Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
gilfoyle
SRE agent that does what you can't. Queries your observability stack. Finds root causes. Doesn't panic. Doesn't guess. Doesn't care about your feelings. Use for incident response, debugging, root cause analysis, or log analysis.
axiomhq/gilfoyle 201
-
apple-container-skill
Interact with the Apple Container CLI to manage containers, images, volumes, networks, and system services on macOS. Use this skill when the user asks to run, build, or inspect containers or manage the container runtime.
gabeosx/agent-skills 1
-
devcontainer-helper
Use this skill when the user asks to create, configure, update, or explain a `devcontainer.json` file or development container environment.
gabeosx/agent-skills 1
-
github-scrum-flow
Unified expert for Project Management (Scrum/Agile) and GitHub Flow enforcement. Use this skill for track orchestration, backlog hygiene, GitHub Issue synchronization, branch management, and enforcing git best practices.
gabeosx/agent-skills 1
-
ux-designer
Expert UX/UI design assistant based on the "Refactoring UI" philosophy (by Wathan & Schoger). Enforces logic-based design, strict hierarchy, and "buildable" visual systems. Use for converting requirements into professional, high-fidelity specs.
gabeosx/agent-skills 1
-
Taro Documentation
This skill should be used when the user mentions "Taro" in any technical context, asks about "Taro API", "Taro components", "Taro configuration", "Taro development", "Taro project", "mini program with Taro", "WeChat mini program", uses Taro methods (like "Taro.request", "Taro.navigateTo"), or discusses multi-platform development with Taro framework. Provides comprehensive Taro framework documentation including APIs, components, configuration, and development guides.
whinc/my-claude-plugins 10
-
ahooks
Comprehensive ahooks React hooks library specialist. Expert in all 76+ ahooks hooks including state management, effects, data fetching, performance optimization, DOM utilities, and advanced patterns. Use when working with ahooks library, need React hooks utilities or want to learn best practices.
whinc/my-claude-plugins 10
-
Formily Ant Design Components
This skill should be used when the user asks to "use formily with ant design", "formily antd components", "formily ant design integration", "formily form layout", "formily form.item", "formily antd forms", or "integrate formily with ant design".
whinc/my-claude-plugins 10
-
Advanced Formily Patterns
This skill should be used when the user asks to "implement dynamic forms", "formily complex forms", "formily conditional fields", "formily nested forms", "formily async validation", "formily performance optimization", or "advanced formily patterns".
whinc/my-claude-plugins 10
-
Formily Core Fundamentals
This skill should be used when the user asks to "learn formily basics", "setup formily", "formily core concepts", "formily getting started", "formily fundamentals", "how to use formily", "formily installation", or "formily form state management".
whinc/my-claude-plugins 10
-
Formily Migration Guide
This skill should be used when the user asks to "convert to formily", "formily migration", "migrate forms to formily", "convert react forms to formily", "formily vs other form libraries", or "replace existing forms with formily".
whinc/my-claude-plugins 10
-
incident-handling
インシデント発生時に自律的に対応するメタスキルです。
初動対応から復旧、事後分析までを体系的に実行し、再発防止を強化します。
Trigger: インシデント, 障害, 緊急対応, トラブル, 本番エラー, デグレ, 互換性破壊, バグ
HikaruEgashira/agent-skills 1
-
risk-assessment
設計・計画段階で自律的にリスクアセスメントを行うメタスキルです。
行動する前に自問自答し、浅い解決策を避け、根本的な問題を特定します。
Trigger: 設計, 計画, 実装前, アーキテクチャ決定, リスク, 懸念
HikaruEgashira/agent-skills 1
-
gap-analysis
技術選定や競合分析を行う際に自律的にギャップ分析を行うメタスキルです。
複数の軸で類似概念を調査し、現行システムとのギャップを洗い出し、
なぜそのギャップが生じているのかを自問して戦略を立案します。
Trigger: 技術選定, 競合分析, 改善提案, ギャップ分析
HikaruEgashira/agent-skills 1
-
review-flow
PR作成後に自律的に実行する必要があるフロースキルです。
Trigger: review, pr created, pr open
HikaruEgashira/agent-skills 1
-
worktree
Planが承認/完了した直後に自律的に呼び出す必要があるスキルです。
Trigger: plan approved, plan completed, taskを開始します
HikaruEgashira/agent-skills 1
-
process-commit
PRを作成する前の分割commitが必要な時に自律的に呼び出す必要があるスキルです。
Trigger: need split commit, prepare commit, organize commit
HikaruEgashira/agent-skills 1
-
commit-push-pr-flow
タスク完了後に自律的に実行する必要があるフロースキルです。
Trigger: task completed, ready to submit code
HikaruEgashira/agent-skills 1
-
openai-knowledge
Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available; otherwise guide the user to enable `openaiDeveloperDocs`.
openai/openai-agents-js 2,570
-
final-release-review
Perform a release-readiness review by locating the previous release tag from remote tags and auditing the diff (e.g., v1.2.3...<commit>) for breaking changes, regressions, improvement opportunities, and risks before releasing openai-agents-js.
openai/openai-agents-js 2,570
-
examples-auto-run
Run examples:start-all in auto mode with parallel execution, per-script logs, and start/stop helpers.
openai/openai-agents-js 2,570
-
implementation-strategy
Decide how to implement runtime and API changes in openai-agents-js before editing code. Use when a task changes exported APIs, runtime behavior, schemas, tests, or docs and you need to choose the compatibility boundary, whether shims or migrations are warranted, and when unreleased interfaces can be rewritten directly.
openai/openai-agents-js 2,570
-
docs-sync
Analyze main branch implementation and configuration to find missing, incorrect, or outdated documentation in docs/. Use when asked to audit doc coverage, sync docs with code, or propose doc updates/structure changes. Only update English docs (docs/src/content/docs/**) and never touch translated docs under docs/src/content/docs/ja, ko, or zh. Provide a report and ask for approval before editing docs.
openai/openai-agents-js 2,570
-
pnpm-upgrade
Keep pnpm current: run pnpm self-update/corepack prepare, align packageManager in package.json, and bump pnpm/action-setup + pinned pnpm versions in .github/workflows to the latest release. Use this when refreshing the pnpm toolchain manually or in automation.
openai/openai-agents-js 2,570