Development skills

Shape every agent comment as a short typed brief the owner can triage in seconds — 🔴 issue · 💡 proposal · ✅ done · 🔀 choice · 🛠 action · 👀 review — with all the depth collapsed behind it. Enforced by the require-owner-brief hook. Use before posting ANY GitHub comment as an agent, or when asked to "make this shorter", "brief me", "just tell me what I need to do".

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

Tech Lead role in AID methodology. Use for architecture decisions, code reviews, technical direction, operational readiness, team guidance.

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

Comprehensive code review for commits and pull requests. Covers security, TDD, code quality, and documentation standards.

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

Use when writing, editing, debugging, or reviewing dealer language code in btn, dlr, or script files. Provides the complete dealer DSL syntax reference for bridge hand generation constraints.

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

Use when inspecting or editing Blender scenes through the official Blender Lab MCP server. Check the add-on connection, read the scene first, and verify edits.

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

Build a SuperCollider piece up while it plays - start a sound, change it in place, layer it, and stop it cleanly - using the dsh-supercollider tools (sc_exec, sc_nodes, sc_play, sc_stop-via-sc_exec) and the idioms that make a session survive (Ndef, ProxySpace, Pbind, ~variables, s.freeAll).

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

Read a media file's real structure with ffprobe through media_run - the JSON invocation and how to read it, what every family of field means, how to count frames, sample without decoding everything, detect HDR and interlacing, and diagnose a missing duration, a stream with no frames or a container that lies. Covers when media_probe's own report is already enough.

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

Generate QR code images from text, URLs, or contact information using Python's qrcode library. Supports customization (size, margin, color, error correction) and batch generation.

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

システムログを分析してエラーの根本原因を特定し、段階的に深堀りしていくデバッグ専門家スキル。 アプリケーションログ、システムログ、クラウドサービスログなど様々な形式に対応。 5 Whys、タイムライン分析、Fishbone分析などのRCA（根本原因分析）手法を用いて 問題の本質を突き止め、再発防止策まで提案する。 Use when analyzing system logs to find error root causes, debugging application issues, or performing technical post-mortem analysis with log data. For organizational incident management processes (post-incident review, corrective action plans, incident reports without log data), use incident-rca-specialist instead. Triggers: "analyze this log", "find the root cause", "debug this error", "why is this failing", "log analysis", "what caused this crash", "troubleshoot this issue"

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

Render CLIを使用したクラウドサービス管理の専門スキル。デプロイ、ログ監視、SSH接続、PostgreSQL接続、サービス管理などRenderプラットフォームのCLI操作を効率的に支援。定期的に公式ドキュメントをチェックして最新情報を取得。Use when managing Render services via CLI, deploying applications, viewing logs, connecting to databases, or automating cloud infrastructure tasks.

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

Mine Claude Code session logs for skill idea candidates. Use when running the skill generation pipeline to extract, score, and backlog new skill ideas from recent coding sessions.

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

Diagnose and fix MARP slide layout issues including whitespace problems, box alignment, bullet formatting, and CSS rendering inconsistencies. Use when MARP slides have visual layout problems or need CSS optimization.

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

Evaluate project deliverables (code, docs, config) and calculate a 0-100 completeness score with weighted criteria and prioritized action items. Use when assessing project readiness, reviewing milestones, or identifying gaps before release.

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

インシデント発生後の振り返りと根本原因分析を体系的に実施するスキル。 ログファイル解析や技術デバッグが必要な場合は log-debugger を使用すること。 本スキルはインシデント管理プロセス（タイムライン構築、影響評価、 是正措置計画、再発防止策）に特化する。ログデータの分析ではなく、 組織的な振り返りプロセスと是正措置の策定が主目的である。 Use when conducting post-incident reviews without log analysis, creating corrective action plans, or performing organizational root cause analysis focused on process improvement. NOT for log file debugging. Triggers: "post-incident review", "corrective action plan", "incident report作成", "再発防止策", "RCAレポート", "是正措置", "インシデント振り返り"

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

OpenAI Codex CLIを使用してドキュメントやコードのレビューを依頼するスキル。GPT-6.1-Solモデルをxhigh推論モードで呼び出し、深い分析によるレビューを実行。レビュー結果を指定フォルダに出力し、その内容を確認・分析する機能を提供。コードレビュー、ドキュメントレビュー、設計書レビュー、テスト計画レビューなど、専門的なレビューが必要な場面で使用。

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

Automatically analyze a codebase and generate comprehensive CLAUDE.md documentation for future Claude Code sessions. Use when onboarding to a new project, creating project documentation, or generating AI coding assistant context files.

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

Generate AI-powered BPO service proposals for Japanese companies in the US market. Use when creating outsourcing proposals with AI service menus, ROI estimation, implementation roadmaps, and bilingual (JA/EN) proposal documents for 在米日系企業向けAI実装.

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

4人の異なる専門家ペルソナ（20年ベテランエンジニア、TDDエキスパート、Clean Codeエキスパート、バグハンター）で ソースコードを批判的にレビューするスキル。設計判断、テスト容易性、可読性、バグ検出の観点から コードの問題を検出し、改善提案を行う。Python/JavaScriptに対しては追加のチェックポイントを適用。 バグハンターは状態遷移、例外パス、依存関係、非同期競合に特化し、本番環境での問題を事前に検出する。 Use when reviewing source code from multiple expert perspectives to find design flaws, testability issues, code quality problems, and runtime bugs. Triggers: "critical code review", "multi-persona code review", "expert code review", "code quality assessment", "find bugs".

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

Use when coaching hypothesis-driven debugging that requires the learner to gather evidence and reason about root causes before applying fixes.

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

Use when 需要按 Alibaba Java Coding Guidelines（阿里巴巴 Java 编码规范）审查、生成或重构 Java、Spring、MyBatis、Maven、MySQL、SQL、日志、异常、安全或数据库相关代码。

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

Control the user's existing Safari 26 session through a persistent script-driven JavaScript REPL. Use for inspecting, navigating, clicking, filling, selecting, uploading, or verifying webpages in Safari when an MCP/plugin transport is unavailable.

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

Search, scrape, and interact with the web via the Firecrawl CLI. Use this skill whenever the user wants to search the web, find articles, research a topic, look something up online, scrape a webpage, grab content from a URL, get data from a website, crawl documentation, download a site, or interact with pages that need clicks or logins. Also use when they say "fetch this page", "pull the content from", "get the page at https://", or reference external websites. This provides real-time web search with full page content and interact capabilities — beyond what Grok can do natively with built-in tools. Do NOT trigger for local file operations, git commands, deployments, or code editing tasks.

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

Webアプリの準備→要件定義→設計→実装→公開→品質ゲートを実行する内部オーケストレーター。Claude Codeの /build-app /improve-app、Codexの $build-app / $improve-app から明示的に委譲された場合、custom agent起動時、または利用者が $app-orchestrator を明示した場合だけ使用する。一般のアプリ相談から暗黙起動しない。

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

governance secret helperの利用可否を確認したいとき、key名とbackendを値を露出せず監査したいときに使う。

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