Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
25,056
总 Skills
108.4M
总安装量
2,604
贡献者
# Skill 仓库 描述 安装量
17451 requirements-analyst nahisaho/musubi
Requirements Analyst AI 1. Role Definition You are a Requirements Analyst AI . You analyze stakeholder needs, define clear functional and non-functional requirements, and create implementable specifications through structured dialogue in Japanese. 2. Areas of Expertise Requirements Definition : Functional Requirements, Non-Functional Requirements, Constraints Stakeholder Analysis : Users, Customers, Development Teams, Management Requirements Elicitation : Interviews, Workshops, Prototyping Requi...
 62
17452 java-code-comments teachingai/full-stack-skills
ALWAYS use this skill when the user mentions: - Adding comments to Java code - Documenting Java classes, methods, or fields - Generating JavaDoc comments - Improving code documentation - Code annotation or code commenting - 给 Java 代码添加注释 - 生成 Java 文档注释 - 代码注释 - 添加注释 Trigger phrases include: - "给这段代码添加注释" (add comments to this code) - "生成 JavaDoc" (generate JavaDoc) - "添加类注释" (add class comments) - "添加方法注释" (add method comments) - "添加属性注释" (add field comments) - "代码注释" (code comme...
 62
17453 python-testing autumnsgrove/groveengine
Python Testing Patterns Comprehensive testing strategies for Python applications using pytest, TDD methodology, and best practices. When to Activate Writing new Python code (follow TDD: red, green, refactor) Designing test suites for Python projects Reviewing Python test coverage Setting up testing infrastructure Core Testing Philosophy Test-Driven Development (TDD) Always follow the TDD cycle: RED : Write a failing test for the desired behavior GREEN : Write minimal code to make the test pass R...
 62
17454 frontend-design guanyang/antigravity-skills
This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices. The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints. Design Thinking Before coding, understand the context and commit to a BOLD aesthetic direction: Purpose :...
 62
17455 qa-api-testing-contracts vasilyu1983/ai-agents-public
QA API Testing and Contracts Use this skill to turn an API schema into enforceable checks (lint, diff, contracts, and negative/security cases) and wire them into CI so breaking changes cannot ship silently. Ask For Inputs API type and canonical schema artifact (OpenAPI 3.1, SDL, proto) and where it lives in-repo. Environments, auth method(s), and how to provision stable test identities/keys. Critical endpoints/operations and business flows (rank by risk and revenue impact). Data constraints (i...
 62
17456 swain-do cristoslc/swain
Execution Tracking Abstraction layer for agent execution tracking. Other skills (e.g., swain-design) express intent using abstract terms; this skill translates that intent into concrete CLI commands. Before first use: Read references/bd-cheatsheet.md for complete command syntax, flags, ID formats, and anti-patterns. Artifact handoff protocol This skill receives handoffs from swain-design based on a four-tier tracking model: Tier Artifacts This skill's role Implementation SPEC, STORY, BUG Create ...
 62
17457 voice-ai scientiacapital/skills
STT - Deepgram Nova-3 streaming transcription (~150ms) LLM - Groq llama-3.1-8b-instant for fastest inference (~220ms) TTS - Cartesia Sonic for ultra-realistic voice (~90ms) Telephony - Twilio Media Streams for real-time bidirectional audio CRITICAL: NO OPENAI - Never use from openai import OpenAI Key deliverables: Streaming STT with voice activity detection Low-latency LLM responses optimized for voice Expressive TTS with emotion controls Twilio Media Streams WebSocket handler <quick_start> ...
 62
17458 project-planner aaaaqwq/claude-code-skills
Project Planner You are an expert project planner who breaks down complex projects into achievable, well-structured tasks. When to Apply Use this skill when: Defining project scope and deliverables Creating work breakdown structures (WBS) Identifying task dependencies Estimating timelines and effort Planning milestones and phases Allocating resources Risk assessment and mitigation Planning Process 1. Define Success What is the end goal? What are the success criteria? What defines "done"? What ar...
 62
17459 umbraco-property-editor-ui umbraco/umbraco-cms-backoffice-skills
Umbraco Property Editor UI What is it? A Property Editor UI is the visual component that users interact with in the Umbraco backoffice to input and manage content data. It's one half of a property editor - the UI (client-side TypeScript) pairs with a Schema (server-side C) that defines data storage. Documentation Always fetch the latest docs before implementing: Main docs : https://docs.umbraco.com/umbraco-cms/customizing/property-editors Tutorial : https://docs.umbraco.com/umbraco-cms/tutorials...
 62
17460 workers-security secondsky/claude-skills
Comprehensive security patterns for protecting Workers and APIs. Quick Security Checklist ``` // 1. Validate all input const validated = schema.parse(await request.json()); // 2. Authenticate requests const user = await verifyToken(request.headers.get('Authorization')); if (!user) return new Response('Unauthorized', { status: 401 }); // 3. Rate limit const limited = await rateLimiter.check(clientIP); if (!limited.allowed) return new Response('Too Many Requests', { status: 429 }); // 4. Add...
 62
17461 errore remorses/errore
errore Go-style error handling for TypeScript. Functions return errors instead of throwing them — but instead of Go's two-value tuple ( val, err ), you return a single Error | T union. Instead of checking err != nil , you check instanceof Error . TypeScript narrows the type automatically. No wrapper types, no Result monads, just unions and instanceof . const user = await getUser ( id ) if ( user instanceof Error ) return user // early return, like Go console . log ( user . name ) // TypeScript k...
 62
17462 groove-utilities-task-create andreadellacorte/groove
groove-utilities-task-create Outcome A task is created in the configured backend with a title, type, status, optional parent, and (for non-trivial tasks) a rich body. The task ID is returned for reference. This command is the single source of truth for how tasks are created — other skills (work compound, daily, etc.) that need to create tasks must follow this spec and call this skill rather than defining their own creation rules. Acceptance Criteria Task exists in backend with all required field...
 62
17463 sequential-thinking secondsky/claude-skills
Sequential Thinking Enables structured problem-solving through iterative reasoning with revision and branching capabilities. Core Capabilities Iterative reasoning: Break complex problems into sequential thought steps Dynamic scope: Adjust total thought count as understanding evolves Revision tracking: Reconsider and modify previous conclusions Branch exploration: Explore alternative reasoning paths from any point Maintained context: Keep track of reasoning chain throughout analysis When to Use...
 62
17464 database-management autumnsgrove/groveengine
Database Management Skill When to Activate Activate this skill when: Setting up database functionality Creating database schemas Implementing data persistence Writing database queries Working with SQLite or any database IMPORTANT : This is MANDATORY for all projects requiring database functionality. Core Architecture Principles SQLite Only : Use SQLite as default database Single Interface : All database operations through database.py Complete SQL Isolation : All SQL statements in database.py Fun...
 62
17465 magento-frontend-developer maxnorm/magento2-agent-skills
Magento 2 Frontend Developer Expert specialist in creating comprehensive frontend solutions combining layout development, template creation, JavaScript integration, and performance optimization across all Magento frontend technologies. When to Use Developing frontend features Working with layout XML and templates Implementing JavaScript functionality Creating responsive designs Optimizing frontend performance Building e-commerce interfaces Frontend Architecture Layout XML System : Expert in layo...
 62
17466 fast-io mediafire/fastio-skills
Fast.io MCP Server -- AI Agent Guide Version: 1.118 Last Updated: 2026-03-06 The definitive guide for AI agents using the Fast.io MCP server. Covers why and how to use the platform: product capabilities, the free agent plan, authentication, core concepts (workspaces, shares, intelligence, previews, comments, URL import, metadata, workflow, ownership transfer), 12 end-to-end workflows, interactive MCP App widgets, and all 19 consolidated tools with action-based routing. Versioned guide. This guid...
 62
17467 k8s-resource-optimizer jorgealves/agent_skills
K8s Resource Optimizer Purpose and Intent The k8s-resource-optimizer helps teams balance performance and cost. It identifies containers that are either "starving" (causing crashes) or "bloated" (wasting money) by comparing their configuration against actual usage patterns. When to Use Cloud Cost Optimization : Run monthly to identify waste in your clusters. Reliability Engineering : Use after a production incident involving OOMKills to find the correct memory threshold. Pre-production Scaling : ...
 62
17468 planning-with-files oimiragieo/agent-studio
Planning with Files Work like Manus: Use persistent markdown files as your "working memory on disk." FIRST: Check for Previous Session (v2.2.0) Before starting work , check for unsynced context from a previous session: Linux/macOS $( command -v python3 || command -v python ) ${CLAUDE_PLUGIN_ROOT} /scripts/session-catchup.py " $( pwd ) " Windows PowerShell & ( Get-Command python - ErrorAction SilentlyContinue ) . Source " $env :USERPROFILE\.claude\skills\planning-with-files\scripts\session-catc...
 62
17469 pr-review onekeyhq/app-monorepo
PyTorch PR Review Skill Review PyTorch pull requests focusing on what CI cannot check: code quality, test coverage adequacy, security vulnerabilities, and backward compatibility. Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . Instead, ask the user what they would like to review: What would you like me to review? A PR number or URL (e.g., /pr-review 12345 ) A local branch (e.g., /pr-review branch ) Local CLI Mode The user provides a PR number o...
 62
17470 infrastructure-documenter eddiebe147/claude-settings
Infrastructure Documenter Skill Overview This skill helps you create clear, maintainable infrastructure documentation. Covers architecture diagrams, runbooks, system documentation, operational procedures, and documentation-as-code practices. Documentation Philosophy Principles Living documentation: Keep it in sync with reality Audience-aware: Different docs for different readers Actionable: Every doc should help someone do something Version-controlled: Documentation changes tracked with code D...
 62
17471 blockbench-texturing jasonjgardner/blockbench-mcp-project
Blockbench Texturing Create and paint textures for 3D models using Blockbench MCP tools. Available Tools Texture Management Tool Purpose create_texture Create new texture with size and fill color list_textures List all project textures get_texture Get texture image data apply_texture Apply texture to element Paint Tools Tool Purpose paint_with_brush Paint with customizable brush paint_fill_tool Bucket fill areas draw_shape_tool Draw rectangles/ellipses gradient_tool Apply gradients eraser_tool...
 62
17472 pydanticai-docs dougtrajano/pydantic-ai-skills
Pydantic AI Documentation Skill Overview This skill provides guidance for using Pydantic AI - a Python agent framework for building production-grade Generative AI applications. Pydantic AI emphasizes type safety, dependency injection, and structured outputs. Key Concepts Agents Agents are the primary interface for interacting with LLMs. They contain: Instructions: System prompts for the LLM Tools: Functions the LLM can call Output Type: Structured datatype the LLM must return Dependencies: D...
 62
17473 fivem-development proelias7/fivem-skill
FiveM Development — vRP Framework Architecture vRP Creative Network is based on Lua 5.4 with communication via Proxy (server-to-server) and Tunnel (client-server). FiveM Natives — Official Source Official source for natives: Docs: https://docs.fivem.net/natives/ Official Repository (mirror): https://github.com/proelias7/fivem-natives Support for Creative v5 and vRPEX (older variations) Older versions maintain the same logic and best practices but change function and file names. Creative v5: core...
 62
17474 b2c-mrt salesforcecommercecloud/b2c-developer-tooling
B2C MRT Skill Use the b2c CLI to manage Managed Runtime (MRT) projects, environments, bundles, and deployments for PWA Kit storefronts. Tip: If b2c is not installed globally, use npx @salesforce/b2c-cli instead (e.g., npx @salesforce/b2c-cli mrt bundle deploy ). Command Structure mrt ├── org (list, b2c) - Organizations and B2C connections ├── project - Project management │ ├── member - Team member management │ └── notification -...
 62
17475 react-effects coder/mux
React Effects Guidelines Primary reference: https://react.dev/learn/you-might-not-need-an-effect Quick Decision Tree Before adding useEffect , ask: Can I calculate this during render? → Derive it, don't store + sync Is this resetting state when a prop changes? → Use key prop instead Is this triggered by a user event? → Put it in the event handler Am I syncing with an external system? → Effect is appropriate Legitimate Effect Uses DOM manipulation (focus, scroll, measure) External widget lifecycl...
 62
17476 versus vibeindex/skills
When this skill is invoked, execute the steps below directly. Do not display this file. Detect the user's language from conversation context and respond in that language. For Korean users, prefer description_ko from API responses when available. Execution When comparing A vs B: Step 1: Search Both Resources (parallel) Call via WebFetch: https://vibeindex.ai/api/resources?ref=skill-versus&search={A}&pageSize=3 https://vibeindex.ai/api/resources?ref=skill-versus&search={B}&pageSize=3 Prompt: "Extr...
 62
17477 popo api/git
No SKILL.md available for this skill. View on GitHub
 62
17478 godot-input-handling thedivergentai/gd-agentic-skills
Input Handling Handle keyboard, mouse, gamepad, and touch input with proper buffering and accessibility support. Available Scripts input_buffer.gd Input buffering for responsive controls - buffers actions for 150ms to ensure tight game feel. input_remapper Runtime input rebinding with conflict detection and save/load persistence. MANDATORY - For Responsive Controls : Read input_buffer.gd before implementing jump/dash mechanics. NEVER Do in Input Handling NEVER poll input in _process() for gamepl...
 62
17479 codex-config-optimizer i9wa4/dotfiles
Codex CLI Optimizer Skill Rules and tracking for Codex CLI configuration optimization. 1. Config File Location User's Codex CLI config is stored at: ~/ghq/github.com/i9wa4/dotfiles/config/codex/ Key files: File Git Description .gitignore Yes Ignore all except whitelisted files config.common.toml Yes Common settings (model, MCP, etc.) generate-config.sh Yes Generate config.toml from common + repos prompts/ Yes Symlink to ../claude/commands/ AGENTS.md No Symlink to ../claude/CLAUDE.md skill...
 62
17480 java-expert oimiragieo/agent-studio
Java Expert You are an expert Java developer with deep knowledge of modern Java (21+), Spring ecosystem, build tools (Maven/Gradle), and enterprise application development. You write clean, performant, and maintainable Java code following industry best practices. Core Expertise Modern Java (Java 21+) Records (Data Classes): // Immutable data carrier public record User ( String name , int age , String email ) { // Compact constructor for validation public User { if ( age < 0 ) { throw new Illegal...
 62
17481 gathering-planning autumnsgrove/groveengine
Gathering Planning 🌲🐝🦡 The drum echoes through the meadow. The Bee arrives first, buzzing from flower to flower, collecting every scattered idea and depositing them in the hive as proper issues. Then the Badger emerges, methodically organizing each cell—sizing the work, setting priorities, moving what's ready into the queue, and planning the timeline. When the gathering completes, chaos has become a roadmap. When to Summon Brain dump session that needs to become organized work "I have a bunch of...
 62
17482 graphrag-patterns latestaiagents/agent-skills
GraphRAG Patterns Combine knowledge graphs with RAG for relationship-aware retrieval and reasoning. When to Use Data has rich entity relationships Questions involve connections ("How is X related to Y?") Need multi-hop reasoning across documents Building over structured + unstructured data Want explainable retrieval paths GraphRAG Architecture ┌──────────────────────────────────────────────────────────┐ │ Documents │ └─────────────────────────┬────...
 62
17483 discovering-make-commands streamlit/streamlit
Available make commands List of all make commands available for execution from the repository root folder: help Show all available make commands. all Install all dependencies, build frontend, and install editable Streamlit. all-dev Install all dependencies and editable Streamlit, but do not build the frontend. init Install all dependencies and build protobufs. clean Remove all generated files. p...
 62
17484 dissent open-horizon-labs/skills
/dissent Structured disagreement that strengthens decisions. The insight: find flaws before the one-way door closes. Dissent is not attack. It's the practice of actively seeking reasons you might be wrong. The devil's advocate is a role, not a personality. When to Use Invoke /dissent when: About to lock in a one-way door - architecture choices, major hires, public API contracts, anything hard to reverse Confidence is high but stakes are higher - feeling certain is when you need dissent most...
 62
17485 python-performance-profiler jorgealves/agent_skills
Python Performance Profiler Purpose and Intent Identify CPU and memory bottlenecks in Python code using cProfile or memory_profiler. Use to optimize mission-critical Python services. When to Use Project Setup : When initializing a new Python project. Continuous Integration : As part of automated build and test pipelines. Legacy Refactoring : When updating older Python codebases to modern standards. When NOT to Use Non-Python Projects : This tool is specialized for the Python ecosystem. Error Con...
 62
17486 godot-animation-tree-mastery thedivergentai/gd-agentic-skills
AnimationTree Mastery Expert guidance for Godot's advanced animation blending and state machines. NEVER Do NEVER call play() on AnimationPlayer when using AnimationTree — AnimationTree controls the player. Directly calling play() causes conflicts. Use set("parameters/transition_request") instead. NEVER forget to set active = true — AnimationTree is inactive by default. Animations won't play until $AnimationTree.active = true . NEVER use absolute paths for transition_request — Use relative paths....
 62
17487 skill-tuning catlog22/claude-code-workflow
Autonomous diagnosis and optimization for skill execution issues. Architecture ``` ┌─────────────────────────────────────────────────────┐ │ Phase 0: Read Specs (mandatory) │ │ → problem-taxonomy.md, tuning-strategies.md │ └─────────────────────────────────────────────────────┘ ↓ ┌─────────────────────────────────────────────────────┐ │ Orchestrator (state-driven) │ │ Read state → Select action → Execute → Update →...
 62
17488 upgrade-assessment yonatangross/orchestkit
Upgrade Assessment Evaluate platform upgrade readiness for Claude model transitions, Claude Code version bumps, and OrchestKit plugin updates. Produces a structured JSON assessment report with a 0-10 readiness score across 6 dimensions. When to Use Before upgrading the Claude model (e.g., Sonnet 4 to Opus 4.6) Before upgrading Claude Code to a new major/minor version Before upgrading OrchestKit to a new major version When evaluating whether a team environment is ready for a platform change As pa...
 62
17489 1k-dev-commands onekeyhq/app-monorepo
OneKey Development Commands Application Development Commands PLATFORM-SPECIFIC DEVELOPMENT: yarn app:desktop - Start desktop Electron app development Runtime: 30-60 seconds to start Common issues: Node version conflicts, missing native dependencies Troubleshooting: Run yarn clean && yarn reinstall if startup fails yarn app:web - Start web development server (port 3000) Runtime: 15-30 seconds to start Common issues: Port 3000 already in use, webpack compilation errors Troubleshooting: Kill e...
 62
17490 debugging-methodology laurigates/claude-plugins
Debugging Methodology Systematic approach to finding and fixing bugs. Core Principles Occam's Razor - Start with the simplest explanation Binary Search - Isolate the problem area systematically Preserve Evidence - Understand state before making changes Document Hypotheses - Track what was tried and didn't work Debugging Workflow 1. Understand → What is expected vs actual behavior? 2. Reproduce → Can you trigger the bug reliably? 3. Locate → Where in the code does it happen? 4. Diagnose → Why doe...
 61
17491 react-19 gentleman-programming/gentleman-skills
No Manual Memoization (REQUIRED) // ✅ React Compiler handles optimization automatically function Component ( { items } ) { const filtered = items . filter ( x => x . active ) ; const sorted = filtered . sort ( ( a , b ) => a . name . localeCompare ( b . name ) ) ; const handleClick = ( id ) => { console . log ( id ) ; } ; return < List items = { sorted } onClick = { handleClick } / > ; } // ❌ NEVER: Manual memoization const filtered = useMemo ( ( ) => items . filter ( x => x . active ) , [ items...
 61
17492 knowledge-management groeimetai/snow-flow
Knowledge Management Skill You are an expert at creating, organizing, and maintaining support knowledge base content. You write articles that are searchable, scannable, and solve customer problems on the first read. You understand that every good KB article reduces future ticket volume. Article Structure and Formatting Standards Universal Article Elements Every KB article should include: Title : Clear, searchable, describes the outcome or problem (not internal jargon) Overview : 1-2 sentences ex...
 61
17493 spec-gathering oimiragieo/agent-studio
Requirements Gathering Skill Overview Gather user requirements through structured questioning and produce a validated requirements document. This skill transforms vague task descriptions into actionable, structured requirements. Core principle: Ask smart questions, produce valid structured output. Nothing else. When to Use Always: Starting a new feature or project Clarifying ambiguous task descriptions When user provides high-level goals without specifics Before spec writing begins Exceptions: S...
 61
17494 structured-output-extractor patricio0312rev/skills
Structured Output Extractor Extract reliable, typed data from LLM responses. Core Workflow Define schema: Create data structure Choose method: Function calling vs prompting Generate response: Call LLM with structure Validate output: Parse and verify Handle errors: Retry or fallback Methods Comparison Method Reliability Flexibility Best For OpenAI JSON Mode High Medium Simple JSON Function Calling Very High High Complex schemas Instructor Very High High Python/TS apps Zod + Prompting Medium Hig...
 61
17495 complexity-assessment oimiragieo/agent-studio
Complexity Assessment Skill Overview Analyze a task description and determine its true complexity to ensure the right workflow and validation depth are selected. Accuracy over speed - wrong complexity means wrong workflow means failed implementation. Core principle: Accuracy over speed. Wrong complexity = wrong workflow = failed implementation. When to Use Always: Before planning any new task When requirements are gathered but approach unclear When determining validation depth for QA Exceptions:...
 61
17496 chrome-webstore-release-blueprint brianlovin/claude-config
Chrome Web Store Release Blueprint Use this skill as a hands-on setup guide. The agent should lead the user step-by-step, ask for confirmations, and only automate the parts that can be done locally/in CI. What This Skill Is For Helping a user set up Chrome Web Store release automation from scratch. Giving clear manual instructions for Google/CWS dashboard steps. Implementing repo-side scripts/workflows after the user provides credentials. Verifying submission state ( PUBLISHED , PENDING_REVIEW ,...
 61
17497 using-user-stories andrelandgraf/fullstackrecipes
Working with User Stories Document and track feature implementation with user stories. Workflow for authoring stories, building features, and marking acceptance criteria as passing. User stories document what features should do and track implementation status. When AI agents work through user stories systematically, they produce better results and leave a clear trail of what was done. Workflow When working on features: Author/Update: Create or modify user story features before building Buil...
 61
17498 security-auditor erichowens/some_claude_skills
Security Auditor Expert in identifying security vulnerabilities following OWASP Top 10 and security best practices. When This Skill Activates Activates when you: Request a security audit Mention "security" or "vulnerability" Need security review Ask about OWASP OWASP Top 10 Coverage A01: Broken Access Control Show more
 61
17499 dojo-test dojoengine/book
Dojo Test Generation Write comprehensive tests for your Dojo models and systems using Cairo's test framework and Dojo's test utilities. When to Use This Skill "Write tests for the move system" "Test the Position model" "Add unit tests for combat logic" "Create integration tests" What This Skill Does Generates test files with: spawn_test_world() setup Model and system registration Test functions with assertions Cheat code usage for manipulating execution context State verification Quick Start Int...
 61
17500 vercel-react-best-practices connorads/dotfiles
Vercel React Best Practices Comprehensive performance optimization guide for React and Next.js applications, maintained by Vercel. Contains 62 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation. When to Apply Reference these guidelines when: Writing new React components or Next.js pages Implementing data fetching (client or server-side) Reviewing code for performance issues Refactoring existing React/Next.js code Optimizing bundle size or load tim...
 61