adjust-pr-base
Use when a pull request base might be wrong after `git rebase`, `gh pr create`, or stacked PR work and the agent needs a fixed procedure to inspect the current PR and correct its base branch.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
animate
Review a feature and enhance it with purposeful animations, micro-interactions, and motion effects that improve usability and delight. Use when the user mentions adding animation, transitions, micro-interactions, motion design, hover effects, or making the UI feel more alive.
animation-best-practices
CSS and UI animation patterns for responsive, polished interfaces. Practical implementation patterns and troubleshooting for common animation issues. Use when implementing hover effects, tooltips, button feedback, transitions, or fixing animation issues like flicker and shakiness.
ast-grep
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for code patterns, find specific language constructs, or locate code with particular structural characteristics.
batch-grill-me
A relentless interview that asks every frontier question at once, round by round.
codex-consultation
>-
codex-review
Run automated code review using Codex CLI. Use when the user wants an automated code review of uncommitted changes, a specific commit, or changes against a base branch. This skill runs `codex review` non-interactively and returns structured feedback — it does not post comments on PRs or interact with GitHub.
cognitive-rhythm-writing
説明的な文章に緩急を設計するための規範。緩急を装飾ではなく認知モードの切替（観察→逡巡→断定→再観察）と未回収の緊張の管理として扱い、文の拍、段落の密度波形、節の入り方、緩みと駄文の判別、執筆後の機械的な点検手順を定める。読み物として読ませたい章・記事・解説文を生成するとき、または「密度はあるが平坦でおもしろくない」文章を診断・修正するときに使用する。
contextual-commit
>-
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications
dd-file-issue
File GitHub issues to the right repository (pup CLI or plugin)
drawio
Always use when user asks to create, generate, draw, or design a diagram, flowchart, architecture diagram, ER diagram, sequence diagram, class diagram, network diagram, mockup, wireframe, or UI sketch, or mentions draw.io, drawio, drawoi, .drawio files, or diagram export to PNG/SVG/PDF.
empirical-prompt-tuning
agent 向けテキスト指示（skill / slash command / task プロンプト / CLAUDE.md 節 / コード生成プロンプト）を、バイアスを排した実行者に動かしてもらい、両面（実行者の自己申告 + 指示側メトリクス）で評価して反復改善する手法。改善が頭打ちになるまで回す。プロンプトや skill を新規作成・大幅改訂した直後、またはエージェントの挙動が期待通りにならない原因を指示側の曖昧さに求めたいときに使う。
fix-github-actions-ci
GitHub Actions CI の失敗を調査して修正するためのスキルです。CI ログを分析して失敗箇所・原因を特定し、そのまま修正作業まで行います。
frontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
gh-sub-issue
GitHub CLI の extension を使って `gh sub-issue` コマンド経由で Sub Issue を操作する Skill. You can connect existing issues as sub-issues to a parent issue,create new issues directly linked to a parent, unlink sub-issues from their parent without deleting the issues, and view all sub-issues connected to a parent issue.
gh-timeline
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`.
git-workflow
>-
github-pr-review-operation
GitHub Pull Request上でのレビュー操作を行うスキル。ghコマンドでPR情報取得、差分確認、コメント投稿・取得、インラインコメント、コメント返信を実行する。PRにコメントを投稿したい、差分を行番号付きで確認したい、レビューコメントに返信したいときに使用。
grill-me
A relentless interview to sharpen a plan or design.
grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
japanese-tech-writing
日本語の技術文書・書籍原稿の文章規範。整形（一文一行、引用ブロック、脚注、コラム記法）、段落と論証の構成（パラグラフライティング）、論証の厳密さ（ツッコミどころの除去）、読み手の負荷の管理、視点と語り、演出の抑制、LLM っぽい空句の禁止、冗長の排除を定める。日本語で技術書の章、草稿、記事、解説文を書くとき、または推敲・リライトするときに使用する。
modern-web-guidance
|
mysql
Plan and review MySQL/InnoDB schema, indexing, query tuning, transactions, and operations. Use when creating or modifying MySQL tables, indexes, or queries; diagnosing slow/locking behavior; planning migrations; or troubleshooting replication and connection issues. Load when using a MySQL database.
neki
Overview and information about Neki, the sharded Postgres product by PlanetScale. Load when working with Neki-related tasks and the need to scale or shard postgres. Load when facing Postgres scaling or sharding issues.
omakase
cwd において、全ての意思決定を Claude と SubAgent に任せる Omakase Mode の ON / OFF を管理する Skill です.
plan-stacked-pr
大きな機能開発を stacked PR で進めるための計画を立案するスキル。Design doc やPlan から、各 PR の scope・What solves Why・Goal/Acceptance Criteria を定義した計画ドキュメント群を生成する。大きな機能を stacked PR で開発したい、feature 開発の PR 分割計画を立てたい、design doc から実装計画を作りたいときに使う。
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
prepare-issue-pr
Prepare repository-ready Issue or Pull Request drafts using local templates and git/GitHub context. Use this whenever the user wants to create or refine an Issue or PR, especially when they need title/body help, template-aware drafting, related document URLs, or stacked PR base branch guidance for chained branches.
refactor-module
Transform monolithic Terraform configurations into reusable, maintainable modules following HashiCorp's module design principles and community best practices.
reorganize-diff
大きなブランチや PR を、機能・振る舞い単位の PR と、その内側のコード変更種別ごとのコミットに2段階で再編成するスキル。「PR が大きすぎる」「PR を分けたら1コミットの大きなPRになった」「コミットが整理されていない」「PoC をレビュー可能な単位に崩したい」「diff の分割方法を相談したい」「plan-stacked-pr から分割粒度の決定を委譲されたとき」に使う。PR 粒度（機能/振る舞い）とコミット粒度（コード変更種別）を明示的に2層で管理する。
request-copilot-review
>
resolve-merge-conflict
現在の branch を分岐元の最新に rebase するときに使う。まず rebase を実行し、止まった conflict を順番に解消して前に進める。長い事前調査を避けて、必要な file だけ見て片付けたいときに使う。
retrospective
Retrospective grounded in the garbage-in-garbage-out principle: traces problems from Output back to their upstream origin across six stages, then fixes at the stage where the cause lives — knowledge deficiencies get knowledge fixes, not downstream rule patches. Implements fixes in the current session. Use after finishing a task, before creating a PR, or whenever the user says 'retrospective', 'wrap up learnings', or similar.
review-plan
Diagnostically review an implementation plan against the current codebase. Focuses on problem framing, expected behavior, and architecture decisions. This skill is read-only — it does not edit files or rewrite the plan.
semgrep
Run Semgrep static analysis scans and create custom detection rules. Use when asked to scan code with Semgrep, find security vulnerabilities, write custom YAML rules, or detect specific bug patterns. IMPORTANT: Also use this skill when users ask to 'scan for bugs', 'check code quality', 'find vulnerabilities', 'static analysis', 'lint for security', 'audit this code', or want to enforce coding standards — even if they don't mention Semgrep by name. Semgrep is the right tool for pattern-based code scanning across 30+ languages.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
smart-compact
セッションのコンテキストを分析し、重要な情報を保持するためのプロンプトを生成して /compact コマンドの実行を支援するスキル。コンテキストウィンドウが逼迫してきた時や、セッションを整理したい時に使用。
stacked-pr
依存関係のある複数の PR を管理・同期するためのスキル。stacked PR のカスケード rebase、PR 間の依存検出、base branch 管理、CI の上流優先修正を行う。PR が別の PR に依存している状況全般で使う — cascade rebase、スタック sync、依存先 PR 更新後のメンテ、PR チェーンの整合性確認などをするときなど。
terraform-search-import
Discover existing cloud resources using Terraform Search queries and bulk import them into Terraform management. Use when bringing unmanaged infrastructure under Terraform control, auditing cloud resources, or migrating to IaC.
terraform-stacks
Comprehensive guide for working with HashiCorp Terraform Stacks. Use when creating, modifying, or validating Terraform Stack configurations (.tfcomponent.hcl, .tfdeploy.hcl files), working with stack components and deployments from local modules, public registry, or private registry sources, managing multi-region or multi-environment infrastructure, or troubleshooting Terraform Stacks syntax and structure.
terraform-style-guide
Generate Terraform HCL code following HashiCorp's official style conventions and best practices. Use when writing, reviewing, or generating Terraform configurations.
terraform-test
Comprehensive guide for writing and running Terraform tests. Use when creating test files (.tftest.hcl), writing test scenarios with run blocks, validating infrastructure behavior with assertions, mocking providers and data sources, testing module outputs and resource configurations, or troubleshooting Terraform test syntax and execution.
triage-pr-reviews
>
vue-style-guide
Vue を書くときは基本的に参考にしてください。 個人的に気に入っている ubgeeei 氏の Vue.js のスタイルガイドです。
watch-ci
>-
writing-great-skills
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
typescript-performance
Comprehensive TypeScript performance analysis and optimization. Use when users report slow TypeScript compilation, slow editor experience, or want to investigate TypeScript performance issues. This skill provides diagnostic tools, trace analysis workflows, and optimization strategies. Key triggers include mentions of slow builds, type-checking delays, tsc performance, editor lag with TypeScript, or requests to analyze/improve TypeScript performance. Always prioritize data-driven analysis using --extendedDiagnostics, --generateTrace, and TS Server logs before making optimization recommendations.