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...
23,097
总 Skills
59.4M
总安装量
2,536
贡献者
# Skill 仓库 描述 安装量
18351 astro-developer withastro/astro
Astro Developer Skill Context-loading skill for AI agents and developers working in the Astro monorepo. Loads relevant documentation based on your task. Quick Decision Matrix What are you doing? → Read these files: Task Primary Docs Supporting Docs Adding a core feature architecture.md , constraints.md testing.md Fixing a bug debugging.md architecture.md Writing/fixing tests testing.md constraints.md Creating an integration Explore packages/integrations/ for examples testing.md Understanding arc...
 49
18352 entity extractor eddiebe147/claude-settings
Entity Extractor The Entity Extractor skill guides you through implementing named entity recognition (NER) systems that identify and classify entities in text. From people and organizations to domain-specific entities like products, medical terms, or financial instruments, this skill covers extraction approaches from simple pattern matching to advanced neural models. Entity extraction is a foundational NLP task that powers applications from search engines to knowledge graphs. Getting it right re...
 49
18353 jira-syntax netresearch/jira-skill
Jira Syntax Validation Skill Provides Jira wiki markup syntax validation, templates, and formatting guidance. For API operations, use the jira-communication skill. Quick Syntax Reference Jira Syntax Purpose NOT this (Markdown) h2. Title Heading Title *bold* Bold bold _italic_ Italic *italic* {{code}} Inline code `code` {code:java}...{code} Code block java ``` [text|url] Link [text](url) [PROJ-123] Issue link - [~username] User mention @username * item Bullet list - item item Numbered list 1. i...
 49
18354 clean catlog22/claude-code-workflow
Workflow Clean Command Overview Evidence-based intelligent cleanup command. Systematically identifies stale artifacts through mainline analysis, discovers drift, and safely removes unused sessions, documents, and dead code. Core workflow : Detect Mainline → Discover Drift → Confirm → Stage → Execute Target Cleanup Focus area : $FOCUS (or entire project if not specified) Mode : $ARGUMENTS --dry-run : Preview cleanup without executing --focus : Focus area (module or path) Execution Process Phase 0...
 49
18355 simplify aaddrick/claude-desktop-debian
You are an expert code simplification specialist focused on enhancing code clarity, consistency, and maintainability while preserving exact functionality. Your expertise lies in applying project-specific best practices to simplify and improve code without altering its behavior. You prioritize readable, explicit code over overly compact solutions. This is a balance that you have mastered as a result your years as an expert software engineer. You will analyze recently modified code and apply refi...
 49
18356 lit-best-practices artmsilva/lit-best-practices
Lit Web Components Best Practices Best practices for building Lit web components, optimized for AI-assisted code generation and review. When to Use Reference these guidelines when: Writing new Lit web components Implementing reactive properties and state Reviewing code for performance or accessibility issues Refactoring existing Lit components Optimizing rendering and update cycles Rule Categories Category Rules Focus 1. Component Structure 4 rules Properties, state, TypeScript 2. Rendering ...
 49
18357 simple-math cisco-ai-defense/skill-scanner
Simple Math Skill Performs basic arithmetic operations safely. Features Addition, subtraction, multiplication, division No eval() or exec() Input validation Safe implementation Usage When user requests calculations, use standard Python operators. Example User: "What's 25 + 17?" Agent: uses simple-math skill The result is 42.
 49
18358 linear-update finesssee/linear-cli
Update Issues Status linear-cli i update LIN-123 -s Done linear-cli i update LIN-123 -s "In Progress" Priority linear-cli i update LIN-123 -p 1 1=urgent, 2=high, 3=normal, 4=low Assignee linear-cli i update LIN-123 -a me linear-cli i update LIN-123 -a "John Doe" Labels linear-cli i update LIN-123 -l bug linear-cli i update LIN-123 -l bug -l urgent Due date linear-cli i update LIN-123 --due tomorrow linear-cli i update LIN-123 --due +3d Agent patterns linear-cli i update LIN-123 -s Done --...
 49
18359 mcp-server-manager xiaolai/vmark
MCP Server Manager Workflow Discover candidate servers Check project .mcp.json for existing server configs. Check ~/.claude.json for global MCP servers (Claude Code). Scan for MCP-related packages in package.json or Cargo.toml . Choose a registration target Project-local: edit .mcp.json directly. Global (Claude Code): use claude mcp add / claude mcp remove . Register the server stdio server: claude mcp add < name > -- < command > < args .. . > stdio with env: claude mcp add < name > -e KEY = VAL...
 49
18360 rspack-tracing rstackjs/agent-skills
Use this skill when you need to: - Diagnose why an Rspack build is slow. - Understand which plugins or loaders are taking the most time. - Analyze a user-provided Rspack trace file. - Guide a user to capture a performance profile. Workflow 1. Capture a Trace First, ask the user to run their build with tracing enabled. ``` Set environment variables for logging to a file RSPACK_PROFILE=TRACE RSPACK_TRACE_LAYER=logger RSPACK_TRACE_OUTPUT=./trace.json pnpm build ``` This will generate a...
 49
18361 run-rust-benchmarks redisearch/redisearch
No SKILL.md available for this skill. View on GitHub
 49
18362 social-media-api-best-practices getlate-dev/social-media-api-best-practices
Social Media API Best Practices Battle-tested patterns from scheduling 1M+ posts across 13 platforms. 1. Authentication Patterns OAuth 2.0 Platforms Instagram (Meta Graph API) Two-step token exchange: short-lived (1 hour) → long-lived (60 days) Use auth_type: 'rerequest' to force permission re-prompts Exchange endpoint: ig_exchange_token grant type Scopes: instagram_business_basic, instagram_business_content_publish, instagram_business_manage_messages, instagram_business_manage_comments, ins...
 49
18363 git-worktree kimny1143/claude-code-template
This skill provides a unified interface for managing Git worktrees across your development workflow. Whether you're reviewing PRs in isolation or working on features in parallel, this skill handles all the complexity. What This Skill Does - Create worktrees from main branch with clear branch names - List worktrees with current status - Switch between worktrees for parallel work - Clean up completed worktrees automatically - Interactive confirmations at each step - Automatic .gitignore ma...
 49
18364 pptx bbeierle12/skill-mcp-claude
PPTX Skill Quick Reference Task Guide Read/analyze content python -m markitdown presentation.pptx Edit or create from template Read editing.md Create from scratch Read pptxgenjs.md Reading Content Text extraction python -m markitdown presentation.pptx Visual overview python scripts/thumbnail.py presentation.pptx Raw XML python scripts/office/unpack.py presentation.pptx unpacked/ Editing Workflow Read editing.md for full details. Analyze template with thumbnail.py Unpack → manipulate slides → ...
 49
18365 seo-audit openclaudia/openclaudia-skills
SEO Audit You are an expert in search engine optimization. Your goal is to identify SEO issues and provide actionable recommendations to improve organic search performance. 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 auditing, understand: Site ...
 49
18366 review-scoring mgd34msu/goodvibes-plugin
Resources scripts/ validate-review.sh validate-fix.sh references/ scoring-examples.md Review Scoring Protocol This skill defines the precise scoring rubric and review format used in Work-Review-Fix-Check (WRFC) loops. It ensures consistent, quantified evaluation of code quality and provides deterministic validation of review outputs. Scoring Rubric (1-10 Scale) Every review evaluates code across 10 dimensions. Each dimension receives a score from 1 to 10, where: 1-3 : Critical deficiencies, fund...
 49
18367 coding-rules kimny1143/claude-code-template
coding-rules - コーディング規約 プロジェクト共通のコーディングルール。 1. TypeScript 型定義 // ✅ 明示的な型定義 interface User { id : string ; email : string ; name : string ; createdAt : Date ; } // ✅ 型推論が明確な場合は省略OK const users = await repository . findAll ( ) ; // 戻り値の型は関数から推論 // ❌ any は使わない const data : any = response . json ( ) ; // ✅ unknown を使って安全に処理 const data : unknown = await response . json ( ) ; if ( isUser ( data ) ) { console . log ( data . email ) ; } Null/Undefined // ✅ Optional chaining const email = user ?. profile...
 49
18368 anti-ai-writing cdeistopened/skill-stack
Anti-AI Writing Engine Transform any content into authentic, human-sounding prose by eliminating AI patterns and applying proven writing fundamentals. Purpose This skill serves as the core humanization engine for all written content. It detects and eliminates patterns that signal AI involvement while teaching the principles of natural, engaging writing. Core Philosophy: The best writing is invisible. Readers should feel like they're reading a real person's thoughts - not processed, filtered, or ...
 49
18369 slot-teams cartridge-gg/docs
Slot Teams Teams are the billing entity in Slot. They own credits used to pay for deployments, paymasters, RPC requests, and other services. Credit System Prepaid credits, deducted automatically 1 CREDIT = $0.01 USD Daily billing cycle (minimum 1-day charge) Fund via credit card or cryptocurrency Creating a Team slot teams < team-name > create --email < email > [ --address "address" ] [ --tax-id "id" ] A team is also auto-created when you create a deployment with a new project name. Funding slot...
 49
18370 blog-post-writer nicknisi/claude-plugins
Nick Nisi Blog Writer Transform unstructured brain dumps into polished blog posts that sound like Nick Nisi. Process 1. Receive the Brain Dump Accept whatever the user provides: Scattered thoughts and ideas Technical points to cover Code examples or commands Conclusions or takeaways Links to reference Random observations Don't require organization. The mess is the input. Clarify constraints (if not provided, ask about): Target length (see references/post-template.md for word count ranges) Target...
 49
18371 authentication mgd34msu/goodvibes-plugin
Authentication Implement authentication flows on iOS using the AuthenticationServices framework, including Sign in with Apple, OAuth/third-party web auth, Password AutoFill, and biometric authentication. Contents Sign in with Apple Credential Handling Credential State Checking Token Validation Existing Account Setup Flows ASWebAuthenticationSession (OAuth) Password AutoFill Credentials Biometric Authentication SwiftUI SignInWithAppleButton Common Mistakes Review Checklist References Sign in with...
 49
18372 react-doctor posthog/posthog
React Doctor Scans your React codebase for security, performance, correctness, and architecture issues. Outputs a 0-100 score with actionable diagnostics. Usage npx -y react-doctor@latest . --verbose --diff Workflow Run after making changes to catch issues early. Fix errors first, then re-run to verify the score improved.
 49
18373 tmux-status-debug edmundmiller/dotfiles
Debugging tmux-opencode-integrated Status Detection When to Use Status icons showing wrong state (e.g., showing ERROR when agent is IDLE) Adding new patterns for agent detection Testing pattern matching against real pane content Quick Commands List all agent panes tmux list-panes -a -F "{session_name}:{window_name}.{pane_index} {pane_current_command}" | grep -E "opencode|claude|amp" Capture pane content (raw) tmux capture-pane -t "main:1" -p -S -30 | tail -40 Capture with control chars visible t...
 49
18374 atlassian-admin borghei/claude-skills
Atlassian Administrator Expert System administrator with deep expertise in Atlassian Cloud/Data Center management, user provisioning, security, integrations, and org-wide configuration and governance. Core Competencies User & Access Management Provision and deprovision users across Atlassian products Manage groups and group memberships Configure SSO/SAML authentication Implement role-based access control (RBAC) Audit user access and permissions Product Administration Configure Jira global settin...
 49
18375 scoped-apps groeimetai/snow-flow
Scoped applications provide isolation and portability for custom development in ServiceNow. Why Use Scoped Apps? | Naming conflicts | Possible | Prevented (x_prefix) | Portability | Difficult | Easy (Update Sets) | Security | Open | Controlled (Cross-scope) | Store publishing | No | Yes | Dependencies | Implicit | Explicit Creating a Scoped Application Via Studio (Recommended) ``` 1. Navigate: System Applications > Studio 2. Click: Create Application 3. Enter: - Nam...
 49
18376 pinocchio-development sendaifun/skills
Pinocchio Development Guide Build blazing-fast Solana programs with Pinocchio - a zero-dependency, zero-copy framework that delivers 88-95% compute unit reduction and 40% smaller binaries compared to traditional approaches. Overview Pinocchio is Anza's minimalist Rust library for writing Solana programs without the heavyweight solana-program crate. It treats incoming transaction data as a single byte slice, reading it in-place via zero-copy techniques. Performance Comparison Metric Anchor Native...
 49
18377 github-copilot vm0-ai/vm0-skills
GitHub Copilot API Use the GitHub Copilot REST API via direct curl calls to manage Copilot subscriptions and retrieve usage metrics for your organization. Official docs: https://docs.github.com/en/rest/copilot Note: This API is for managing Copilot subscriptions and viewing metrics, not for code generation. When to Use Use this skill when you need to: Manage Copilot seat assignments (add/remove users and teams) View Copilot billing information for an organization Retrieve usage metrics (ac...
 49
18378 ljg-xray-book lijigang/ljg-skill-xray-book
LJG-Xray-Book: 深度拆书机 你是 Structure_Miner (结构矿工) ，一位深谙认知科学的知识提取专家。 核心哲学：Epiplexity 原理 来自论文《From Entropy to Epiplexity》的核心洞见： +------------------------------------------------------------------+ | 传统观点：信息是数据的固有属性 | | Epiplexity：信息是相对的，取决于观察者的"认知算力" | +------------------------------------------------------------------+ | | | 同一本书 = 可学习的结构(S) + 不可学习的噪声(N) | | ...
 49
18379 shader-sdf bbeierle12/skill-mcp-claude
Shader SDFs Signed Distance Functions return the distance from a point to a shape's surface. Negative = inside, positive = outside, zero = on surface. Quick Start // 2D circle SDF float sdCircle(vec2 p, float r) { return length(p) - r; } // Usage float d = sdCircle(uv - 0.5, 0.3); // Render vec3 color = d < 0.0 ? vec3(1.0) : vec3(0.0); // Hard edge vec3 color = vec3(smoothstep(0.01, 0.0, d)); // Soft edge vec3 color = vec3(smoothstep(0.02, 0.0, abs(d))); // Outli...
 49
18380 instagram-automation davepoon/buildwithclaude
Instagram Automation via Rube MCP Automate Instagram operations through Composio's Instagram toolkit via Rube MCP. Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Instagram connection via RUBE_MANAGE_CONNECTIONS with toolkit instagram Always call RUBE_SEARCH_TOOLS first to get current tool schemas Instagram Business or Creator account required (personal accounts not supported) Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuratio...
 49
18381 weather-skill google/adk-python
Weather Skill Provides current weather and forecasts for any location using two free APIs: Nominatim (OpenStreetMap) for geocoding locations → scripts/geocode.py Open-Meteo for weather data → scripts/fetch_weather.py Workflow Understand the user's request. Extract the location, time range, and whether they're planning travel. See examples below. Geocode the location by running scripts/geocode.py "<location>" . It returns JSON with display_name , lat , lon , and an ambiguous flag. If ambiguous, a...
 49
18382 game-system-designer api/git
No SKILL.md available for this skill. View on GitHub
 49
18383 nixos-best-practices lihaoze123/my-skills
Configure NixOS systems with flakes, manage overlays properly, and structure configurations for maintainability. Core Principle Understand the interaction between NixOS system configuration and Home Manager overlays. When `useGlobalPkgs = true`, overlays must be defined at the NixOS configuration level, not in Home Manager configuration files. When to Use - Configuring NixOS with flakes and Home Manager - Adding overlays that don't seem to apply - Using `useGlobalPkgs = true` with custo...
 49
18384 do cexll/myclaude
Do Plan You are an ORCHESTRATOR. Deploy subagents to execute all work. Do not do the work yourself except to coordinate, route context, and verify that each subagent completed its assigned checklist. Execution Protocol Rules Each phase uses fresh subagents where noted (or when context is large/unclear) Assign one clear objective per subagent and require evidence (commands run, outputs, files changed) Do not advance to the next step until the assigned subagent reports completion and the orchestra...
 49
18385 finops-caches laurigates/claude-plugins
/finops:caches Analyze GitHub Actions cache usage - size breakdown, cache key patterns, branch distribution, and stale cache detection. Context Current repo: ! gh repo view --json nameWithOwner --jq '.nameWithOwner' Repo owner: ! gh repo view --json owner --jq '.owner.login' Parameters Parameter Description Default repo Repository in owner/name format Current repository org:orgname Analyze org-wide cache usage - Execution bash " ${SKILL_DIR} /scripts/cache-analysis.sh" $ARGS Output Format === Ca...
 49
18386 marketing-email-automation vasilyu1983/ai-agents-public
Built as a no-fluff execution skill for email marketing automation across B2B and B2C. Structure: Core workflows and segmentation in SKILL.md. Platform setup in `references/`. Revenue economics in `references/email-economics.md`. Templates in `assets/`. Modern Best Practices (January 2026) 2026 Email Landscape | SPF/DKIM/DMARC mandatory | Non-authenticated mail blocked | Audit quarterly, not just at setup | BIMI adoption | 38% higher opens, 120% brand recall | Implement verified logo...
 49
18387 influencer finder eddiebe147/claude-settings
Influencer Finder Discover and evaluate influencers who can authentically represent your brand to their engaged audiences. This skill helps you identify the right creators, assess their fit, evaluate their metrics, and structure partnerships that deliver results. Influencer marketing works when you find the right match. This skill provides frameworks for influencer discovery, audience alignment analysis, engagement rate calculation, and partnership structure. Move beyond follower counts to find ...
 49
18388 tailwind-refactor pproenca/dot-skills
Community Tailwind CSS Refactoring Best Practices Comprehensive code quality refactoring guide for Tailwind CSS applications targeting v4. Contains 50 rules across 8 categories, prioritized by migration urgency. Every transformation preserves the existing look and feel — this skill is purely about cleaner code, modern syntax, and v4 compatibility. Companion skills: Use tailwind-ui-refactor for visual design improvements and tailwind-responsive-ui for responsive layout patterns. When to Apply Bef...
 49
18389 cybersecurity omer-metin/skills-for-antigravity
Cybersecurity Identity You're a security engineer who has protected systems handling millions of users and billions in transactions. You've responded to breaches, conducted penetration tests, and built security programs from the ground up. You understand that security is about risk management, not elimination—and you know how to communicate risk to stakeholders. You've seen every OWASP Top 10 vulnerability in the wild and know how to prevent them. You believe in automation, defense in depth, an...
 49
18390 pattern-dev commontoolsinc/labs
Use Skill("ct") for ct CLI documentation when running commands. You and the user are a team finding the efficient path to their vision. Always Plan First Use EnterPlanMode before building. Scale the plan to the task: Simple pattern (todo list, counter): One file, types + handlers + UI together Minimal clarification needed Plan in 2-3 sentences Medium pattern (form with validation, data viewer): Maybe split schemas if types get complex Clarify data shape and key actions Plan in a short list Compl...
 49
18391 writing-python julianobarbosa/claude-code-skills
$ npx skills add https://github.com/julianobarbosa/claude-code-skills --skill writing-python<div
 49
18392 financial reporter eddiebe147/claude-settings
Financial Reporter Generate comprehensive financial reports that tell the story of your business. From P&L statements to cash flow analysis, create reports that inform decisions. Core Workflows Workflow 1: P&L Statement Revenue Collection - Gather all revenue streams Expense Categorization - Organize costs by category Gross Margin - Calculate gross profit Operating Expenses - Deduct operating costs Net Income - Calculate bottom line Variance Analysis - Compare to budget/prior period Workflow 2: ...
 49
18393 pattern-schema commontoolsinc/labs
Use Skill("ct") for ct CLI documentation when running commands. Schema Design Phase Goal Create schemas.tsx with all data types and Input/Output types BEFORE any pattern code. Read First docs/common/concepts/types-and-schemas/default.md docs/common/concepts/types-and-schemas/writable.md docs/common/concepts/pattern.md (Input/Output section) Rules ALWAYS use pattern<Input, Output>() - Never use single-type pattern<State>() . Single-type patterns cannot be tested via .send() . Every editable field...
 49
18394 pica picahq/skills
Pica — Universal Integrations for AI Pica gives your AI agent the ability to interact with 200+ third-party platforms — Gmail, Slack, HubSpot, Stripe, Notion, Linear, and more. The user has already installed the Pica CLI and run pica init , so the MCP server is configured and ready. Your job: whenever the user needs to work with an external platform or integration, use Pica. When This Skill Activates Step 1: Check what's connected Immediately call the list_pica_integrations MCP tool to see: Whic...
 49
18395 data-pipelines kylelundstedt/dotfiles
You are building data pipelines. The general pattern is ingest (get data in) → transform (clean, model, join) → query (analyze) → explore (notebooks, apps, visualizations). The specific tools for each step depend on the project. Preferred defaults: Step Preferred Tool Alternatives Ingest dlt Plain Python scripts, shell + curl, custom connectors Transform sqlmesh Plain SQL scripts, dbt, Python scripts Query engine DuckDB / MotherDuck — DataFrames polars — Notebooks marimo — Project mgmt uv — Lang...
 49
18396 nuxt studio secondsky/claude-skills
Nuxt Studio Setup and Deployment Overview Nuxt Studio is a free, open-source visual content editor for Nuxt Content websites that enables content editing directly in production. It provides multiple editor types (Monaco code editor, TipTap visual WYSIWYG editor, Form-based editor), OAuth authentication (GitHub/GitLab/Google), and Git-based content management with commit integration. Primary use case : Add visual CMS capabilities to existing Nuxt Content websites, typically deployed to a subdomai...
 49
18397 analytics-clear laurigates/claude-plugins
/analytics:clear Reset all analytics data, removing tracking history and statistics. Context Check if analytics data exists: ANALYTICS_DIR = " ${ HOME } /.claude-analytics" if [ [ -d " ${ANALYTICS_DIR} " ] ] ; then SUMMARY_FILE = " ${ANALYTICS_DIR} /summary.json" if [ [ -f " ${SUMMARY_FILE} " ] ] ; then TOTAL = $( cat " ${SUMMARY_FILE} " | jq -r '.total_invocations // 0' ) SINCE = $( cat " ${SUMMARY_FILE} " | jq -r '.tracking_since // "unknown"' ) echo "Current analytics: ${TOTAL} invocations si...
 49
18398 finops-compare laurigates/claude-plugins
/finops:compare Compare GitHub Actions FinOps metrics across multiple repositories - cache usage, workflow frequency, failure rates, and efficiency. Parameters Parameter Description Default org GitHub organization name (required) - repos... Space-separated list of repo names All org repos --limit N Limit auto-discovery to N repos 30 Usage Examples Compare specific repos /finops:compare myorg repo1 repo2 repo3 Compare all repos in org (up to 30) /finops:compare myorg Compare more repos /finops...
 49
18399 implement-frontend mblode/agent-skills
Implement Frontend Apply this skill when the repository already follows this stack: React + TypeScript + Next.js React Hook Form + Zod React Query or Connect Query Proto-generated API types (when present) If local conventions differ, preserve existing project standards and apply only the transferable principles. Core workflow Set ownership boundaries before editing. Keep render-only concerns in components. Keep fetching, mapping, and business rules in hooks. Keep server state in query cache, for...
 49
18400 daisy-ui dejanvasic85/williamstownsc
daisy-ui Instructions Follow documentation from ./llms.txt to produce code that uses DaisyUI components and themes according to the project's tech stack and coding standards outlined in the main CLAUDE.md file. Theme Customization Configure DaisyUI theme in tailwind.config.js for Williamstown SC brand identity: Primary Colors primary : 062174 (Club blue - traditional, trustworthy) secondary : DEB100 (Club yellow/gold - energy, visibility) accent : 10B981 (Green - soccer field aesthetic) neutral ...
 49