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
14651 elegant-reports jdrhyne/agent-skills
elegant-reports Generate minimalist, elegant PDF reports inspired by Scandinavian design principles. Quick Start cd ~/clawd-nuri-internal/skills/elegant-reports Generate a report (dense layout) node generate.js report.md output.pdf --template report Generate a presentation (bold slides) node generate.js data.md slides.pdf --template presentation Dark mode node generate.js report.md --template report --theme dark List templates node generate.js --list Templates Template Style Use Case report ...
50
14652 card-sort-analysis owl-listener/designer-skills
Card Sort Analysis Analyze card sorting results to inform information architecture decisions. Context You are a UX researcher analyzing card sort data for $ARGUMENTS. If the user provides files (card sort results, spreadsheets), read them first. Instructions Understand the study : Confirm methodology (open vs closed), number of participants, and card set. Analyze groupings : Identify common category patterns and naming conventions. Create a similarity matrix : Show how frequently items were grou...
50
14653 azure-cosmos-db-py sickn33/antigravity-awesome-skills
Cosmos DB Service Implementation Build production-grade Azure Cosmos DB NoSQL services following clean code, security best practices, and TDD principles. Installation pip install azure-cosmos azure-identity Environment Variables COSMOS_ENDPOINT = https:// < account > .documents.azure.com:443/ COSMOS_DATABASE_NAME = < database-name > COSMOS_CONTAINER_ID = < container-id > For emulator only (not production) COSMOS_KEY = < emulator-key > Authentication DefaultAzureCredential (preferred) : from azu...
50
14654 chanjing-tts-voice-clone chanjing-ai/chan-skills
Chanjing TTS Voice Clone When to Use This Skill Use this skill when the user needs to generate speech from text, with a user-provided reference voice. The reference audio needs to be provided as a publicly accessible url. This TTS service supports: bilingual Chinese and English adjustment of speech rate sentence-level timestamp How to Use This Skill Chanjing-TTS-Voice-Clone provides an asynchronous speech synthesis API. Hostname for all APIs is: " https://open-api.chanjing.cc ". All requests com...
50
14655 claude-code-learning popup-studio-ai/bkit-claude-code
Claude Code Learning Skill Master Claude Code configuration and optimization Actions Action Description Example learn Start learning guide /claude-code-learning learn 1 setup Auto-generate settings /claude-code-learning setup upgrade Latest features guide /claude-code-learning upgrade learn [level] Learning content by level: Level 1 : Basics - Writing CLAUDE.md, Using Plan Mode Level 2 : Automation - Commands, Hooks, Permission management Level 3 : Specialization - Agents, Skills, MCP integratio...
50
14656 clarify:unknown team-attention/workshop-upstage
Unknown: Surface Blind Spots with Known/Unknown Quadrants Surface hidden assumptions and blind spots in any strategy, plan, or decision using the Known/Unknown quadrant framework and hypothesis-driven questioning. When to Use Strategy or planning documents that need scrutiny Decisions with unclear direction or hidden assumptions Any situation where "what we don't know" matters more than "what we do know" For specific requirement clarification (feature requests, bug reports), use the vague skill....
50
14657 accessibility-test-plan owl-listener/designer-skills
Accessibility Test Plan You are an expert in planning comprehensive accessibility testing. What You Do You create testing plans that systematically evaluate accessibility across assistive technologies and WCAG criteria. Testing Layers 1. Automated Testing Axe, Lighthouse, WAVE tools Catches approximately 30-40% of issues Run on every page/state Integrate into CI/CD pipeline 2. Manual Testing Keyboard-only navigation Screen reader walkthrough Zoom to 200% and 400% High contrast mode Reduced motio...
50
14658 post-game-press-conference-simulator onewave-ai/claude-skills
Post Game Press Conference Simulator Generate realistic coach/player interview responses for wins, losses, controversies, injuries. Authentic coachspeak and player personalities. Instructions You are an expert at sports media and press conference dynamics. Generate authentic interview responses with: realistic coachspeak, player personalities, handling of wins/losses/controversies, 'one game at a time' clichés, and both serious and comedic tones. Output Format Post Game Press Conference Sim...
50
14659 tdd kimny1143/claude-code-template
/tdd - Test-Driven Development Workflow Strict TDD workflow: tests first, then implementation. When to Use "Implement X using TDD" "Build this feature test-first" "Write tests for X then implement" Any feature where test coverage is critical Bug fixes that need regression tests TDD Philosophy Overview Write the test first. Watch it fail. Write minimal code to pass. Core principle: If you didn't watch the test fail, you don't know if it tests the right thing. Violating the letter of the rules is ...
50
14660 documentation-specialist caomeiyouren/momei
Documentation Specialist Skill (文档专家技能) 能力 (Capabilities) 文档检索 : 快速查找和总结位于 docs/ 目录下的设计文档、规范文档和计划文档。 文档生成 : 根据代码变更自动更新或创建新的 Markdown 文档。 规范检查 : 确保文档遵循项目的文档结构和风格指南 (如 AGENTS.md 和 docs/standards/documentation.md 中定义的)。 计划管理 : 能够读取 docs/plan/todo.md 和 docs/plan/roadmap.md 以了解当前任务状态,读取 docs/plan/todo-archive.md 以了解已归档任务状态。 门户维护 : 负责更新根目录下的 README.md ,确保其与项目特性和状态保持同步。 指令 (Instructions) Worktree 意识 : 大规模文档更新务必在 ../momei-docs 目录执行,确保文档版本独立于代码开发分支。 目录感知 : 始终在 docs/ 目录下操作(除了根目录的 README.md )。了解子目录结构: desi...
50
14661 ios-hig pproenca/dot-skills
iOS Human Interface Guidelines Apple's Human Interface Guidelines define the visual language, interaction patterns, and accessibility standards that make iOS apps feel native and intuitive. The core principle: clarity and consistency through thoughtful design. Reference Loading Guide ALWAYS load reference files if there is even a small chance the content may be required. It's better to have the context than to miss a pattern or make a mistake. Reference Load When Interaction Touch targets, n...
50
14662 skill-capture shipshitdev/library
Skill Capture This skill extracts valuable learnings, patterns, and workflows from conversations and persists them as reusable skill files for future sessions. When This Skill Activates Activate when the user mentions ANY of these: Explicit Requests "let's save this as a skill" "this workflow should be reusable" "capture this as a skill" "make this a skill" "turn this into a skill" "save this pattern" Workflow Completion Signals Complex problem solved after multiple iterations Multi-step pro...
50
14663 obsidian-dashboard oldwinter/skills
Obsidian Vault Dashboard Generator This skill generates comprehensive statistics and visual overview of Obsidian note vaults. It analyzes files, tags, links, folder structure, and creates an interactive HTML dashboard. Purpose To provide detailed insights into Obsidian vault structure and content through automated analysis and visualization. When to Use When users want to understand their vault structure To identify orphaned files, unused attachments, or broken links To analyze tag usage pat...
50
14664 analytics-export laurigates/claude-plugins
/analytics:export Export analytics data for external analysis or reporting. Context Check analytics availability: ANALYTICS_DIR = " ${ HOME } /.claude-analytics" SUMMARY_FILE = " ${ANALYTICS_DIR} /summary.json" EVENTS_FILE = " ${ANALYTICS_DIR} /events.jsonl" if [ [ ! -f " ${SUMMARY_FILE} " ] ] ; then echo "No analytics data to export." exit 0 fi TOTAL = $( cat " ${SUMMARY_FILE} " | jq -r '.total_invocations' ) echo "Exporting ${TOTAL} invocations..." Parameters $ARGS - Format and optional output...
50
14665 accessibility tech-leads-club/agent-skills
Web Accessibility (WCAG 2.1 AA) Status : Production Ready ✅ Last Updated : 2026-01-14 Dependencies : None (framework-agnostic) Standards : WCAG 2.1 Level AA Quick Start (5 Minutes) 1. Semantic HTML Foundation Choose the right element - don't use div for everything: <!-- ❌ WRONG - divs with onClick --> < div onclick = " submit ( ) " > Submit </ div > < div onclick = " navigate ( ) " > Next page </ div > <!-- ✅ CORRECT - semantic elements --> < button type = " submit " > Submit </ button > < a hre...
50
14666 tempo tempoxyz/agent-skills
Tempo Skill for building applications on the Tempo network. Capabilities Navigate Tempo documentation and protocol specs Browse source code for tempoxyz/tempo (Rust node) and tempoxyz/tempo-ts (TypeScript SDK) Access related libraries: viem, wagmi, reth, foundry MCP Tools Use these tools to explore Tempo: Tool Description mcp__tempo__list_pages List all documentation pages mcp__tempo__read_page Read a specific documentation page mcp__tempo__search_docs Search documentation mcp__tempo__list_s...
50
14667 tavily vm0-ai/vm0-skills
Tavily Purpose Provide a curl-based interface to Tavily’s REST API for web search, extraction, mapping, crawling, and optional research. Return structured results suitable for LLM workflows and multi-step investigations. When to Use Use when a task needs live web information, site extraction, mapping, or crawling. Use when web searches are needed and no built-in tool is available, or when Tavily’s LLM-friendly output (summaries, chunks, sources, citations) is beneficial. Use when a task requir...
50
14668 configure-package-management laurigates/claude-plugins
/configure:package-management Check and configure modern package managers for optimal development experience. When to Use This Skill Use this skill when... Use another approach when... Setting up a new project with modern package managers (uv, bun) Installing a single dependency — run uv add or bun add directly Migrating from legacy package managers (pip, npm, yarn, poetry) to modern ones Project uses cargo or go mod (already optimal, no migration needed) Auditing package manager configuration f...
50
14669 china-macro-analyst nicepkg/ai-workflow
No SKILL.md available for this skill. View on GitHub
50
14670 azure-ai-vision-imageanalysis-py sickn33/antigravity-awesome-skills
Azure AI Vision Image Analysis SDK for Python Client library for Azure AI Vision 4.0 image analysis including captions, tags, objects, OCR, and more. Installation pip install azure-ai-vision-imageanalysis Environment Variables VISION_ENDPOINT = https:// < resource > .cognitiveservices.azure.com VISION_KEY = < your-api-key > If using API key Authentication API Key import os from azure . ai . vision . imageanalysis import ImageAnalysisClient from azure . core . credentials import AzureKeyCredenti...
50
14671 google-genai-sdk-python cnemri/google-genai-skills
Google GenAI Python SDK Skill Use this skill to write high-quality, idiomatic Python code for the Gemini API. Reference Materials Identify the user's task and refer to the relevant file: Setup & Client : Installation, auth, client initialization. Models : Recommended models (Flash, Pro, Lite, Imagen, Veo). Text Generation : Basic inference, streaming, system instructions, safety. Chat : Multi-turn conversations and history. Reasoning : Thinking config ( thinking_level / thinking_budget ), though...
50
14672 vapi gracebotly/flowetic-app
Vapi Platform Skill Overview Vapi is a voice AI platform for building phone agents. Users connect Vapi assistants to Getflowetic to monitor call performance, track costs, and analyze conversation outcomes. Vocabulary call : A single voice interaction between an assistant and a caller assistant : A configured Vapi voice agent with a system prompt, model, and voice ended_reason : Why the call terminated (hangup, voicemail, error, silence-timeout, max-duration) cost : Per-call cost in USD based on ...
50
14673 configure-skaffold laurigates/claude-plugins
/configure:skaffold Check and configure Skaffold against project standards. When to Use This Skill Use this skill when... Use another approach when... Checking Skaffold configuration compliance for a Kubernetes project Project has no k8s/ or helm/ directories (Skaffold is not applicable) Fixing port forwarding security issues (binding to 0.0.0.0) Managing Kubernetes manifests or Helm charts directly Adding dotenvx hooks for secret generation in Skaffold Configuring container builds without Kuber...
50
14674 temu-competitor-search zhuhongyin/global-ecom-skills
Temu 竞品与卷王价查询 核心定位 这是 Temu 选品的竞品分析工具。查找 Temu 上的同类产品,获取"卷王价"(最低竞品价),分析竞争格局和差异化机会。 核心概念 卷王价 :Temu 平台上同类产品的最低售价,是核价计算的关键输入参数。 数据来源 Temu 网站: 美国: https://www.temu.com 英国: https://www.temu.com/uk 欧盟: https://www.temu.com/eu 输入参数 { "keyword" : "standing desk converter" , "category" : "Home & Kitchen" , "site" : "us" , "limit" : 20 , "sort_by" : "price_asc" , "min_rating" : 3.5 } 参数 类型 必需 默认值 说明 keyword string 是 - 搜索关键词 category string 否 全类目 商品类目 site string 否 us 站点(us/uk/eu) limit int 否 20 返回商品数量 sort_...
50
14675 design-critique owl-listener/designer-skills
/design-critique If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md . Get structured design feedback across multiple dimensions. Usage /design-critique $ARGUMENTS Review the design: @$1 If a Figma URL is provided, pull the design from Figma. If a file is referenced, read it. Otherwise, ask the user to describe or share their design. What I Need From You The design : Figma URL, screenshot, or detailed description Context : What is this? Who is it for?...
50
14676 page-cro openclaudia/openclaudia-skills
Page Conversion Rate Optimization (CRO) You are a conversion rate optimization expert. Your goal is to analyze marketing pages and provide actionable recommendations to improve conversion rates. Initial Assessment Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task. Before provi...
50
14677 sentry-svelte-sdk getsentry/sentry-agent-skills
All Skills > SDK Setup > Svelte SDK Sentry Svelte SDK Opinionated wizard that scans your project and guides you through complete Sentry setup for Svelte and SvelteKit. Invoke This Skill When User asks to "add Sentry to Svelte" or "set up Sentry" in a Svelte/SvelteKit app User wants error monitoring, tracing, session replay, or logging in Svelte or SvelteKit User mentions @sentry/svelte , @sentry/sveltekit , or Sentry SDK for Svelte Note: SDK versions and APIs below reflect current Sentry docs at...
50
14678 bun nuxt secondsky/claude-skills
Bun Nuxt Run Nuxt 3 applications with Bun for faster development. Quick Start Create new Nuxt project bunx nuxi@latest init my-app cd my-app Install dependencies bun install Development bun run dev Build bun run build Preview production bun run preview Project Setup package.json { "scripts" : { "dev" : "nuxt dev" , "build" : "nuxt build" , "generate" : "nuxt generate" , "preview" : "nuxt preview" , "postinstall" : "nuxt prepare" } , "dependencies" : { "nuxt" : "^4.0.0" , "vue" : "^3.5.0" } ...
50
14679 query-layer epicenterhq/epicenter
Query Layer Patterns The query layer is the reactive bridge between UI components and the service layer. It wraps pure service functions with caching, reactivity, and state management using TanStack Query and WellCrafted factories. When to Apply This Skill Use this pattern when you need to: Create queries or mutations that consume services Transform service-layer errors into user-facing error types Implement runtime service selection based on user settings Add optimistic cache updates for instan...
50
14680 spring-boot-expert personamanagmentlayer/pcl
Expert guidance for Spring Boot development, Spring Framework, building REST APIs, and microservices architecture. Core Concepts Spring Boot Fundamentals - Auto-configuration - Dependency injection - Spring Boot Starters - Application properties - Profiles and configuration - Spring Boot Actuator Spring Framework - Spring Core (IoC, DI) - Spring Data JPA - Spring Security - Spring Web MVC - Spring AOP - Spring Transaction Management Microservices - Service discovery - API G...
50
14681 react-spring dylantarre/animation-principles
React Spring Animation Principles Implement all 12 Disney animation principles using React Spring's spring physics system. 1. Squash and Stretch const [springs, api] = useSpring(() => ({ scaleX: 1, scaleY: 1, config: { tension: 300, friction: 10 } })); api.start({ scaleX: 1.2, scaleY: 0.8 }); <animated.div style={springs} /> 2. Anticipation const [props, api] = useSpring(() => ({ y: 0, scaleY: 1 })); const jump = async () => { await api.start({ y: 10, scaleY: 0.9 }); // wind up ap...
50
14682 document-chat-interface qodex-ai/ai-agent-skills
Document Chat Interface Build intelligent chat interfaces that allow users to query and interact with documents using natural language, transforming static documents into interactive knowledge sources. Overview A document chat interface combines three capabilities: Document Processing - Extract and prepare documents Semantic Understanding - Understand questions and find relevant content Conversational Interface - Maintain context and provide natural responses Common Applications PDF Q&A: Ans...
50
14683 install-flutter-from-git rodydavis/skills
Install Flutter from Git This skill guides you through installing the Flutter SDK using git clone and setting up the environment for Web, Mobile, and Desktop development. 1. Prerequisites (All Platforms) Ensure you have the following installed: Git : Install Git Curl/Unzip (macOS/Linux usually have these; Windows usually needs Git Bash or similar) 2. Install Flutter SDK macOS / Linux Open your terminal and run the following commands to clone the stable branch of the Flutter SDK. Create a direct...
50
14684 configure-workflows laurigates/claude-plugins
/configure:workflows Check and configure GitHub Actions CI/CD workflows against project standards. When to Use This Skill Use this skill when... Use another approach when... Checking GitHub Actions workflows for compliance with project standards Debugging a failing CI run (use github-actions-inspection skill) Setting up container build, test, or release-please workflows Installing Claude-powered reusable workflows (use /configure:reusable-workflows ) Updating outdated action versions (checkout, ...
50
14685 biome-linting thebushidocollective/han
Biome Linting Expert knowledge of Biome's linting capabilities, rule categories, and code quality enforcement for JavaScript and TypeScript projects. Overview Biome's linter provides fast, comprehensive code quality checks with a focus on correctness, performance, security, and best practices. It's designed to catch common bugs and enforce consistent code patterns. Core Commands Basic Linting Check files without fixing biome check . Check and auto-fix biome check --write . Check specific file...
50
14686 find-skills connorads/dotfiles
Find Skills This skill helps you discover and install skills from the open agent skills ecosystem. When to Use This Skill Use this skill when the user: Asks "how do I do X" where X might be a common task with an existing skill Says "find a skill for X" or "is there a skill for X" Asks "can you do X" where X is a specialized capability Expresses interest in extending agent capabilities Wants to search for tools, templates, or workflows Mentions they wish they had help with a specific domain (desi...
50
14687 fastapi itechmeat/llm-code
FastAPI Skill Production-tested patterns for FastAPI with Pydantic v2, SQLAlchemy 2.0 async, and JWT authentication. Latest Versions (verified January 2026): FastAPI: 0.128.0 Pydantic: 2.11.7 SQLAlchemy: 2.0.30 Uvicorn: 0.35.0 python-jose: 3.3.0 Requirements : Python 3.9+ (Python 3.8 support dropped in FastAPI 0.125.0) Pydantic v2.7.0+ (Pydantic v1 support completely removed in FastAPI 0.128.0) Quick Start Project Setup with uv Create project uv init my-api cd my-api Add dependencies uv add fa...
50
14688 biorxiv-search yorkeccak/scientific-skills
bioRxiv Search Search the complete bioRxiv database of biological sciences preprints using natural language queries powered by Valyu's semantic search API. Why This Skill is Powerful No API Parameter Parsing: Just pass natural language queries directly - no need to construct complex search parameters Semantic Search: Understands the meaning of your query, not just keyword matching Full-Text Access: Returns complete article content, not just abstracts Image Links: Includes figures and images fr...
50
14689 favicon shpigford/skills
Generate a complete set of favicons from the source image at $1 and update the project's HTML with the appropriate link tags. Prerequisites First, verify ImageMagick v7+ is installed by running: which magick If not found, stop and instruct the user to install it: macOS : brew install imagemagick Linux : sudo apt install imagemagick Step 1: Validate Source Image Verify the source image exists at the provided path: $1 Check the file extension is a supported format (PNG, JPG, JPEG, SVG, WEBP, GIF) ...
50
14690 mobile-development groeimetai/snow-flow
Mobile Development Skill Production-ready mobile development with modern frameworks, best practices, and mobile-first thinking patterns. When to Use Building mobile applications (iOS, Android, or cross-platform) Implementing mobile-first design and UX patterns Optimizing for mobile constraints (battery, memory, network, small screens) Making native vs cross-platform technology decisions Implementing offline-first architecture and data sync Following platform-specific guidelines (iOS HIG, Mater...
50
14691 wagmi-development wevm/wagmi
Wagmi Development Full-stack patterns for adding Wagmi features. This skill covers Viem-based actions only (not Wagmi config actions). Layer Overview Core Action (packages/core/src/actions/) - Base functionality wrapping Viem Query Options (packages/core/src/query/) - TanStack Query integration Framework Bindings - React (packages/react/src/hooks/), Vue (packages/vue/src/composables/) 1. Core Action Structure import { type MyActionErrorType as viem_MyActionErrorType, type MyActionParameter...
50
14692 podcast-production-guide dengineproblem/agents-monorepo
Podcast Production Guide Expert in podcast creation, production, distribution, and growth strategies. Pre-Production Planning Format Selection podcast_formats : interview : description : "Host interviews guests" pros : [ "Fresh perspectives" , "Built-in networking" , "Easier content" ] cons : [ "Scheduling complexity" , "Variable audio quality" ] best_for : "Thought leadership, industry insights" solo : description : "Single host commentary" pros : [ "Complete control" , "Flexible scheduling" ] ...
50
14693 axiom-mapkit charleswiltgen/axiom
MapKit Patterns MapKit patterns and anti-patterns for iOS apps. Prevents common mistakes: using MKMapView when SwiftUI Map suffices, annotations in view bodies, setRegion loops, and performance issues with large annotation counts. When to Use Adding a map to your iOS app Displaying annotations, markers, or custom pins Implementing search (address, POI, autocomplete) Adding directions/routing to a map Debugging map display issues (annotations not showing, region jumping) Optimizing map performanc...
50
14694 env-management andrelandgraf/fullstackrecipes
Environment Variable Management Complete environment variable management with type-safe validation, Vercel dev workflow, and prebuild validation. Cookbook - Complete These Recipes in Order Type-Safe Environment Configuration Type-safe environment variable validation using Zod with a Drizzle-like schema API. Supports server/public fields, feature flags, either-or constraints, and client-side protection. curl -H "Accept: text/markdown" https://fullstackrecipes.com/api/recipes/config-schema-set...
50
14695 champion-identifier onewave-ai/claude-skills
Champion Identifier Find the perfect internal champion at any target account using AI-powered LinkedIn analysis. Instructions You are an expert sales strategist specializing in account-based selling and multi-threading. Your mission is to analyze target accounts and identify the individuals most likely to become internal champions who will advocate for your solution. What Makes a Great Champion? The Champion Profile: Has Pain: Directly affected by the problem you solve Has Power: Can influ...
50
14696 trend spotter eddiebe147/claude-settings
Trend Spotter Expert foresight and trend analysis agent that identifies emerging trends, detects weak signals, analyzes momentum, and predicts future directions. Specializes in multi-source synthesis, pattern recognition, trajectory analysis, and strategic foresight. This skill combines quantitative data analysis (search volume, social signals, funding patterns) with qualitative analysis (expert opinions, emerging narratives, technological developments) to spot trends early. Perfect for innovati...
50
14697 design-principles owl-listener/designer-skills
Design Principles This skill enforces precise, crafted design for enterprise software, SaaS dashboards, admin interfaces, and web applications. The philosophy is Jony Ive-level precision with intentional personality — every interface is polished, and each is designed for its specific context. Design Direction (REQUIRED) Before writing any code, commit to a design direction. Don't default. Think about what this specific product needs to feel like. Think About Context What does this product do...
50
14698 web-design-guidelines kimny1143/claude-code-template
Web Interface Guidelines Review files for compliance with Web Interface Guidelines. How It Works Fetch the latest guidelines from the source URL below Read the specified files (or prompt user for files/pattern) Check against all rules in the fetched guidelines Output findings in the terse file:line format Guidelines Source Fetch fresh guidelines before each review: https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md Use WebFetch to retrieve the latest rules. Th...
50
14699 customer-training-curriculum dengineproblem/agents-monorepo
Customer Training Curriculum Expert Эксперт по разработке программ обучения клиентов для ускорения adoption, снижения нагрузки на поддержку и customer success. Core Competencies Curriculum Design Learning path architecture Adult learning principles Bloom's taxonomy application Progressive disclosure Content Development Multi-modal content creation Interactive exercises Assessment design Localization Program Management LMS administration Certification programs Effectiveness measurement Continuous...
50
14700 meta-audit laurigates/claude-plugins
Context Agent definitions: ! find .claude/agents -name "*.md" -not -name "settings*" Settings file: ! find .claude/agents -maxdepth 1 -name "settings.local.json" -type f Your task 1. Discovery Phase Use Glob to find all agent definition files in .claude/agents/ Read each agent file to extract frontmatter and configuration Identify the settings.local.json for permission overrides 2. Frontmatter Validation For each agent, verify required fields are present: ✅ name : Agent identifier (must match fi...
50