Loading…
Showing 8761–8790 of 10191 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| stack-setgracefullight/pkgsAuto-detect project tech stack and generate stack-specific references for domain skills | Stars: 4 | Updated | Claude CodeCodex | Verified | Install |
| toolsgracefullight/pkgsManage MCP tools with natural language commands — list, enable, disable tools and tool groups | Stars: 4 | Updated | Claude CodeCodex | Verified | Install |
| edu-deckinsightflo/edu-deck-skillsEntry skill for education deck requests. Use FIRST when the user wants 교육자료, 강의 자료, 교육용 슬라이드, 직원 교육 덱, or a training series (예: "○○ 교육자료 만들어줘", "사내 교육 시리즈 만들어", "여러 편으로 나눠 교육 자료"). 판별 후 단일 발행(주제 하나, 파일 하나)이면 edu-deck-solo 경로를, 여러 편 시리즈·진도 관리·허브가 필요하면 edu-deck-series 경로를 탄다. 애매하면 사용자에게 한 번 묻는다. 덱 제작 절차는 이 스킬에 없고 각 하위 스킬에 있다. | Stars: 7 | Updated | Claude CodeCodex | Unverified | Install |
| apexMy5t3r10us/cesizenSystematic implementation using APEX methodology (Analyze-Plan-Execute-eXamine) with optional parallel subagents, self-validation, and adversarial review. Use when implementing features, fixing bugs, or making code changes that benefit from structured workflow. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| publish-websitesornkan/publish-websitePublish or host a static website from a zip with SORNKan MCP at publish.sornkan.com. Use when going live for $1 USDC on Base via x402, previewing a site for 60 minutes then claiming, or connecting Claude Code, Grok, OpenClaw, or Cursor. Also when find-skills or npx skills find is searching for website hosting, static hosting, paid MCP, or x402 publish. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| ai-native-organization-diagnosticycangel/GO-OSAssess organization-level AI-native maturity and transformation priorities. Use for whole-organization diagnosis, AI transformation planning, maturity assessments, operating-model reviews, executive workshops, before/after comparisons, or questions such as how AI-native an organization is. Also trigger when many copilots or agents coexist with unchanged approvals, weak feedback loops, fragmented memory, unclear authority, repeated coordination bottlenecks, or uncertainty about the next transformation step. Do not trigger for evaluating a single AI tool unless organization-level implications are requested. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| ai-native-talent-human-valueycangel/GO-OSRedesign human roles, talent standards, leadership and performance for organizations where AI agents perform substantial cognition and execution. Use for future-of-work questions, role redesign, hiring criteria, performance systems, management evolution, human value, mission ownership, or how people should work with increasingly capable agents. Also trigger when a role mostly routes information, supervises routine work, measures busyness or team size, or when the user asks what remains uniquely human as machine capability rises. Do not trigger for ordinary resume, compensation or HR-administration questions without an AI-native role/organization dimension. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| go-society-cognitive-bridgeycangel/GO-OSConnect a ChatGPT or Codex conversation to GO Society's private cognitive space: load compact ratified organizational context, and only after explicit member selection and internal-only consent, stage bounded candidate material for GO Society human review. Use when the user wants a conversation to read from, contribute to, synchronize with, or continue GO Society cognition. Never use it to ratify, approve, commit, version, or directly mutate organizational cognition. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| mission-organizational-runtimeycangel/GO-OSCompile intent, goals or strategy into durable, autonomous and evidence-verifiable Missions. Use when goals are vague, work is expressed as task lists or OKRs without executable state transitions, agents lose context on long-horizon work, projects stall on coordination, actors repeatedly seek permission, or the user wants to turn intent into autonomous organizational execution. Also trigger when success criteria, authority, exception conditions or durable state are missing. Do not trigger for a simple one-off task that has clear instructions, low consequence and no need for organizational runtime semantics. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| git-guardrails-claude-codemhrsdev/AI-Agent-Skills-LibrarySet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| git-guardrails-claude-codemhrsdev/AI-Agent-Skills-LibrarySet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| domain-modelingmhrsdev/AI-Agent-Skills-LibraryBuild and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| domain-modelingmhrsdev/AI-Agent-Skills-LibraryBuild and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| qwen-native-agentsvakovalskii/qwen-native-agentsBuild and prompt agents for Qwen3.x-family models the way Alibaba does it — aligned with the conventions baked into qwen-code and Qwen-Agent. Use when writing a system prompt for a Qwen agent, defining tools, choosing a function-calling format, configuring the thinking mode, or debugging why a Qwen model ignores your instructions. Qwen "sticks to" its trained-in habits; speak its native dialect instead of fighting it. | Stars: 42 | Updated | Claude CodeCodex | Verified | Install |
| huashu-weread-advisoralchaincyf/huashu-weread微信读书高阶顾问。在底层 weread skill 的原子 API 之上,提供四类工作流:基于已读做个性化进阶推荐(advisor)、给方向规划入门到前沿的阶梯书单(path)、把零散划线想法提炼成读书笔记总结(alchemy)、做季度/年度阅读复盘并生成可发朋友圈/公众号的文章(review)。核心方法是「书架 + 笔记交叉分析」——书架揭示用户主动分类的兴趣,笔记数据揭示「真读过的」vs「只放着的」。当用户说「推荐书」「下一本读啥」「该读什么」「想搞懂 X 这个领域」「整理我的笔记」「这本书我记住了啥」「我今年读了什么」「读书复盘」「年度盘点」时触发。即使用户只是说「不知道读啥」「有没有相关的书」「帮我看看这本读完了吗」「这个领域我入门了吗」也应触发。 | Stars: 161 | Updated | Claude CodeCodex | Verified | Install |
| marketing-ideashamzabellouch/agent-skillsWhen the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing strategies,' 'marketing tactics,' 'ways to promote,' 'ideas to grow,' 'what else can I try,' 'I don't know how to market this,' 'brainstorm marketing,' or 'what marketing should I do.' Use this as a starting point whenever someone is stuck or looking for inspiration on how to grow. For specific channel execution, see the relevant skill (ads, social, emails, etc.). | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| auto-updaterEniggman/termux-labУниверсальная безопасная проверка и обновление приложений и пакетов в Termux по стандартам termux-fix-path. Claude Code намеренно исключён. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| internal-commsVidyFoo/antigravity-skill-engineA set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. The Agent should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.). | Stars: 13 | Updated | Claude CodeCodex | Verified | Install |
| delegation-harnesshassan-mohiddin/freeflowUse when coordinating Freeflow Pi/cmux pane delegation, orchestrator/planning-parent/execution-parent workflows, task packets, child results, context locality, capability reroutes, multi-agent execution, work packages, worktrees, routing fresh-reviewer/subagent requests, or when the user asks to spawn/manage visible pane agents. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| reviewaboylabs/ai-agent-skillsReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X". | Stars: 15 | Updated | Claude CodeCodex | Verified | Install |
| agent-ops-branch-workflowdiegosouzapw/awesome-omni-skillStandardized branch creation with type detection, issue ID extraction, and worktree setup. Creates working branches (-WB) and integrates with selective-copy for clean PRs. | Stars: 67 | Updated | Claude CodeCodex | Verified | Install |
| agent-ops-code-review-interactivediegosouzapw/awesome-omni-skillInteractive code review for agent iterations. Captures comments, tracks resolution status, and integrates with git diffs. | Stars: 67 | Updated | Claude CodeCodex | Verified | Install |
| agent-ops-create-skilldiegosouzapw/awesome-omni-skillCreate new AgentOps skills via interactive interview. Supports from-scratch and clone modes with tiered complexity. | Stars: 67 | Updated | Claude CodeCodex | Verified | Install |
| agent-ops-retrospectivediegosouzapw/awesome-omni-skillScan the current chat session for durable learnings (clarifications, corrections, decisions, pitfalls) and update .agent/memory.md. Use after critical review and before concluding work. | Stars: 67 | Updated | Claude CodeCodex | Verified | Install |
| agent-ops-selective-copydiegosouzapw/awesome-omni-skillCreate clean git branches from feature work, excluding agent-ops files. Use for PR preparation. | Stars: 67 | Updated | Claude CodeCodex | Verified | Install |
| agent-ops-validationdiegosouzapw/awesome-omni-skillPre-commit and pre-merge validation checks. Use before committing changes or declaring work complete to ensure all quality gates pass. | Stars: 67 | Updated | Claude CodeCodex | Verified | Install |
| 10-andruia-skill-smithpinkpixel-dev/skills-collection-1Ingeniero de Sistemas de Andru.ia. Diseña, redacta y despliega nuevas habilidades (skills) dentro del repositorio siguiendo el Estándar de Diamante. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| agent-memory-systemspinkpixel-dev/skills-collection-1You are a cognitive architect who understands that memory makes agents intelligent. You've built memory systems for agents handling millions of interactions. You know that the hard part isn't storing - it's retrieving the right memory at the right time. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| agentfoliopinkpixel-dev/skills-collection-1Skill for discovering and researching autonomous AI agents, tools, and ecosystems using the AgentFolio directory. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| ai-engineerpinkpixel-dev/skills-collection-1Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |