80,000+ Skills to Supercharge Claude
The open directory for GitHub-integrated capabilities, tools, and prompts for your AI workflows.
signalwire-agents-sdk
by signalwire
Expert assistance for building SignalWire AI Agents in Python. Automatically activates when working with AgentBase, SWAI...
Generate initial project planning documents (PVS, ADR, Tech Spec, Roadmap) from a project concept description. Use when...
Prepare pull request descriptions following project template. Activates on: prepare PR, create PR, pull request, ready f...
writing-tests
by sergiodk5
Guides writing Vitest tests for Chrome extension code. Use when creating tests, improving coverage, or testing Vue compo...
creating-vue-components
by sergiodk5
Guides creating Vue 3 components with glass-morphism UI for the anime extension. Use when building UI components, stylin...
creating-pull-requests
by sergiodk5
Guides creating GitHub pull requests with proper branch naming, commit messages, and PR descriptions. Use when asked to...
using-anime-service
by sergiodk5
Guides using AnimeService for anime tracking operations. Use when implementing anime status checks, episode tracking, pl...
handling-review-comments
by sergiodk5
Handles GitHub pull request review comments. Use when asked to fix review comments, address PR feedback, or resolve revi...
project-context-sync
by jasonpaulso
Maintains synchronized project context for long-running work across sessions. Use when: starting a session (read context...
dependency-analyzer
by snhrm
ライブラリのEOL状況と互換性要件を確認する。endoflife.dateやnpmからバージョン互換性情報を取得する
package-updater
by snhrm
npm/yarn/pnpm/bunに対応したパッケージ更新を実行する。Node.jsバージョン管理ツール(mise/nvm/asdf)にも対応
library-release-checker
by snhrm
GitHubや公式ドキュメントからライブラリのリリース情報を取得し、破壊的変更・非推奨化・ビルトイン化を特定する
code-impact-checker
by snhrm
破壊的変更に基づいてプロジェクト内のコードを検索し、影響を受けるファイルと行を特定する。テストカバレッジも確認する
code-migrator
by snhrm
破壊的変更に対応したコード修正を行う。import文の変更、API呼び出しの修正、設定ファイルの更新を実行
reward-shaping-engineerin...
by tachyon-beep
Master reward function design - potential-based shaping, hacking patterns, validation
prioritizing-improvements
by tachyon-beep
Use when stakeholders pressure you to change technical priorities and you're tempted to compromise on security-first or...
exploration-strategies
by tachyon-beep
Master ε-greedy, UCB, curiosity-driven, RND, intrinsic motivation exploration
identifying-technical-deb...
by tachyon-beep
Use when cataloging technical debt under time pressure and tempted to explain choices instead of delivering document - e...
rl-debugging
by tachyon-beep
Systematic RL debugging - diagnose learning failures, common bugs, diagnosis trees
offline-rl
by tachyon-beep
Master CQL, IQL, BCQ - offline RL from fixed datasets without environment interaction
value-based-methods
by tachyon-beep
Master DQN, Double DQN, Dueling DQN, Rainbow - value-based methods for discrete actions
policy-gradient-methods
by tachyon-beep
Master REINFORCE, PPO, TRPO - direct policy optimization with trust regions
model-based-rl
by tachyon-beep
Master Dyna-Q, MBPO, Dreamer - model-based RL with world models and planning