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
challenge-sciml-model
Challenge SciML evidence for leakage, physical constraints, extrapolation, uncertainty, baselines, and cost.
career-documents
Write and edit professional career documents: CVs, cover letters, research statements, fellowship proposals, and resignation letters. Audience-aware framing, credential accuracy, and submission limit tracking. Part of Career Writer plugin. Use for cover letters, CVs, applications, or career document editing.
capture-scientific-run
Capture a replayable scientific run with units, provenance, numerical equivalence, and uncertainty contracts.
build-crypto-inventory
Build a hash-backed cryptographic bill of materials from authorized repository evidence without collecting secrets or raw key material.
build-attack-scenario
Build a portable, hash-pinned agent attack scenario with explicit trusted goals, untrusted channels, prohibited effects, and benign criteria.
audit-scientific-claim
Audit claims against hashed evidence while separating verification, validation, and uncertainty quantification.
audit-cognitive-debt
Audits cognitive load across seven debt categories: dead code, over-engineering, duplication, abstraction quality, control flow, naming, and test debt. Writes COGNITIVE_DEBT.md. Complements review-quality. Part of Codecraft plugin. Use when asked to audit cognitive load, find dead code, or analyze complexity.
assess-repository-trust
Inventory repository control-plane inputs and produce a private, hash-based trust record before an agent executes repository-supplied automation.
analyze-codebase
Analyzes a codebase across 16 dimensions — naming, formatting, architecture, async patterns, error handling, testing, anti-patterns — and writes CODING_REQUIREMENTS.md as prescriptive rules for future agent sessions. Pipeline: analyze → write-conformant-code → review-quality → audit-cognitive-debt. Use when asked to analyze conventions, document coding standards, capture code style, or extract project patterns.
agent-ste
Use when rewriting user or planner instructions before planning or execution; when prompts contain vague verbs (optimize, improve, better, appropriate, reasonable, quickly, carefully, as needed, if necessary); when multiple agents or LLMs must interpret the same task reproducibly; when an instruction lacks explicit actor, inputs, outputs, success criteria, failure conditions, ordering, or scope; or when preparing handoffs between orchestrators and workers.
sample-landing-skill
Example skill for landing zone documentation. Copy to landing/skills/ and assign in registry.yaml before running skills-maintain. Not ingested from examples/.
check-entropy-runtime
Check the optional pinned JSON Schema runtime required by entropy evidence helpers and hooks without installing software.
check-crypto-runtime
Check the optional pinned JSON Schema runtime required by crypto evidence helpers and hooks without installing software.
install-plugin-agents
Safely preview and install this plugin's bundled Codex agent templates.
identify-root-cause
Identify the root cause of the issue through detailed code examination-based skill consuming code_analysis, issue_description to produce root_cause
generate-code-fix
Generate minimal code changes that resolve the identified issue-based skill consuming root_cause, issue_description to produce code_patch
analyze-code-repository
Systematically analyze repository structure to locate code relevant to the issue-based skill consuming repository, issue_description to produce code_analysis
generate-code-patch
minimal code changes to resolve identified issue-based skill consuming bug_analysis, code_context to produce unified_diff_patch