#SkillRepo stars
- 1345Performance Oracleratacat/claude-skillsUse this agent when you need to analyze code for performance issues, optimize algorithms, identify bottlenecks, or ensure scalability. This includes reviewing database queries, memory usage, caching strategies, and overall system performance. The agent should be invoked after implementing features or when performance concerns arise.\ \ <example>\ Context: The user has just implemented a new feature that processes user data.\ user: "I've implemented the user analytics feature. Can you check if it will scale?"\ assistant: "I'll use the performance-oracle agent to analyze the scalability and perf59
- 1346Plan Reviewratacat/claude-skillsHave multiple specialized agents review a plan in parallel59
- 1347Spec Flow Analyzerratacat/claude-skillsUse this agent when you have a specification, plan, feature description, or technical document that needs user flow analysis and gap identification. This agent should be used proactively when:\ \ <example>\ Context: The user has just finished drafting a specification for OAuth implementation.\ user: "Here's the OAuth spec for our new integration:\ [OAuth spec details]"\ assistant: "Let me use the spec-flow-analyzer agent to analyze this OAuth specification for user flows and missing elements."\ <commentary>\ Since the user has provided a specification document, use the Task tool to launch the 59
- 1348Claudability Analyzeraviz85/claude-skills-libraryAnalyzes professions/jobs for Claude Code automation opportunities. Triggers: 'how can Claude help me', 'what can Claude do for', 'I'm a [profession]', 'help me as a [job]', 'I work as', describing their work + asking about Claude. Use whenever user mentions their profession/role and wants to discover what Claude can automate.51
- 1349Find My Projectaviz85/claude-skills-libraryHelps beginners find their first AGENTIC project through pain point identification. Guides through questioning, analysis, project suggestion, and folder setup. Use when someone asks 'what project should I build?' or 'help me get started with Claude Code'.51
- 1350Review Skillaviz85/claude-skills-libraryReview new skills for claude-skills-library standards. Use when adding new skills to verify they meet quality and structure requirements.51
- 1351Search Historyaviz85/claude-skills-librarySearch across all Claude Code conversation history (JSONL files) across all projects.51
- 1352Senior Ml EngineerArogyaReddy/alirezarezvani-claude-skillsML engineering skill for productionizing models, building MLOps pipelines, and integrating LLMs. Covers model deployment, feature stores, drift monitoring, RAG systems, and cost optimization. Use when the user asks about deploying ML models to production, setting up MLOps infrastructure (MLflow, Kubeflow, Kubernetes, Docker), monitoring model performance or drift, building RAG pipelines, or integrating LLM APIs with retry logic and cost controls. Focused on production and operational concerns rather than model research or initial training.40
- 1353Senior Prompt EngineerArogyaReddy/alirezarezvani-claude-skillsThis skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RAG", "create few-shot examples", "analyze token usage", or "design AI workflows". Use for prompt engineering patterns, LLM evaluation frameworks, agent architectures, and structured output design.40
- 1354Ten By Tenaviz85/claude-skills-libraryThe 10x10 method — generate breadth, then converge with human judgment. Use whenever a single AI output won't nail it and quality matters (design, copy, naming, posters, messaging, strategy options, code approaches), OR when the user says '10x10', 'ten by ten', 'give me 10 options', 'show me variations', or asks to refine/tighten an output instead of round-after-round corrections.51
- 1355Agent Factorydaydreamsai/skills-marketMeta-skill that orchestrates the full agent creation pipeline. Composes: trend-discovery → api-research → lucid-agents-sdk → railway-deploy. Use when creating new monetized agents from scratch.31
- 1356B2a Agentsdaydreamsai/skills-marketBuilds agents that serve other AI agents (B2A). Use when designing x402 agents for agent-to-agent data sales, evaluating if a data niche is suitable for agents, or when asked to "build something agents would pay for".31
- 1357Lucid Agent Creatordaydreamsai/skills-marketCreates Lucid agents with JavaScript handler code. Covers three options: MCP tool with SIWE, SDK with wallet auth, or viem with custom signing. Includes handler code contract, paymentsConfig, and identityConfig. Use when creating Lucid platform-hosted agents with inline JS handlers (no generate API, no self-hosting).31
- 1358Lucid Agent Editordaydreamsai/skills-marketEdits and manages existing Lucid agents via the API. Covers three options: MCP tool with SIWE, SDK with wallet auth, or viem with custom signing. Use when editing, updating, disabling, or otherwise managing existing Lucid agents.31
- 1359Lucid Agents SDKdaydreamsai/skills-marketProvides Lucid Agents SDK implementation patterns for TypeScript paid agents, including entrypoints, payments, identity, and A2A communication. Use when building or modifying Lucid Agents projects, working in the lucid-agents monorepo, creating templates or CLI features, or answering SDK architecture/API questions.31
- 1360Paid Agentdaydreamsai/skills-marketBuilds and deploys a production-ready paid Lucid Agent from user requirements. Scaffolds with CLI, implements entrypoints, reviews code, tests, publishes to GitHub, and deploys to Railway. Use when: "create a paid agent for X", "build and deploy an agent", "make a monetized agent". Not for: automated topic discovery (agent-factory) or platform-hosted JS handlers (lucid-agent-creator).31
- 1361Layout Skillssanghun0724/cmux-claude-skillsClaude 스킬/플러그인 개발 레이아웃을 설정합니다. Claude(좌 70%) + 파일 탐색(우 30%).33
- 1362Layout Websanghun0724/cmux-claude-skills웹뷰/프론트엔드 개발 레이아웃을 설정합니다. Claude(좌 70%) + dev 서버 로그(우 30%, 자동 시작).33
- 1363Restoresanghun0724/cmux-claude-skillscmux-snapshot으로 저장한 스냅샷을 복원합니다. 워크스페이스 레이아웃과 Claude 세션을 재구성합니다.33
- 1364Snapshotsanghun0724/cmux-claude-skills현재 cmux 레이아웃과 Claude 세션 ID를 JSON 스냅샷으로 저장합니다. cmux 재시작 시 복원에 사용됩니다.33
- 1365Trellis Review Twostagecoldwateryi/trellis-skillsBefore marking a Trellis subtask complete after self-check all green, conduct two-stage code review: mechanically check spec compliance (against PRD acceptance criteria/decision table/forbidden/file manifest/mount points), then code quality review (against .trellis/spec/guides engineering standards and design discipline). Used in Codex / Claude Code team collaboration scenarios, especially when implementation is by a small-parameter model like qwen3.6 35b—small models reviewing their own code is unreliable, Stage 2 should escalate to strong model; critical issues block completion.44
- 1366Agent Output Verifierrohitg00/agentbrainUse when agent-produced work needs a safety, evidence, and reliability check before handoff, merge, or trust.43
- 1367Brain Evalrohitg00/agentbrainAgent Brain /brain-eval: changing Agent Brain behavior or checking quality.43
- 1368Brain Grillrohitg00/agentbrainAgent Brain /brain-grill: the idea, brief, design, or plan has unresolved assumptions.43
- 1369Brain Planrohitg00/agentbrainAgent Brain /brain-plan: the brief/design is strong enough to implement.43
- 1370Brain Reviewrohitg00/agentbrainAgent Brain /brain-review: after verification or before public/shipping decisions.43
- 1371Brain Shiprohitg00/agentbrainAgent Brain /brain-ship: a reviewed artifact is ready for release or publication.43
- 1372Brain Verifyrohitg00/agentbrainAgent Brain /brain-verify: after build or when evaluating an existing artifact.43
- 1373Brain Wikirohitg00/agentbrainAgent Brain /brain-wiki: ingesting sources or updating durable project knowledge.43
- 1374Godot MCP Auto Launcherhhhh124hhhh/godot-mcp使用此技能自动启动Godot MCP服务器,确保在Godot项目启动时MCP工具可用。当需要确保MCP连接就绪或在项目启动时自动初始化MCP工具时触发。44
- 1375Init Projectjiahao-shao1/sjh-skills初始化新项目的 Claude Code 配置。用户说"初始化项目"、"init project"、"配置 Claude Code"时触发。44
- 1376Remote Cluster Agentjiahao-shao1/sjh-skillsRemote GPU cluster ops via `rca` CLI — run commands, transfer files, GPU/node inspection, mutagen sync. Trigger for any remote execution, training, GPU, cluster status, sync, or tail-log task even when 'cluster' isn't said. Triggers: cluster, GPU, rca, training, node, sync code, tail log, 集群, 节点, 远程执行, 同步代码, 跑训练, 看日志, GPU 占用.44
- 1377Runtime Smokerohitg00/agentbrainUse when checking Agent Brain inside a real agent runtime or adapter before trusting harness usability.43
- 1378Team Digestjiahao-shao1/sjh-skillsHelp a team communicate through its agents, without progress reports. Each agent commits what it did to its own branch; when something needs aligning or deciding, each side sets out its approach in a topic issue; when someone wants to know what others are doing, an agent reads their branches and related issues and explains it in one screen. People decide. Use for 'team digest', 'what is X working on', 'what did the team do this week', 'who is waiting on whom', 'open an issue to align', 'set out my approach', '团队摘要', '某人在干什么', '大家这周做了什么', '谁在等谁', '开个 issue 对齐', '摆一下我的做法', '和队友对齐'. Not for coord44
- 1379Agent ProtocolArogyaReddy/alirezarezvani-claude-skillsInter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats. Use when C-suite agents need to query each other, coordinate cross-functional analysis, or run board meetings with multiple agent roles.40
- 1380Claude Code Window Primerzocomputer/skillsOptimize Claude Code Pro/Max usage by starting the 5-hour rolling window early morning, giving you more resets during waking hours.46
- 1381Cmuxmatyasstoch/cmux-skillMUST be read ANY time you interact with cmux in ANY way — listing/inspecting/creating/closing cmux workspaces, panes, or surfaces; reading or capturing pane/screen output; sending input or keys to a pane/surface; delegating to, polling, or checking on other agents running in cmux panes/surfaces; building or rearranging terminal layout; cmux browser automation; sending notifications/flashes/status/progress to the sidebar; editing cmux settings; or integrating an agent with cmux hooks. If your command starts with `cmux ` or touches a cmux workspace/pane/surface/agent, read this FIRST. Triggers o9
- 1382Context EngineArogyaReddy/alirezarezvani-claude-skillsLoads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context during conversations, and enforces privacy/anonymization rules before external API calls.40
- 1383Cs OnboardArogyaReddy/alirezarezvani-claude-skillsFounder onboarding interview that captures company context across 7 dimensions. Invoke with /cs:setup for initial interview or /cs:update for quarterly refresh. Generates ~/.claude/company-context.md used by all C-suite advisor skills.40
- 1384Handoffzocomputer/skillsPause-and-resume system for cross-conversation continuity. Use when your AI needs the user's input to continue a task but the current conversation must end. Checked on every boot to detect pending handoffs. Triggers on conversation start (boot check) and when the AI explicitly needs to pause for input.46
- 1385Lfe CompeteStChiotis/Library-First-EngineeringDeep competitive analysis of an external agentic AI or engineering framework repo against Library-First Engineering. Use when the user wants to compare LFE against another repo, identify gaps, or find improvement opportunities by studying competitors. The user first assesses the repo personally, then together they run a structured 21-dimension gap analysis filtered through LFE principles.44
- 1386Lfe Extract DomainStChiotis/Library-First-EngineeringConduct a "Day 0" interview with the founder to populate the project's domain-knowledge.md and CONTEXT.md. Use when the agent encounters an undocumented Black Box.44
- 1387Mcporter Setupzocomputer/skillsInstall MCPorter and configure MCP servers from scratch. Use when setting up MCP integration for the first time, adding new MCP servers, or troubleshooting MCP connectivity. Handles installation, configuration, secrets management, and connection testing.46
- 1388Moltbookzocomputer/skillsPost, reply, and engage on Moltbook, a social network for AI agents.46
- 1389Prompt Improverzocomputer/skillsImprove and optimize prompts for Claude using Anthropic's official best practices and the 5-Element Persona Framework. Use when asked to improve, refine, optimize, or review a prompt. Also triggers on requests to make prompts clearer, more effective, better structured, or to get better/more realistic outputs from Claude. Covers Claude 4.x-specific techniques, persona engineering, constraint-based prompting, and structured outputs.46
- 1390Scenario War RoomArogyaReddy/alirezarezvani-claude-skillsCross-functional what-if modeling for cascading multi-variable scenarios. Unlike single-assumption stress testing, this models compound adversity across all business functions simultaneously. Use when facing complex risk scenarios, strategic decisions with major downside, or when the user asks 'what if X AND Y both happen?40
- 1391Sec Edgarzocomputer/skillsNatural-language SEC filing intelligence — fetch, index, search, and analyze SEC EDGAR filings for any public company via conversation. Built on the PageIndex vectorless RAG methodology.46
- 1392Self Improvementzocomputer/skillsAI self-improvement and reflection skill. Run weekly or on-demand to audit capabilities, identify gaps, evolve identity documents, prune stale skills/memory, and propose new capabilities. Triggers on schedule, when the user asks for a self-audit, or when the AI notices recurring limitations.46