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
tailwind
Tailwind CSS v4 — utility-first styling, responsive design, dark mode, and component extraction. Use when building or reviewing Tailwind-based UIs, setting up Tailwind v4, or designing responsive or dark-mode styling.
app-workshop-session-pdf-recap-next
Extract content from a workshop session PDF and produce a structured recap focused on (1) what was learned, (2) next steps, and (3) possible enhancements. Ingests a single PDF file path, parses session material (slides, transcripts, exercises, Q&A), and emits a Markdown report with Learning Recap, Next Steps, and Enhancement Opportunities sections with page-level traceability. Use when the user asks to "summarize a workshop", "recap a training PDF", "pull next steps from a session deck", or provides a workshop/seminar/tutorial PDF and wants a learn-and-act summary.
system-design
System design methodology — requirements, capacity estimation, component design, trade-offs. Use when designing a new distributed system, evaluating an existing architecture for scalability or cost, performing back-of-envelope capacity estimation, or preparing for a system design review.
app-workshop-recaps-consolidate
Consolidate multiple workshop-session recap Markdown files (typically produced by the workshop-session-pdf-recap-next skill) into a single unified report. Merges and deduplicates learnings across sessions and emits six sections — Consolidated Recap, Follow-ups, Action Items, Next Steps, Possible Enhancements, and Industry / External Viewpoint. The last section supplements the attendees' material with current external perspective via web research. Use when the user has a set of per-session recap files and wants one portfolio-level summary with an outside-in lens ("consolidate these recaps", "merge my workshop notes", "cross-session summary", "roll up action items").
sql-style-guide
SQL style — snake_case, singular tables, named constraints, one-clause-per-line formatting. Use when writing or reviewing SQL, designing schemas, or naming tables, columns, constraints, and migrations.
app-risk-analysis-agent
Conduct a formal risk analysis on a target codebase location against a user-specified goal. Ingests a <location>/* path as the Current State, parses the <prompt> as the Target State, identifies vulnerabilities and transition risks, evaluates each on a Likelihood × Impact matrix, and emits a prioritized report classified into P0 (Critical Risk), P1 (High-Value Risk), and P2 (Low-Risk). Use when the user asks to "risk analyze", "assess risks", "evaluate vulnerabilities", "threat model the delta", or requests a Likelihood/Impact matrix evaluation of a folder or repo against stated target requirements.
sql-patterns
SQL query patterns, schema design, and optimization — joins, CTEs, window functions, indexing, and anti-patterns. Use when writing or optimizing SQL queries, designing or reviewing a relational schema, reading EXPLAIN plans, choosing indexes, or implementing pagination, deduplication, or analytical queries.
app-plan-feature-stories
Decompose a piece of work into a 3-tier Feature > Story > Task plan tree, written to disk as self-contained markdown files. Use when the user asks to plan a feature, break down work, write an implementation plan, or create a task tree for a larger effort.
software-modularization
Design and evaluate module and package boundaries for maintainability, low coupling, and AI agent context efficiency.
app-gap-analysis-agent
Perform a systematic gap analysis on a target codebase location against a user-specified goal. Ingests a <location>/* path, maps the Current State, parses the <prompt> into a Target State, extracts the delta, and emits a prioritized action plan classified into P0 (critical blockers), P1 (high-value features), and P2 (low-risk utility) with cross-reference traceability. Use when the user asks to "gap analyze", "audit", "compare current vs target", "prioritize gaps", or requests a P0/P1/P2 triage of a folder or repo against stated requirements.
software-architecture
Codebase architecture analysis — patterns, ADRs, structural review, C4 diagrams. Use when evaluating a codebase's architecture, choosing a pattern for a new project, writing an Architecture Decision Record, reviewing for layer violations, or generating C4 diagrams.
app-extraction-and-static-analysis
Run a read-only static-analysis-and-extraction pass on one or more information sources (code packages, document repositories, datasets, API specifications) and emit an 8-file structured reference package — README, sources, surface, capabilities, flow, dependencies, parity, references — with absolute path/URI traceability for every claim. With N=1 sources it acts as a solo public-surface survey; with N≥2 it adds a parity matrix that flags naming drift, shape/semantic drift, and one-sided entities. Use when the user asks to "extract", "statically analyze", "survey the public surface", "compare two libraries/specs", "document an unknown codebase", or wants a structured reference doc as input to downstream planning, migration, or audit work.
shell-scripting
Bash scripting — strict mode, quoting, arg parsing, traps, shellcheck compliance. Use when writing or reviewing bash scripts, adding error handling and argument parsing, or fixing shellcheck warnings.
secure-coding
Secure coding practices grounded in the OWASP Top 10. Use when reviewing code for security issues, implementing input validation, hardening web applications, or adding defenses against injection, XSS, or CSRF.
agentteams
Orchestrate plan execution — analyze a plan tree, score it against expectations, resolve a dependency DAG, slice work into token-budgeted groups, and drive a human-in-the-loop iteration loop with canonical handoff blocks. Use to orchestrate agent teams, run plan analysis, render scoreboards, build punch lists (P0/P1/P2), slice plans by token budget, drive iteration loops, render handoff blocks (Landed / Tested / Acceptance / Next / To Resume), and resume after /clear.
agentteams-assets
Static assets for the AgentTeams orchestrator — bundled fixture plans (minimal, multi-feature), CLI/SDK/API example scenarios, and golden files used by the parity harness and acceptance gate. Read-only from the perspective of the org-agentteams skill; consumers reference these via relative paths from packages, scripts, and tests.
secret-management
Handle secrets safely — env vars, .env files, vaults, rotation. Use when dealing with API keys, passwords, tokens, database credentials, or any other sensitive value the application needs at runtime.
agent-skill-kit-validator
Validate one or many SKILL.md files against the agentskills.io specification — frontmatter, naming, body, optional-directory, and reference checks. Use when the user asks to validate a skill, audit skills, check SKILL.md, or run skills-ref against an existing skill or directory tree.