年10月16日 更新

Write, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when creating or modifying scripts that manipulate documents, layers, paths, text frames, colors, symbols, artboards, or any Illustrator DOM objects. Covers the complete JavaScript object model, coordinate system, measurement units, export workflows, and scripting best practices.

日本語の概要は準備中です。原文の説明を表示しています。

mouadja02/skills102026年10月16日 更新

Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases, file systems) - Implementing policy-based access controls for agent tool usage - Adding semantic intent classification to detect dangerous prompts - Creating trust scoring systems for multi-agent workflows - Building audit trails for agent actions and decisions - Enforcing rate limits, content filters, or tool restrictions on agents - Working with any agent framework (PydanticAI, CrewAI, OpenAI Agents, LangChain, AutoGen)

日本語の概要は準備中です。原文の説明を表示しています。

mouadja02/skills102026年10月16日 更新

Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use this skill when: - Evaluating an agent system's security posture before production deployment - Running a compliance check against OWASP ASI 2026 standards - Mapping existing security controls to the 10 agentic risks - Generating a compliance report for security review or audit - Comparing agent framework security features against the standard - Any request like "is my agent OWASP compliant?", "check ASI compliance", or "agentic security audit"

日本語の概要は準備中です。原文の説明を表示しています。

mouadja02/skills102026年10月16日 更新

mouadja02 のスキルをすべて見る

このスキルの問題を報告する