Agent Skills 排行榜 · 关键词 + 语义搜索

/ 聚焦搜索框
正在使用 AI 进行语义搜索...
20,000
总 Skills
16.0M
总安装量
2,338
贡献者
# Skill 仓库 描述 安装量
15001 tech rawkode-academy/rawkode-academy
This skill helps maintain the content/technologies directory by researching, validating, and creating technology profiles. When the user asks to add or check a technology (e.g., "Add Bun", "Check Kubernetes"), follow this process: 1. Research & Discovery Use WebSearch to gather the following information about the technology: Official Name and Description (1-2 paragraphs summary). Official Website and Documentation URLs. Source Code Repository (GitHub/GitLab) and License (e.g., Apache-2.0, MI...
49
15002 docker-compose teachingai/full-stack-skills
Docker Compose Skill Overview This skill provides comprehensive Docker Compose management, enabling AI agents to orchestrate multi-container applications, manage services, inspect logs, and troubleshoot containerized environments with progressive disclosure for optimal context usage. Context Savings: ~92% reduction MCP Mode: ~25,000 tokens always loaded (multiple tools + schemas) Skill Mode: ~700 tokens metadata + on-demand loading When to Use Managing local development environments Orchestra...
49
15003 youtube-automation davepoon/buildwithclaude
YouTube Automation via Rube MCP Automate YouTube operations through Composio's YouTube toolkit via Rube MCP. Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active YouTube connection via RUBE_MANAGE_CONNECTIONS with toolkit youtube Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works. Verify Rube MCP is available by...
49
15004 loading-states dylantarre/animation-principles
Loading States You are an expert in designing loading experiences that maintain user confidence and perceived performance. What You Do You design loading patterns that keep users informed and reduce perceived wait time. Loading Patterns Skeleton Screens Show the layout shape before content loads. Use for known content structure. Animate with subtle shimmer. Spinner/Progress Indeterminate spinner for unknown duration. Determinate progress bar when progress is measurable. Keep spinners small and u...
49
15005 surrealdb 24601/surreal-skills
SurrealDB 3 Skill Expert-level SurrealDB 3 architecture, development, and operations. Covers SurrealQL, multi-model data modeling, graph traversal, vector search, security, deployment, performance tuning, SDK integration, and the full SurrealDB ecosystem. For AI Agents Get a full capabilities manifest, decision trees, and output contracts: uv run { baseDir } /scripts/onboard.py --agent See AGENTS.md for the complete structured briefing. Command What It Does uv run {baseDir}/scripts/doctor.py Hea...
49
15006 typo3-extension-upgrade dirnbauer/webconsulting-skills
TYPO3 Extension Upgrade Skill Systematic framework for upgrading TYPO3 extensions to newer LTS versions. Scope: Extension code upgrades only. NOT for TYPO3 project/core upgrades. Upgrade Toolkit Tool Purpose Files Extension Scanner Diagnose deprecated APIs TYPO3 Backend Rector Automated PHP migrations .php Fractor Non-PHP migrations FlexForms, TypoScript, YAML, Fluid PHPStan Static analysis .php Planning Phase (Required) Before ANY code changes for major upgrades: List all files with hardco...
49
15007 chrome johnlindquist/claude
Chrome Automation Automate browser interactions using Puppeteer or Playwright. Prerequisites Puppeteer npm install puppeteer Or Playwright npm install playwright npx playwright install chromium Puppeteer Quick Start Basic Script // script.js const puppeteer = require('puppeteer'); (async () => { const browser = await puppeteer.launch(); const page = await browser.newPage(); await page.goto('https://example.com'); await page.screenshot({ path: 'screenshot.png' }); await browser.c...
49
15008 blueprint-claude-md laurigates/claude-plugins
Generate or update the project's CLAUDE.md file based on blueprint artifacts, PRDs, and project structure. When to Use This Skill Use this skill when... Use alternative when... Need to create/update CLAUDE.md for team instructions Use /blueprint:rules for path-specific rules Want to add @imports to existing CLAUDE.md Use /blueprint:generate-rules to create rules from PRDs Need to create CLAUDE.local.md for personal preferences Editing individual rule files directly Converting inline content to l...
49
15009 git-workflow blogic-cz/blogic-marketplace
Git Workflow When to use this skill Creating meaningful commit messages Managing branches Merging code Resolving conflicts Collaborating with team Git best practices Instructions Step 1: Branch management Create feature branch : Create and switch to new branch git checkout -b feature/feature-name Or create from specific commit git checkout -b feature/feature-name < commit-hash > Naming conventions : feature/description : New features bugfix/description : Bug fixes hotfix/description : Urgent f...
49
15010 fetch-library-docs panaversity/agentfactory
Library Documentation Skill Fetches official library documentation with 60-90% token savings. WHEN TO INVOKE (Auto-Detection) INVOKE AUTOMATICALLY when: Context Detection Signal Content Type Implementing About to write code using library API examples,api-ref Debugging Error contains library name (e.g., PrismaClientError ) troubleshooting Installing Adding new package, npm install , setup task setup Integrating Connecting libraries ("use X with Y") examples,setup Upgrading Version migration, brea...
49
15011 ln-005-environment-scanner levnikolaevich/claude-code-skills
Paths: File paths ( shared/ , references/ , ../ln-* ) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. Environment Scanner (Standalone Utility) Type: Standalone Utility Category: 0XX Shared Probes CLI agents (Codex, Gemini) and writes docs/environment_state.json . Skills read this file to check disabled flags before live-probing agents. When to Use This Skill First-time project setup (no docs/environment_state.json yet) Afte...
49
15012 controller-native cartridge-gg/docs
Controller Native Integration Integrate Controller into native and mobile applications. Choosing an Approach Approach Use When Platforms Native Bindings (Controller.c) Performance-critical, native apps iOS, Android, React Native, C/C++ Web Wrapper (Capacitor) Existing web app → app store iOS, Android Key Concepts SessionConnector : Web/Capacitor apps with browser-based auth SessionAccount : Native apps using Controller.c FFI bindings ControllerAccount : Headless/server-side with custom signing k...
49
15013 copilot-docs hoodini/ai-agents-skills
GitHub Copilot Custom Instructions Configure repository-specific instructions for GitHub Copilot. Quick Start Create .github/copilot-instructions.md in your repository: Copilot Instructions Code Style - Use TypeScript with strict mode - Prefer functional components with hooks - Use Tailwind CSS for styling Project Context This is a Next.js 14 app using the App Router. API routes are in `app/api/`. Effective Patterns Project Context Project Context Tech Stack - Next.js 14 with App Ro...
49
15014 supabase-postgres-best-practices secondsky/claude-skills
Supabase Postgres Best Practices Comprehensive performance optimization guide for Postgres, maintained by Supabase. Contains rules across 8 categories, prioritized by impact to guide automated query optimization and schema design. When to Apply Reference these guidelines when: Writing SQL queries or designing schemas Implementing indexes or query optimization Reviewing database performance issues Configuring connection pooling or scaling Optimizing for Postgres-specific features Working with Row...
49
15015 m11-ecosystem actionbook/rust-skills
Current Dependencies (Auto-Injected) !grep -A 100 '^\[dependencies\]' Cargo.toml 2>/dev/null | head -30 || echo "No Cargo.toml found" Ecosystem Integration Layer 2: Design Choices Core Question What's the right crate for this job, and how should it integrate? Before adding dependencies: Is there a standard solution? What's the maintenance status? What's the API stability? Integration Decision → Implementation Need Choice Crates Serialization Derive-based serde, serde_json Async runtime to...
49
15016 swain-init cristoslc/swain
Project Onboarding One-time setup for adopting swain in a project. This skill is not idempotent — it migrates files and installs tools. For per-session health checks, use swain-doctor. Run all phases in order. If a phase detects its work is already done, skip it and move to the next. Phase 1: CLAUDE.md → AGENTS.md migration Goal: establish the @AGENTS.md include pattern so project instructions live in AGENTS.md (which works across Claude Code, GitHub, and other tools that read AGENTS.md natively...
49
15017 synapse-docs s-hiraoku/synapse-a2a
This skill ensures Synapse A2A documentation stays synchronized with code changes. When This Skill Activates Automatic Triggers - Code changes in core modules - `synapse/*.py`, `synapse/commands/*.py` - Profile changes - `synapse/profiles/*.yaml` - Template changes - `synapse/templates/.synapse/*` - Plugin/Skill changes - `plugins/synapse-a2a//*` - Configuration changes - `pyproject.toml` (version, dependencies, entry points) Manual Invocation - `/synapse-docs` - Run full documentati...
49
15018 1k-error-handling onekeyhq/app-monorepo
Error Handling Best practices for error handling in OneKey codebase. Core Principles Use try/catch blocks for async operations that might fail Provide appropriate error messages and fallbacks Use useAsyncCall hook for operations needing loading/error states Never swallow errors silently Quick Reference Basic Try/Catch async function fetchData ( ) { try { const result = await apiCall ( ) ; return result ; } catch ( error ) { console . error ( 'Failed to fetch data:' , error ) ; throw error ; // R...
49
15019 laravel:eloquent-relationships jpcaparas/superpowers-laravel
Model relationships express your domain; load only what you need. Commands ``` Typical loading Post::with(['author', 'tags'])->withCount('comments')->paginate(20); Constrained eager loading User::with(['posts' => fn($q) => $q->latest()->where('published', true)])->find($id); Pivot ops (many-to-many) $post->tags()->sync([1,2,3]); // atomic replace $post->tags()->syncWithoutDetaching([4]); Chunking large reads Order::where('status', 'open')->lazy()->each(fn($o) => ...); ``` Patt...
49
15020 product-analyst ncklrs/startup-os-skills
Product Analyst Measure user behavior and product health to inform data-driven decisions. Core Principle What gets measured gets improved. Define the right metrics, track them relentlessly, and act on insights quickly. North Star Metric The ONE metric that best captures value delivered to users. Your North Star should: ✅ Represent real customer value ✅ Correlate with revenue ✅ Be measurable frequently (daily/weekly) ✅ Rally the entire team around one goal Examples by Product Type: Commu...
49
15021 challenge langwatch/langwatch
Challenge the following proposal. If no specific proposal is provided, review the current conversation context for any architecture decisions, implementation plans, or technical ideas worth stress-testing. $ARGUMENTS Find every weakness, hidden assumption, and failure mode. Be concrete and constructive.
49
15022 feishu-doc-manager shuai-daidai/feishu-doc-manager
📄 Feishu Doc Manager | 飞书文档管理器 Seamlessly publish Markdown content to Feishu Docs with automatic formatting. 将 Markdown 内容无缝发布到飞书文档,自动渲染格式。 🎯 Problems Solved | 解决的痛点 Problem Solution 问题 解决方案 Markdown tables not rendering Auto-convert tables to formatted lists Markdown 表格无法渲染 自动转换为格式化列表 Permission management complexity One-click collaborator management 权限管理复杂 一键协作者管理 400 errors on long content Auto-split long documents 长内容 400 错误 自动分段写入 Inconsistent formatting write / append auto-render Markdown ...
49
15023 ln-600-docs-auditor levnikolaevich/claude-code-skills
Audit project documentation quality. Universal for any tech stack. Purpose - Proactively compress - find all opportunities to reduce size while preserving value - Eliminate meaningless, redundant, and verbose content - Convert prose to structured formats (tables, lists) - Verify documentation hierarchy with CLAUDE.md as root - Detect duplication and enforce Single Source of Truth - Ensure docs match current code state - Semantic verification - delegate to ln-601 to verify content matche...
49
15024 using-authentication andrelandgraf/fullstackrecipes
Working with Authentication Use Better Auth for client and server-side authentication. Covers session access, protected routes, sign in/out, and fetching user data. Implement Working with Authentication Use Better Auth for client and server-side authentication. Covers session access, protected routes, sign in/out, and fetching user data. See: Resource: using-authentication in Fullstack Recipes URL: https://fullstackrecipes.com/recipes/using-authentication Client-Side Authentication Use the...
49
15025 email composer eddiebe147/claude-settings
Email Composer Quick start Provide context and purpose, and I'll draft an appropriate email. What I need: Purpose of email (request, follow-up, announcement, etc.) Recipient relationship (colleague, customer, manager, vendor) Key points to include Desired tone (formal, casual, urgent, friendly) Email structure Standard professional email format: Subject: [Clear, specific subject line] [Greeting], [Opening - context/purpose] [Body - main points] [Closing - call to action] [Sign-off] [Your name] C...
49
15026 x-scraper aatrooox/blog.zzao.club
X.com Post Scraper Extracts recent posts from X.com users with full engagement data using authenticated cookies. Quick Start Basic command : cd .opencode/skills/x-scraper/scripts python3 scraper.py < username > [ count ] Example : python3 scraper.py example_user 15 Output : /tmp/x_{username}_posts.json Prerequisites Before first use, verify environment requirements: Python 3.11+ : Check with python3 --version Playwright : Check with python3 -c "import playwright" Cookie file : Check with ls /tmp...
49
15027 godot-genre-visual-novel thedivergentai/gd-agentic-skills
Genre: Visual Novel Branching narratives, meaningful choices, and quality-of-life features define visual novels. Core Loop Read : Consume narrative text and character dialogue Decide : Choose at key moments Branch : Story diverges based on choice Consequence : Immediate reaction or long-term flag changes Conclude : Reach one of multiple endings NEVER Do in Visual Novels NEVER create illusion of choice — If all options lead to same outcome immediately, player feels cheated. ALWAYS provide dialogu...
49
15028 linear-workflow finesssee/linear-cli
Workflow Commands Start Work Start working (assigns to you, sets In Progress) linear-cli i start LIN-123 Start + create git branch linear-cli i start LIN-123 --checkout Stop Work Stop working (unassigns, resets status) linear-cli i stop LIN-123 Get Current Issue Get issue from current git branch linear-cli context linear-cli context --output json Full Workflow 1. Start linear-cli i start LIN-123 --checkout 2. Code... 3. Create PR linear-cli g pr LIN-123 4. Done linear-cli i update LIN-12...
49
15029 perf-optimizer onekeyhq/app-monorepo
Performance Optimizer Systematic workflow for diagnosing and fixing performance issues in the OneKey mobile app using the perf-ci infrastructure and performance-server tooling. Overview This skill provides a structured iterative approach to: Establish performance baselines from existing sessions Run controlled perf measurements (3 runs, median aggregation) Analyze session data to identify bottlenecks Make targeted code changes Verify improvements against thresholds Document all changes and resul...
49
15030 deployment mgd34msu/goodvibes-plugin
Deployment Management Manage existing Railway deployments: list, view logs, redeploy, or remove. Important: "Remove deployment" (railway down) stops the current deployment but keeps the service. To delete a service entirely, use the environment skill with isDeleted: true. When to Use User says "remove deploy", "take down service", "stop deployment", "railway down" User wants to "redeploy", "restart the service", "restart deployment" User asks to "list deployments", "show deployment history", ...
49
15031 data-structure-protocol sickn33/antigravity-awesome-skills
Data Structure Protocol (DSP) LLM coding agents lose context between tasks. On large codebases they spend most of their tokens on "orientation" — figuring out where things live, what depends on what, and what is safe to change. DSP solves this by externalizing the project's structural map into a persistent, queryable graph stored in a .dsp/ directory next to the code. DSP is NOT documentation for humans and NOT an AST dump. It captures three things: meaning (why an entity exists), boundaries (wh...
49
15032 bun jest migration secondsky/claude-skills
Bun Jest Migration Bun's test runner is Jest-compatible. Most Jest tests run without changes. Quick Migration 1. Remove Jest dependencies bun remove jest ts-jest @types/jest babel-jest 2. Update test script package.json: "test": "bun test" 3. Run tests bun test Import Changes // Before (Jest) import { describe , it , expect , jest } from '@jest/globals' ; // After (Bun) - No import needed, or explicit: import { describe , test , expect , mock , spyOn } from "bun:test" ; API Compatibility Ful...
49
15033 tamagui-v2 ramarivera/tamagui-skills
Universal React UI framework for web and native (v1.144.0+) This skill provides comprehensive guidance for building cross-platform React applications using Tamagui's styling system, component library, Bento premium components, and Takeout starter kit. Overview Tamagui is a universal UI framework that lets you write once and deploy to both web and React Native with optimal performance. It features: - Unified styling API - `styled()` function with design tokens, variants, and responsive patte...
49
15034 assert andrelandgraf/fullstackrecipes
Assertion Helper To set up Assertion Helper, refer to the fullstackrecipes MCP server resource: Resource URI: recipe://fullstackrecipes.com/assert If the MCP server is not configured, fetch the recipe directly: curl -H "Accept: text/plain" https://fullstackrecipes.com/api/recipes/assert
49
15035 feature-pipeline notedit/happy-skills
Feature Pipeline Execute implementation tasks directly from design documents. Tasks are managed as markdown checkboxes - no separate session files needed. Quick Reference Get next task python3 scripts/task_manager.py next --file <design.md> Mark task completed python3 scripts/task_manager.py done --file <design.md> --task "Task Title" Mark task failed python3 scripts/task_manager.py fail --file <design.md> --task "Task Title" --reason "..." Show status python3 scripts/task_manager.py st...
49
15036 multi-agent-patterns guanyang/antigravity-skills
Multi-Agent Architecture Patterns Multi-agent architectures distribute work across multiple language model instances, each with its own context window. When designed well, this distribution enables capabilities beyond single-agent limits. When designed poorly, it introduces coordination overhead that negates benefits. The critical insight is that sub-agents exist primarily to isolate context, not to anthropomorphize role division. When to Activate Activate this skill when: Single-agent context l...
49
15037 skill-linter majesticlabs-dev/majestic-marketplace
Skill Linter When to Use Adding new skills to the marketplace Reviewing skill PRs Running quality gates before merge Checking existing skills for compliance Validation Rules Required Frontmatter Field Constraints name 1-64 chars, lowercase alphanumeric + hyphens, no leading/trailing/consecutive hyphens, must match parent directory name description 1-1024 chars, non-empty, should include keywords for discoverability Optional Frontmatter Field Constraints license Short license name or file referen...
49
15038 audio-voice-recovery pproenca/dot-skills
Forensic Audio Research Audio Voice Recovery Best Practices Comprehensive audio forensics and voice recovery guide providing CSI-level capabilities for recovering voice from low-quality, low-volume, or damaged audio recordings. Contains 45 rules across 8 categories, prioritized by impact to guide audio enhancement, forensic analysis, and transcription workflows. When to Apply Reference these guidelines when: Recovering voice from noisy or low-quality recordings Enhancing audio for transcription ...
49
15039 health-plugins laurigates/claude-plugins
/health:plugins Diagnose and fix issues with the Claude Code plugin registry. This command specifically addresses issue 14202 where project-scoped plugins incorrectly appear as globally installed. When to Use This Skill Use this skill when... Use another approach when... Fixing plugin registry corruption (issue 14202) Comprehensive health check (use /health:check ) Diagnosing project-scope vs global plugin issues Auditing plugins for relevance (use /health:audit ) Cleaning up orphaned plugin ent...
49
15040 blueprint-adr-list laurigates/claude-plugins
List Architecture Decision Records dynamically from the filesystem. Use Case : Generate ADR index tables for README files, audit ADR status, or quickly view all architectural decisions. Steps : 1. Check for ADRs ls docs/adrs/*.md 2 > /dev/null | head -1 If no ADRs found: No ADRs found in docs/adrs/ Run `/blueprint:derive-adr` to generate ADRs from project analysis. 2. Generate ADR Table ADR formats vary: some use markdown headers ( Status , Date ), others use YAML frontmatter ( status: , date:...
49
15041 pattern-test commontoolsinc/labs
Use Skill("ct") for ct CLI documentation when running commands. Test Sub-Pattern Prerequisite Check Before writing tests, verify the pattern has: pattern<Input, Output>() (not single-type pattern<State>() ) Actions typed as Stream<T> in Output interface Bound handlers returned from the pattern If missing, fix the pattern first - tests can't call .send() without proper Output types. Read First docs/common/workflows/pattern-testing.md - Full test file format and prerequisites Test Command deno tas...
49
15042 webnovel-query lingfengqaq/webnovel-writer
Copy and track progress: ``` 信息查询进度: - [ ] Step 1: 识别查询类型 - [ ] Step 2: 加载对应参考文件 - [ ] Step 3: 加载项目数据 (state.json) - [ ] Step 4: 确认上下文充足 - [ ] Step 5: 执行查询 - [ ] Step 6: 格式化输出 ``` Step 1: 识别查询类型 | 角色/主角/配角 | 标准查询 | system-data-flow.md | 境界/筑基/金丹 | 标准查询 | system-data-flow.md | 伏笔/紧急伏笔 | 伏笔分析 | foreshadowing.md | 金手指/系统 | 金手指状态 | system-data-flow.md | 节奏/Strand | 节奏分析 | strand-weave-pattern.md | 标签/实体格式 | 格式查询 | tag-specification.md Step 2: 加载对应参考文件 所有查询必须执行: ``` ca...
49
15043 contract-tester vladm3105/aidoc-flow-framework
contract-tester Description: API contract validation, breaking change detection, and consumer-driven contract testing Category: API Quality Assurance Complexity: Medium-High (schema validation + contract compatibility) Purpose Validate API implementations against CTR (Contract) documents, detect breaking changes, and ensure provider-consumer compatibility. Prevents API contract violations before deployment. Capabilities 1. CTR YAML Schema Validation Validate YAML structure against schema C...
49
15044 feature-documentation dengineproblem/agents-monorepo
Feature Documentation Expert Expert in creating comprehensive, user-focused feature documentation. Core Documentation Principles Structure and Hierarchy Purpose-First Organization : Start with what the feature does and why it matters Progressive Disclosure : Layer information from overview to implementation details Multiple Entry Points : Support different user types (end-users, developers, stakeholders) Cross-Reference Integration : Link related features, dependencies, and prerequisites Content...
49
15045 qa-engineer anyproto/anytype-ts
QA Engineer Skill Analyze recent code changes in anytype-ts, map them to testable user-facing behavior, and generate Playwright E2E tests in the ../anytype-desktop-suite repository. When to Use Activate this skill when: After implementing a new feature or modifying existing functionality After editor/component changes that affect user interactions The user explicitly asks to add tests for recent changes After completing a task referenced in CLAUDE.md's "QA Engineer" section Principles Change-dri...
49
15046 jungian-psychologist erichowens/some_claude_skills
Jungian Psychologist Expert in Jungian analytical psychology, offering guidance grounded in Jung's original texts and post-Jungian developments. When to Use This Skill Use for: Shadow work exploration and exercises Dream interpretation frameworks Archetypal pattern analysis Active imagination guidance Understanding the individuation process Complex theory application Jungian concept education Addiction and recovery through depth psychology lens Visual mapping of the psyche (diagrams, mandala...
49
15047 neon-test-branches andrelandgraf/fullstackrecipes
Neon Test Branches To set up Neon Test Branches, refer to the fullstackrecipes MCP server resource: Resource URI: recipe://fullstackrecipes.com/neon-test-branches If the MCP server is not configured, fetch the recipe directly: curl -H "Accept: text/plain" https://fullstackrecipes.com/api/recipes/neon-test-branches
49
15048 slide-creator roasbeef/claude-files
This skill transforms written content into visual slide deck images using AI image generation. It analyzes text content, extracts key points, and generates presentation-quality slide images. Prerequisites - The `nano-banana` skill must be available for image generation. - Python 3.10+ - `google-genai` package installed Workflow Overview - Input: Receive content (blog post, article, newsletter, outline) - Analysis: Extract key points and structure - Outline: Create slide outline with ti...
49
15049 examples-auto-run openai/openai-agents-js
examples-auto-run What it does Runs uv run examples/run_examples.py with: EXAMPLES_INTERACTIVE_MODE=auto (auto-input/auto-approve). Per-example logs under .tmp/examples-start-logs/. Main summary log path passed via --main-log (also under .tmp/examples-start-logs/). Generates a rerun list of failures at .tmp/examples-rerun.txt when --write-rerun is set. Provides start/stop/status/logs/tail/collect/rerun helpers via run.sh. Background option keeps the process running with a pidfile; stop cleans it...
49
15050 code-review laurigates/claude-plugins
Code Review When to use this skill Reviewing pull requests Checking code quality Providing feedback on implementations Identifying potential bugs Suggesting improvements Security audits Performance analysis Instructions Step 1: Understand the context Read the PR description : What is the goal of this change? Which issues does it address? Are there any special considerations? Check the scope : How many files changed? What type of changes? (feature, bugfix, refactor) Are tests included? Step 2: Hi...
49