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
ln-630-test-auditor
Test suite audit coordinator: automated + manual tests. Delegates to 6 workers (Business Logic, E2E, Value, Coverage, Isolation, Manual Quality). Output: docs/project/test_audit.md.
ln-629-lifecycle-auditor
Checks bootstrap initialization order, graceful shutdown, resource cleanup, signal handling, liveness/readiness probes. Returns findings.
ln-628-concurrency-auditor
Checks async races, thread safety, TOCTOU, deadlocks, blocking I/O, resource contention, cross-process races. Two-layer detection: grep + agent reasoning.
ln-627-observability-auditor
Checks structured logging, health check endpoints, metrics collection, request tracing, log levels. Returns findings with severity, location, effort, recommendations.
ln-626-dead-code-auditor
Checks unreachable code, unused imports/variables/functions, commented-out code, backward compatibility shims, deprecated patterns. Returns findings.
ln-625-dependencies-auditor
Checks outdated packages, unused deps, reinvented wheels, vulnerability scan (CVE/CVSS). Supports mode: full | vulnerabilities_only.
ln-624-code-quality-auditor
Checks cyclomatic complexity, nesting, long methods, god classes, method signatures, O(n²), N+1 queries, constants management. Returns findings.
ln-623-code-principles-auditor
Checks DRY (10 types), KISS/YAGNI, error handling, DI patterns. Returns findings with severity, location, effort, pattern_signature.
ln-622-build-auditor
Checks compiler/linter errors, deprecation warnings, type errors, failed tests, build config issues. Returns findings with severity, location, effort, recommendations.
ln-621-security-auditor
Checks hardcoded secrets, SQL injection, XSS, insecure dependencies, missing input validation. Returns findings with severity, location, effort, recommendations.
ln-620-codebase-auditor
Coordinates 9 audit workers (ln-621..ln-629) in parallel. Research best practices, delegate, aggregate into docs/project/codebase_audit.md.
ln-614-docs-fact-checker
Extracts verifiable claims from ALL .md files (paths, versions, counts, configs, names, endpoints), verifies each against codebase, cross-checks between documents for contradictions.
ln-613-code-comments-auditor
Checks WHY-not-WHAT, density (15-20%), forbidden content, docstrings quality, actuality, legacy cleanup. Returns findings with severity, location, and recommendations.
ln-612-semantic-content-auditor
Audits document semantic content against stated SCOPE and project goals. Checks coverage, off-topic content, SSOT. File-based report with scope_alignment score.
ln-611-docs-structure-auditor
Checks hierarchy & links, SSOT, proactive compression, requirements compliance, freshness indicators, legacy cleanup, stack adaptation. Returns findings with severity, location, and recommendations.
ln-610-docs-auditor
Coordinates 4 documentation audit workers (structure, semantic, fact-check, code comments). Delegates parallel audits, aggregates into docs/project/docs_audit.md.
ln-523-auto-test-planner
Plans automated tests (E2E/Integration/Unit) using Risk-Based Testing after manual testing. Calculates priorities, delegates to ln-301-task-creator.
ln-522-manual-tester
Performs manual testing of Story AC via executable bash scripts saved to tests/manual/. Creates reusable test suites per Story.