GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
river-review-frontend
フロントエンド観点のレビューエージェント。 アクセシビリティ、デザインシステム準拠、Tailwind クラス衛生、UI 状態設計、 Next.js / React Router のフレームワーク境界を個別スキルへルーティングする。
river-review-docs
ドキュメント観点のレビューエージェント。 README / docs / AGENTS.md と実装の整合性、API ドキュメントとコードの対応、 usage や例の正確性、i18n(JA/EN)整合性、用語統一を検証する。
river-review-code
一般コード品質のレビューエージェント。デフォルトのフォールバック先。 可読性、保守性、型安全性、ロギング等の個別スキルへルーティングする。
river-review-architecture
設計・アーキテクチャ観点のレビューエージェント。 依存関係、境界設計、データモデル、API設計等の個別スキルへルーティングする。
review-team
6つの専門レビュアーロールを並列実行し、consensusLevel(複数ロールの合意度)と Tech Lead レポート(top3指摘・blindSpots・consensusSummary)で結果を統合する マルチエージェントレビュー entry skill。 Parallel multi-role review with consensus scoring (consensusLevel) and Tech Lead report. Use when a major release needs exhaustive multi-angle review, or when a single-perspective review is not enough and you want confidence that no reviewer angle was missed(重要リリース前の網羅レビュー・多視点の確証が 欲しいとき)。
adversarial-review
敵対的分析手法を統合したレビューの entry skill。認知バイアス対策の3手法 (Pre-mortem / War Game / Logic Torturing)と、宣言・主張と実態の乖離を突く claim-vs-actual 検出3パターン(Self-Contradiction / Refactor-Claim Audit / Cross-File Leakage)へルーティングし、通常のレビューでは見えない設計の盲点・ 防御の穴・論理の弱点・宣言と実装のズレを可視化する。
send-mail
Print and mail a real postcard or letter to a US address with Sendpaper, including USPS Certified Mail with tracking and a return receipt. Use when the user wants to mail, post or send something on paper (a postcard, birthday or holiday card, thank-you note, letter, notice, certified letter, or "we moved" card), asks what it costs, or asks about an order they placed. Not for email, texts, packages or non-US addresses.
tool-design
Design or audit the tools an AI agent calls (MCP server tools, function calling, Runtype runtime and saved tools), or find out why an agent picks the wrong tool or misuses one. Routes naming, schema, output, error, execution, and security work to focused guides.
tool-design-security
Design or audit a tool's trust boundary: keep API keys and tenant ids out of model-visible parameters, resist prompt injection, enforce permissions and approval gates in code, declare scopes, and log calls safely.
tool-design-output
Design or audit what an agent tool returns: shape and trim payloads, paginate, report partial success, reference files and media, and add next-step hints. Use when tool output bloats the context window.
tool-design-interface
Design agent-facing tool names, descriptions, and parameter schemas; diagnose incorrect tool selection or inputs.
tool-design-execution
Design how an agent tool runs: sync or async job, idempotency, timeouts, transactions, and compensation. Use when a tool is slow, has side effects that a retry could duplicate, or spans several systems.
tool-design-errors
Design actionable agent tool errors, ambiguity handling, retry guidance, and fallback behavior, or debug an agent that loops on or misreads a failing tool.
tool-design-composition
Compose and expose agent toolsets: task-level operations, batching, discovery, dry runs, and versioning.
runtype
Scope a Runtype project or set up platform access; route implementation to the relevant Runtype skill.
runtype-templates
Create, validate, or share distributable Runtype Full Product Object (FPO) templates with import-time variables and pending secrets, or install a product from a runtype.com example, a use.runtype.com/now link, or a template URL.
runtype-sdk-marathon
Build source-controlled Runtype workflows with the SDK or CLI: config-as-code deploys from CI (ensure), save-and-run flows (upsert), long-running or multi-session agent runs with Marathon (runtype marathon or runtype agents task), and Marathon playbooks.
runtype-persona
Embed, theme, or debug a Runtype Persona chat widget on a website: client tokens, embed snippets, fullscreen assistant layouts, WebMCP page tools, and browser-side chat integrations.