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
synthetic-review-candidate
Candidate for smoke testing an evaluation runner only.
synthetic-review-baseline
Baseline for smoke testing an evaluation runner only.
llm-security
Authorized security assessment of LLM applications and AI agents: prompt injection, tool abuse, RAG exposure, memory poisoning, system-prompt extraction, and agent-compliance engineering per OWASP LLM/ASI Top 10.
review
Run the existing user-invoked review bundle and independently adjudicate its findings.
review-adjudication
Verify generated or human review findings before fixing, defending, replying, resolving, or reusing them as learned guidance. Use within a review, review-comment fix, monitor, or readiness workflow.
monitor-mr
Monitor review findings and CI using the shared adjudication procedure.
llm-inference-scaling
Auto-scale LLM inference clusters on Kubernetes using KEDA, custom GPU metrics, and horizontal pod autoscaling.
migrate-to-codex
Migrate supported instruction files, skills, agents, and MCP configuration into Codex project and global files. USE FOR: move existing agent definitions and MCP setup into Codex global configuration, migrate supported skills into Codex project files, convert supported Claude Code configuration to Codex. DO NOT USE FOR: PostgreSQL database migrations, moving a database schema to a new server, unrelated data migrations.
llm-gateway
Deploy an API gateway for LLM traffic with load balancing, rate limiting, key management, semantic caching, fallback routing, and cost tracking.
fix-mr-comment
Verify and fix unresolved review claims using the shared adjudication procedure.
llm-fine-tuning
Set up infrastructure for fine-tuning LLMs with QLoRA, LoRA, and full fine-tuning using Hugging Face TRL, Axolotl, and distributed training with DeepSpeed or FSDP.
create-mr
Create a draft merge or pull request with repository title policy and a concise description; ready creation requires an explicit human request.
web-design-guidelines
Review existing UI code for Web Interface Guidelines compliance. USE FOR: "audit UI accessibility", "sanity-check a site's UX and web interface practices", "check accessibility in UI files and report findings". DO NOT USE FOR: building or redesigning a new UI without a review request.
vercel-react-best-practices
Apply Vercel Engineering performance guidance when writing, reviewing, or refactoring React and Next.js code. USE FOR: "optimize Next.js data fetching and bundle size", "review a React component for performance problems", "read-only performance review of a Next.js page". DO NOT USE FOR: non-React software or general Python performance work.
llm-council
Run Fireworks-hosted open-weight model councils that compare responses and synthesize a final answer.
organization-best-practices
Guidance and enforcement rules for Better Auth's organization plugin. USE FOR: implement multi-tenant organizations teams and role-based access control with Better Auth, model team membership and roles inside each organization, advise on Better Auth organization-plugin team and role structure without changing code. DO NOT USE FOR: generic roles for an auth provider that does not use Better Auth's organization plugin, unrelated authentication providers.
llm-cost-optimization
Reduce LLM API and infrastructure costs through model selection, prompt caching, batching, caching, quantization, and self-hosting strategies.
nodejs-backend-patterns
Build production-ready Node.js backend services with Express or Fastify, including middleware, error handling, authentication, database integration, and API design. USE FOR: build a Fastify REST API, structure a Node GraphQL service for a microservices architecture, improve error handling in a Node REST API, create Node.js servers or backend services. DO NOT USE FOR: React component tests, frontend-only implementation or testing.