Browse skills

自律型Claude Codeループのパターンとアーキテクチャ — シンプルなシーケンシャルパイプラインからRFC駆動のマルチエージェントDAGシステムまで

The English summary is being prepared. Showing the original description.

一行の目的をマルチセッション・マルチエージェントエンジニアリングプロジェクトの ステップバイステップの構築計画に変換する。各ステップは自己完結型のコンテキスト ブリーフを持ち、新しいエージェントがコールドスタートで実行可能。 敵対的レビューゲート、依存関係グラフ、並列ステップ検出、アンチパターン カタログ、計画変更プロトコルを含む。 トリガー条件：複雑なマルチPRタスクの計画・ブループリント・ロードマップを 要求された場合、または複数セッションが必要な作業が記述された場合。 トリガーしない場合：単一のPRまたは3回未満のツール呼び出しで完了可能なタスク、 またはユーザーが「just do it」と言った場合。

The English summary is being prepared. Showing the original description.

Vets third-party skills, plugins, MCP servers, GitHub Actions and model weights before install, with a verdict (PASS, CONDITIONAL, HOLD, FAIL) and install terms. Trigger on any should-I-install question, even with its files or hooks pasted in or a scan already clean; is this skill safe, vet this MCP server, check this GitHub Action, is this checkpoint safe or commercially usable, what does this installer write, a licence check before a fold-in, what changed in a plugin update; or say trustwarden (vet, revet, terms, refresh). Uses skillspector, zizmor, pinact and Scorecard when present; lists files no scanner read. Runtime permissions are gatewarden's; secrets shieldwarden's; your own skills skillwright's; sandboxing a download hypervrunner's.

The English summary is being prepared. Showing the original description.

Finds what changed in Claude — docs, release notes, changelogs, GitHub and community posts on Claude Code, claude.ai, Cowork, the API and models — and turns each change into adopt rows for your setup, plus a fit card for a new model or feature and a monthly bench of your skills against public skill and plugin repos (build, adopt or skip). Trigger on what changed since a date or version, a weekly sweep, features worth adopting, a feature that broke unannounced, a stale model table, what a new model or feature is good for, or how your skills compare with popular or little-known skill and plugin repos; or say scoutwright (sweep, since, watch, adopt, fit, bench, sources, refresh). Outside research is researchscribe's; applying a row, skillwright's; config, rigwright's; schedules, agentwright's; tier picks, promptwright's.

The English summary is being prepared. Showing the original description.

Use after implementing features - verifies each acceptance criterion with structured testing and posts verification reports to the GitHub issue

The English summary is being prepared. Showing the original description.

Land one PR end-to-end (changelog + thanks, lint, merge, back to main).

The English summary is being prepared. Showing the original description.

When the user requests to create or customize an academic personal website from a GitHub template repository. This skill handles the complete workflow of forking academic template repositories (like academicpages.github.io), extracting structured personal information from memory or provided data, and systematically updating configuration files (_config.yml), navigation menus (_data/navigation.yml), content pages (_pages/about.md), and publication listings (_publications/). It specifically handles academic profiles including personal details, education background, research experience, publications, skills, and contact information. Triggers include requests to 'fork and customize academic homepage', 'build personal academic website', 'create research portfolio', or 'set up GitHub pages with academic template'.

The English summary is being prepared. Showing the original description.

Adds comprehensive accessibility testing to CI/CD pipelines using axe-core Playwright integration or pa11y-ci. Automatically generates markdown reports for pull requests showing WCAG violations with severity levels, affected elements, and remediation guidance. This skill should be used when implementing accessibility CI checks, adding a11y tests to pipelines, generating accessibility reports, enforcing WCAG compliance, automating accessibility scans, or setting up PR accessibility gates. Trigger terms include a11y ci, accessibility pipeline, wcag ci, axe-core ci, pa11y ci, accessibility reports, a11y automation, accessibility gate, compliance check.

The English summary is being prepared. Showing the original description.

Coordinator workflow for orchestrating dockeragents through fix-review-iterate-present loop. Use when delegating any task that produces code changes. Ensures agents achieve 10/10 quality before presenting to human.

The English summary is being prepared. Showing the original description.

Use this to view the timeline of GitHub issues or pull requests. Note that it does not fetch the title and description, unlike `gh pr view`.

The English summary is being prepared. Showing the original description.

Use when GitHub may have shipped a GraphQL schema update affecting timeline event unions (PullRequestTimelineItems / IssueTimelineItems), when the gh-timeline dispatcher fallback is hitting more than expected, before a gh-timeline release, or when the user requests phrases like "verify timeline coverage", "audit gh-timeline schema", "check for new timeline events", "GitHub schema changed". Walks through schema diff → patch → test update → live verification → optional fixture refresh, marking each spot where a human decision is required.

The English summary is being prepared. Showing the original description.

make review / make review-close があるプロジェクトで、Codex の PR レビューと修正を最大5周回す。「レビューループ」「review-loop」「make review で回して」で発火。各レビューを対象 commit と対応付け、根拠を確認して修正し、完了後にクローズする。

The English summary is being prepared. Showing the original description.

プロジェクト監査。「監査して」「audit」「/audit」で発火。設計/UX/品質/テストなどの観点でコードベース全体を監査し、課題をissuesディレクトリに書き出す。実行ログで重複実行を防止。特定の差分・コミットのレビューには使わない（codex-review / cross-review を使う）。

The English summary is being prepared. Showing the original description.

status:investigated な issue の調査結果コメントを読み、実装可能なら status:ready に昇格させる

The English summary is being prepared. Showing the original description.

GitHub issue を起点に実装を始めるときに、実装より前に使うスキル。「issue

The English summary is being prepared. Showing the original description.

open な issue 一覧を取得し、内容を分析して status ラベルを付与する

The English summary is being prepared. Showing the original description.

GitHub issue を新規作成・下書きするとき、または既存 issue の本文を書き直すときに必ず使うスキル。「issue を作って」「issue 化して」「これを issue にまとめて」のような依頼で発火し、`gh issue create` を直接呼ぶ前に必ず参照する。人間が合意した内容だけを、意味を足さずに issue へ残すための基準を定める。

The English summary is being prepared. Showing the original description.

GitHub に Pull Request を作成するスキル。ユーザーが「PRを作って」「プルリクエストを出して」「PR作成して」と言ったとき、またはコミット済みの変更をレビューに出したいときに使用する。

The English summary is being prepared. Showing the original description.

Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. DO NOT TRIGGER when: task is completable in a single PR or fewer than 3 tool calls, or user says "just do it".

The English summary is being prepared. Showing the original description.

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

The English summary is being prepared. Showing the original description.

Master of defensive Bash scripting for production automation, CI/CD pipelines, and system utilities. Expert in safe, portable, and testable shell scripts.

The English summary is being prepared. Showing the original description.

Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI.

The English summary is being prepared. Showing the original description.

Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.

The English summary is being prepared. Showing the original description.

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches. AI agents running in CI/CD pipelines.

The English summary is being prepared. Showing the original description.