90 skills found · Page 2 of 3
AI-agents-incubator / uiLaunch Web UI for dialog management
zsxink / cr自动代码审查（CR）——只读 subagent 对照规格审查变更，产出问题清单；作为独立审查环节或 /pipe 流水线的一部分
redhat-ai-americas / dsBreak down complex tasks into sub-problems, solve them efficiently, then aggregate results
xmtplabs / qaRun the Convos iOS QA suite (structured tests in qa/tests/structured/*.yaml). Results are persisted to CXDB so runs resume across context resets.
bredmond1019 / fixClaude Code SDK for Rust
robisson / wbProduction-grade engineering skills for AI coding agents, built on Amazon Way of building services
bountonw / scSC Thai rounds — pre-process a raw chapter, run QA1 or QA2 on one or more chapters, check a resolved chapter, or mine terms for the glossary
aspiers / scStage relevant changes and then commit them
aspiers / rrFind and address all unresolved GitHub PR review comments
aspiers / pcBreak down uncommitted changes and propose a set of commits
aspiers / sqSummarise where this session stands and what happens next
navox-labs / qaSenior QA Engineer that creates test plans and executes comprehensive testing including auth flows and edge cases. Trigger on testing, QA, test plan, regression, bug report, or auth flow testing.
feizhen / pm生成产品规格文档 (使用 --file 指定 idea 文件，可用 @ 引用参考文档)
hiromaily / recreate-prCryptocurrency wallet for trading for Bitcoin, Bitcoin cash, Ethereum, ERC20, XRP Leger (Ripple)
ThomDietrich / commitCommit all pending changes in this repository, grouping them into well-structured, logical commits. 1. Run `git status` and `git diff` (staged + unstaged) to understand all pending changes. 2.
kcwoodfield / professorInvoke Professor - Literary Critic and Reading Mentor for deep reading
bitflight-devops / spikeThe best platform agnostic Linter for AI agent plugins and skills — validates structure, frontmatter, and token limits for Claude Code, Cursor, Codex, and many others!
Flux-Frontiers / setup-kgrag-mcpKGRAG - KnowledgeGraph RAG
vscarpenter / qcheckSkeptical staff-engineer code review of every changed file in this session, against coding-standards.md and CLAUDE.md.
danmindru / awEnsure what you implement Always Works™ with comprehensive testing
JNU-econovation / new-prEEOS(Econovation Event Operation System) 프로젝트의 백엔드 레포지토리입니다.
muggelpotato / wake-reviewReview uncommitted working-tree changes against Wake's standards (CLAUDE.md) before committing
rawphp / releaseProduction release — quality gates, package.json version, v* tag, GitHub Release via Actions.
reichaves / gerar-dossieGera o dossiê PDF final a partir de um arquivo findings-consolidated.json. Usa a sub-skill generate-dossier-pdf com template ReportLab. Requer revisão humana dos achados antes de executar.
SardarHussain65 / qaVerify the current work against the hard rules, the design, and the browsers it will meet
johnfinleyproductions-lang / awEnsure what you implement Always Works™ with comprehensive testing
AryanXPatel / awEnsure what you implement Always Works™ with comprehensive testing
GentlemanDan / awEnsure what you implement Always Works™ with comprehensive testing
qyndex / harness-doctorDiagnose the harness itself. Reports version drift vs upstream, plugin staleness, MCP version pins, hook log size, memory growth, settings.json size. Run monthly or when behavior feels off.
Saidiibrahim / prime⚽🏃➡️ A WatchOS and iOS combo app for football/soccer referees
