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...
27,972
总 Skills
178.3M
总安装量
2,762
贡献者
# Skill 仓库 描述 安装量
23251 product-leader ncklrs/startup-os-skills
Product Leader Strategic product expertise for building and scaling world-class product organizations — from vision and strategy to discovery, execution, and growth. Philosophy Product management is not about shipping features. It's about creating value by solving real problems for real users in ways that work for the business. The best product organizations: Start with outcomes — Ship outcomes, not output Obsess over users — Data informs, users decide Prioritize ruthlessly — Saying no is the jo...
 48
23252 arxiv-watcher sundial-org/awesome-openclaw-skills
ArXiv Watcher This skill interacts with the ArXiv API to find and summarize the latest research papers. Capabilities Search : Find papers by keyword, author, or category. Summarize : Fetch the abstract and provide a concise summary. Save to Memory : Automatically record summarized papers to memory/RESEARCH_LOG.md for long-term tracking. Deep Dive : Use web_fetch on the PDF link to extract more details if requested. Workflow Use scripts/search_arxiv.sh "<query>" to get the XML results. Parse the ...
 48
23253 proactive-agent nkchivas/openclaw-skill-proactive-agent
Proactive Agent 🦞 By Hal Labs — Part of the Hal Stack A proactive, self-improving architecture for your AI agent. Most agents just wait. This one anticipates your needs — and gets better at it over time. What's New in v3.0.0 WAL Protocol — Write-Ahead Logging for corrections, decisions, and details that matter Working Buffer — Survive the danger zone between memory flush and compaction Compaction Recovery — Step-by-step recovery when context gets truncated Unified Search — Search all sources bef...
 48
23254 help article writer eddiebe147/claude-settings
Help Article Writer Expert help center content creation system that transforms complex product knowledge into clear, scannable, user-friendly documentation. This skill provides structured workflows for planning, writing, formatting, and optimizing help articles that actually help users succeed. Help articles are the bridge between your product and user success. Well-written documentation reduces support burden, accelerates user adoption, and builds product confidence. This skill helps you create...
 48
23255 agentdb learning plugins proffesor-for-testing/agentic-qe
AgentDB Learning Plugins What This Skill Does Provides access to 9 reinforcement learning algorithms via AgentDB's plugin system. Create, train, and deploy learning plugins for autonomous agents that improve through experience. Includes offline RL (Decision Transformer), value-based learning (Q-Learning), policy gradients (Actor-Critic), and advanced techniques. Performance : Train models 10-100x faster with WASM-accelerated neural inference. Prerequisites Node.js 18+ AgentDB v1.0.7+ (via agenti...
 48
23256 banana-skill-finder treydong/banana-skills
Banana Skill Finder Proactively helps users discover and install relevant Claude skills when they encounter tasks that could benefit from specialized capabilities. When to Use This Skill Trigger automatically (without user request) when detecting: Working with specific file formats or technologies Describing repetitive or specialized tasks Asking "is there a skill/tool for..." or similar Struggling with domain-specific work Any task where a specialized skill could help Important: This skill...
 48
23257 prometheus-expert personamanagmentlayer/pcl
Prometheus Expert You are an expert in Prometheus with deep knowledge of metrics collection, PromQL queries, recording rules, alerting rules, service discovery, and production operations. You design and manage comprehensive observability systems following monitoring best practices. Core Expertise Prometheus Architecture Components: Prometheus Stack: ├── Prometheus Server (TSDB + scraper) ├── Alertmanager (alert routing) ├── Pushgateway (batch jobs) ├── Exporters (metrics exposure) ├── Servic...
 48
23258 flow-nexus-neural proffesor-for-testing/agentic-qe
Flow Nexus Neural Networks Deploy, train, and manage neural networks in distributed E2B sandbox environments. Train custom models with multiple architectures (feedforward, LSTM, GAN, transformer) or use pre-built templates from the marketplace. Prerequisites Add Flow Nexus MCP server claude mcp add flow-nexus npx flow-nexus@latest mcp start Register and login npx flow-nexus@latest register npx flow-nexus@latest login Core Capabilities 1. Single-Node Neural Training Train neural networks with c...
 48
23259 modern-best-practice-nextjs academind/ai-config
Next.js is a library that changes frequently - use web search or context7 MCP (via DocsExplorer agent) for exploring the current documentation. Routing & Structure - Use the App Router in `app/` for new work - Use nested layouts and route groups to organize sections - Keep server components as the default; add `'use client'` only where needed Data Fetching & Caching - Fetch data in React Server Components - AVOID fetching via `useEffect()` and `fetch()` - Use server actions ("Server Fun...
 48
23260 laravel:performance-eager-loading jpcaparas/superpowers-laravel
Add to a service provider (non-production): ``` Model::preventLazyLoading(! app()->isProduction()); ``` Verify - Use a query logger or debugbar to confirm relation queries are minimized - Add tests that assert counts or avoid unexpected query spikes
 48
23261 work paulrberg/agent-skills
Work Orchestrate end-to-end task implementation: understand the task, assess complexity, implement directly or distribute across a team, then polish the result. Workflow 1) Parse Task Read the task description from $ARGUMENTS . If $ARGUMENTS is empty, ask the user for a task description and stop. Extract key signals: scope (files, modules, components mentioned), action type (new feature, bug fix, refactor, migration), and any constraints. Note any referenced issues, PRs, or URLs for later contex...
 48
23262 mcp-installer igorwarzocha/opencode-workflows
Find, install, and configure MCP servers for OpenCode. 1. Search for MCP Server Check local catalog first (quick check for already-documented MCPs): ``` python3 ~/.config/opencode/skill/mcp-installer/scripts/list_mcps.py ``` If not found locally, search online: - `websearch("MCP server for [capability]")` - `webfetch("https://github.com/modelcontextprotocol/servers")` - Check npm: `@modelcontextprotocol/server-*` - Check the MCP spec repo: [https://github.com/modelcontextprotocol](http...
 48
23263 app-store-optimization borghei/claude-skills
App Store Optimization (ASO) Search visibility and conversion optimization for App Store product pages. This skill covers strategic metadata decisions -- which keywords to target, how to structure descriptions for conversion, and how to use Custom Product Pages and in-app events for discoverability. For metadata compliance rules (character limits, screenshot device requirements, rejection triggers), see the app-store-review skill. Contents Show more Installs 1.7K Repository dpearson2699/sw…s-ski...
 48
23264 blueprint-derive-adr laurigates/claude-plugins
Generate Architecture Decision Records (ADRs) for an existing project by analyzing code structure, dependencies, and documentation. Use Case : Onboarding existing projects to Blueprint Development system, documenting implicit architecture decisions. Prerequisites : Blueprint Development initialized ( docs/blueprint/ exists) Ideally PRD exists (run /blueprint:derive-prd first) Steps : Phase 1: Discovery 1.1 Check Prerequisites ls docs/blueprint/manifest.json ls docs/prds/ If blueprint not initial...
 48
23265 bot-process-control terrylica/cc-skills
Bot Process Control Manage the Gmail Commander bot daemon and scheduled digest via launchd. Mandatory Preflight Step 1: Check Current Process Status echo "=== Gmail Commander Processes ===" pgrep -fl "gmail-commander" 2 > /dev/null || echo "No processes found" echo "" echo "=== launchd Status ===" launchctl list | grep gmail-commander 2 > /dev/null || echo "No launchd jobs" echo "" echo "=== PID Files ===" cat /tmp/gmail-commander-bot.pid 2 > /dev/null && echo " (bot)" || echo "No bot PID file" ...
 48
23266 install-wallet-ui-react-native wallet-ui/wallet-ui
This skill helps you set up Wallet UI in your Expo React Native application. You need to choose which Solana library you are using, as the setup differs significantly. Choose Your Path 1. Modern: `@solana/kit` (Recommended) Use this if: - You are starting a new project. - You prefer the modern, lightweight, functional API of `@solana/kit`. - You want better tree-shaking and smaller bundle sizes. Instructions: [Open Solana Kit Guide](https://github.com/wallet-ui/wallet-ui/blob/main/.rule...
 48
23267 community-marketing dengineproblem/agents-monorepo
Community Marketing You are an expert community builder and community-led growth strategist. Your goal is to help the user design, launch, and grow a community that creates genuine value for members while driving measurable business outcomes. Before You Start 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 ...
 48
23268 minimize-rust-ffi-crate-surface redisearch/redisearch
No SKILL.md available for this skill. View on GitHub
 48
23269 secret-scanner ovachiever/droid-tings
Secret Scanner Skill Prevent accidental secret exposure in your codebase. When I Activate ✅ Before git commits ✅ Files modified/saved ✅ User mentions secrets, keys, or credentials ✅ .env files changed ✅ Configuration files modified What I Detect API Keys & Tokens AWS access keys (AKIA...) Stripe API keys (sk_live_..., pk_live_...) GitHub tokens (ghp_...) Google API keys OAuth tokens JWT secrets Database Credentials Database connection strings MySQL/PostgreSQL passwords MongoDB connection URIs ...
 48
23270 wechat-article-fetcher nanzhipro/questskills
微信公众号文章获取器 获取、解析并保存微信公众号文章，支持单篇和批量下载、元数据提取、图片下载和 Markdown 转换。 快速开始 获取单篇文章： python scripts/fetch_wechat_article.py "https://mp.weixin.qq.com/s/xxxxx" 批量获取多篇文章（空格分隔）： python scripts/fetch_wechat_article.py "url1" "url2" "url3" --output-dir ./output 批量获取多篇文章（逗号分隔）： python scripts/fetch_wechat_article.py "url1,url2,url3" --output-dir ./output 仅输出元数据（不保存文件）： python scripts/fetch_wechat_article.py "https://mp.weixin.qq.com/s/xxxxx" --json 依赖安装 pip install beautifulsoup4 html2text requests 功能说明 1. 获取文章...
 48
23271 aid-finances nweii/agent-stuff
Financial Advisory Provide personalized, actionable financial advice as an expert with advanced credentials. Prioritize user's long-term financial well-being. Expertise areas Cover full spectrum of personal finance: Budgeting and expense management Debt management and repayment strategies Investing (short-term and long-term) Retirement planning Tax optimization (see taxes.md for detailed guidance) Insurance and risk management Real estate and mortgages Career financial planning Stock market and ...
 48
23272 roadmap builder eddiebe147/claude-settings
Roadmap Builder The Roadmap Builder skill helps product teams create strategic roadmaps that align tactical execution with business objectives. It emphasizes theme-based planning over feature lists, outcome-focused goals using OKRs, and flexible planning that adapts to market feedback and changing priorities. This skill excels at translating business strategy into quarterly themes, breaking themes into initiatives and epics, aligning stakeholders around shared goals, and maintaining roadmap clar...
 48
23273 ai-model-wechat tencentcloudbase/cloudbase-mcp
When to use this skill Use this skill for calling AI models in WeChat Mini Program using wx.cloud.extend.AI . Use it when you need to: Integrate AI text generation in a Mini Program Stream AI responses with callback support Call Hunyuan models from WeChat environment Do NOT use for: Browser/Web apps → use ai-model-web skill Node.js backend or cloud functions → use ai-model-nodejs skill Image generation → use ai-model-nodejs skill (not available in Mini Program) HTTP API integration → use http-ap...
 48
23274 arch-tsdown hairyf/skills
arch-tsdown is a TypeScript library starter (based on antfu/starter-ts) that uses tsdown for building. It provides a minimal, opinionated setup: ESM-only output, automatic `.d.ts` generation, pnpm, Vitest, ESLint, and optional npm Trusted Publisher for CI-based releases. The skill is based on starter-ts (arch-tsdown source), generated at 2026-01-30. Recommended practices: - Build pure ESM; enable `dts` and `exports` in tsdown config - Use npm Trusted Publisher for releases - Run publint (vi...
 48
23275 ruby-optimise pproenca/dot-skills
Community Ruby Best Practices Comprehensive performance optimization guide for Ruby applications, maintained by the community. Contains 42 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation. When to Apply Reference these guidelines when: Writing new Ruby code or gems Optimizing ActiveRecord queries and database access patterns Processing large collections or building data pipelines Reviewing code for memory bloat and GC pressure Configuring Ruby r...
 48
23276 aws-cost-cleanup sickn33/antigravity-awesome-skills
AWS Cost Cleanup Automate the identification and removal of unused AWS resources to eliminate waste. When to Use This Skill Use this skill when you need to automatically clean up unused AWS resources to reduce costs and eliminate waste. Automated Cleanup Targets Storage Unattached EBS volumes Old EBS snapshots (>90 days) Incomplete multipart S3 uploads Old S3 versions in versioned buckets Compute Stopped EC2 instances (>30 days) Unused AMIs and associated snapshots Unused Elastic IPs Networking ...
 48
23277 cc-skill-clickhouse-io sickn33/antigravity-awesome-skills
ClickHouse Analytics Patterns ClickHouse-specific patterns for high-performance analytics and data engineering. Overview ClickHouse is a column-oriented database management system (DBMS) for online analytical processing (OLAP). It's optimized for fast analytical queries on large datasets. Key Features: Column-oriented storage Data compression Parallel query execution Distributed queries Real-time analytics Table Design Patterns MergeTree Engine (Most Common) CREATE TABLE markets_analytics ( date...
 48
23278 bootstrap-project kylelundstedt/dotfiles
Bootstrap Project Set up agent context files so Claude Code, Codex, and other AI agents understand a project from the first prompt. When to Use This Skill Use when the user: Wants to start a new project with agent context from the beginning Opens an existing repo that lacks AGENTS.md Says "bootstrap this project", "set up agent context", or similar Asks for help creating CLAUDE.md or AGENTS.md Steps 1. Determine whether this is a new or existing project Existing project — the current directory h...
 48
23279 tooluniverse-custom-tool mims-harvard/tooluniverse
Adding Custom Tools to ToolUniverse Three ways to add tools — pick the one that fits your needs: Approach When to use JSON config REST API with standard request/response — no coding needed Python class (workspace) Custom logic for local/private use only Plugin package Reusable tools you want to share or install via pip Option A — Workspace tools (local use) Tools in .tooluniverse/tools/ are auto-discovered at startup. No installation needed. mkdir -p .tooluniverse/tools JSON config Create .toolu...
 48
23280 icml-reviewer sundial-org/skills
ICML Paper Reviewer Enables rigorous review of ML research papers following official ICML guidelines. Workflow Step 1: Input Analysis & Mode Selection Determine input type: Complete paper : PDF/text with abstract, methodology, experiments, results → Full Review Mode Incomplete document : Missing major sections, labeled draft/proposal, or user indicates early stage → Early-Stage Feedback Mode Code repository : User points to folder/repo path → Repository Review Mode For complete papers , extract:...
 48
23281 remotion-performance-optimizer ncklrs/startup-os-skills
Remotion Performance Optimizer Comprehensive performance analysis and optimization recommendations for Remotion video compositions. Identifies bottlenecks and provides actionable fixes to reduce render times. What This Skill Does Performs deep performance analysis: Computation analysis — Identify expensive operations in render path Re-render detection — Find unnecessary component re-renders Asset optimization — Recommend asset size and format improvements Memoization opportunities — Identify...
 48
23282 rust-expert oimiragieo/agent-studio
Rust Expert Apply idiomatic Rust patterns with strong safety, performance, and maintainability guarantees. Core Principles Model correctness through the type system; make invalid states unrepresentable. Prefer explicit over implicit; surface ownership intent in every signature. Write minimal, zero-cost abstractions — no allocation or indirection that serves no purpose. Test behavior, not implementation; favor integration tests at crate boundaries. 1. Ownership, Borrowing, and Lifetimes Ownership...
 48
23283 outreach sequencer eddiebe147/claude-settings
Outreach Sequencer Design and optimize multi-touch email sequences that cut through inbox noise and drive meaningful conversations. This skill helps you craft personalized outreach cadences that respect prospects' time while persistently delivering value. Cold outreach is hard. Most emails get ignored. This skill applies proven patterns for subject lines, opening hooks, value propositions, and calls-to-action that actually get responses. Learn optimal timing, sequence length, and personalization...
 48
23284 founder coach eddiebe147/claude-settings
Founder Coach Support founder mental health, decision-making, and leadership challenges When to Use This Skill Use this skill when you need to: Improve personal productivity Achieve personal goals Develop better habits Not recommended for: Tasks requiring business strategy team coordination Quick Reference Action Command/Trigger Create founder coach founder coaching Review and optimize review founder coach Get best practices founder coach best practices Core Workflows Workflow 1: Initial Founder...
 48
23285 config-manager eddiebe147/claude-settings
Configuration Manager Skill Overview This skill helps you design and implement robust configuration management for applications. Covers environment variables, config files, secrets management, validation, type safety, and multi-environment deployments. Configuration Philosophy Twelve-Factor App Principles Store config in the environment: Separate config from code Strict separation: Config that varies between deploys should be in env vars No secrets in code: Ever. Period. Configuration Hierarch...
 48
23286 test-environment-management proffesor-for-testing/agentic-qe
<default_to_action> When managing test environments: - DEFINE environment types (local, CI, staging, prod) - CONTAINERIZE with Docker for consistency - ENSURE parity with production (same versions, configs) - MOCK external services (service virtualization) - OPTIMIZE costs (auto-shutdown, spot instances) Quick Environment Checklist: - Same OS/versions as production - Same database type and version - Same configuration structure - Containers for reproducibility - Auto-shutdown after ho...
 48
23287 shift-left-testing proffesor-for-testing/agentic-qe
<default_to_action> When implementing early testing practices: - VALIDATE requirements before coding (testability, BDD scenarios) - WRITE tests before implementation (TDD red-green-refactor) - AUTOMATE in CI pipeline (every commit triggers tests) - FOLLOW test pyramid: Many unit (70%), some integration (20%), few E2E (10%) - FIX defects immediately - never let them accumulate Quick Shift-Left Levels: - Level 1: Unit tests with each PR (developer responsibility) - Level 2: TDD practice (t...
 48
23288 rust-docs-guidelines redisearch/redisearch
Rust Docs Guidelines Standards to follow when writing Rust documentation. Guidelines Key concepts should be explained only once. All other documentation should use an intra-documentation link to the first explanation. Always use an intra-documentation link when mentioning a Rust symbol (type, function, constant, etc.). Avoid referring to specific lines or line ranges, as they may change over time. Use line comments if the documentation needs to be attached to a specific code section inside a fun...
 48
23289 letta-development-guide letta-ai/skills
Comprehensive guide for designing and building effective Letta agents with appropriate architectures, memory configurations, model selection, and tool setups. When to Use This Skill Use this skill when: - Starting a new Letta agent project - Choosing between agent architectures (letta_v1_agent vs memgpt_v2_agent) - Designing memory block structure and architecture - Selecting appropriate models for your use case - Planning tool configurations - Optimizing memory management and performan...
 48
23290 slack-messaging obra/superpowers-lab
Slack Messaging Best Practices This skill provides guidance for composing well-formatted, effective Slack messages. When to Use Apply this skill whenever composing, drafting, or helping the user write a Slack message — including when using slack_send_message , slack_send_message_draft , or slack_create_canvas . Slack Formatting (mrkdwn) Slack uses its own markup syntax called mrkdwn , which differs from standard Markdown. Always use mrkdwn when composing Slack messages: Format Syntax Notes Bold ...
 48
23291 mutation-testing proffesor-for-testing/agentic-qe
Mutation Testing — Campaign Configuration (mewt/muton) Note : muton and mewt share identical interfaces but target different languages — mewt for general-purpose languages (Rust, Solidity, Go, TypeScript, JavaScript), muton for TON smart contracts (Tact, Tolk, FunC). All examples use mewt commands, but they work exactly the same with muton . File names change accordingly: mewt.toml → muton.toml , mewt.sqlite → muton.sqlite . When to Use Use this skill when the user: Mentions "mewt", "muton", or ...
 48
23292 agent-customization microsoft/vscode-copilot-chat
Agent Customization Decision Flow Primitive When to Use Workspace Instructions Always-on, applies everywhere in the project File Instructions Explicit via applyTo patterns, or on-demand via description MCP Integrates external systems, APIs, or data Hooks Deterministic shell commands at agent lifecycle points (block tools, auto-format, inject context) Custom Agents Subagents for context isolation, or multi-stage workflows with tool restrictions Prompts Single focused task with parameterized input...
 48
23293 modern-auth-2026 erichowens/some_claude_skills
Modern Authentication Expert (2026) Master passwordless-first authentication with passkeys, OAuth, magic links, and cross-device sync for modern web and mobile applications. When to Use ✅ USE this skill for: Implementing passkeys/WebAuthn authentication Google and Apple OAuth social login Supabase Auth configuration and troubleshooting Magic link/OTP passwordless flows Cross-device authentication sync MFA implementation (TOTP, passkeys as 2FA) Email/SMS recovery flows App Store compliance fo...
 48
23294 mercury vm0-ai/vm0-skills
Mercury Banking API Manage business bank accounts, transactions, transfers, and financial operations via Mercury's REST API. Official docs: https://docs.mercury.com/reference/getaccount When to Use Use this skill when you need to: View account balances and details List and search transactions Create internal transfers between accounts Manage recipients for external transfers Download account statements Access treasury account information Prerequisites Sign up for a Mercury business bank account ...
 48
23295 spec-implementation-plan zixun-github/aisdlc
spec-implementation-plan（I1：实现计划 / plan.md SSOT） 概览 I1 的目标是把 {FEATURE_DIR}/requirements/* 与 {FEATURE_DIR}/design/* 转换为 可直接执行 的实现计划 {FEATURE_DIR}/implementation/plan.md ，并将其作为 唯一执行清单与状态 SSOT （checkbox 任务 + 每任务步骤 + 最小验证 + 提交点 + 审计信息）。 开始时宣布： 「我正在使用 spec-implementation-plan 技能创建实现计划（plan.md SSOT）。」 何时使用 / 不使用 使用时机 你需要产出或更新 {FEATURE_DIR}/implementation/plan.md （I1 必做）。 你准备进入 I2 执行，但当前没有“可勾选 + 可执行”的任务清单。 不要用在 spec-context 失败、拿不到 FEATURE_DIR （此时必须停止）。 输入侧 SSOT 不足： requirements/solution.md 与 requiremen...
 48
23296 maplibre-pmtiles-patterns maplibre/maplibre-agent-skills
MapLibre PMTiles Patterns PMTiles is a single-file format for vector or raster map tiles. You host one (or a few) files on any static host; MapLibre requests byte ranges over HTTP. No tile server, no dynamic backend. This skill covers when to use PMTiles, how to generate and host them, and how to connect them to MapLibre GL JS. When to Use This Skill Hosting map tiles without running a tile server (S3, Cloudflare R2, GitHub Pages, etc.) Building a fully static or serverless map stack Serving lar...
 48
23297 skill-review joelhooks/joelclaw
Skill Review IRON LAW: Be specific and actionable. Never say "could be improved" without stating exactly what to change and why it matters for model output quality. Workflow Skill Review Progress: Show more Installs 527 Repository sanyuan0704/san…n-skills GitHub Stars 3.7K First Seen May 11, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Snyk Pass
 48
23298 atlassian-templates borghei/claude-skills
Atlassian Template & Files Creator Expert Specialist in creating, modifying, and managing reusable templates and files for Jira and Confluence. Ensures consistency, accelerates content creation, and maintains org-wide standards. Core Competencies Template Design Create Confluence page templates with dynamic content Design Jira issue templates and descriptions Build blueprints for complex content structures Implement template versioning and updates Content Standardization Establish org-wide conte...
 48
23299 operations optimizer eddiebe147/claude-settings
Operations Optimizer Expert operations optimization system that helps you analyze workflows, eliminate inefficiencies, automate repetitive tasks, and drive operational excellence. This skill provides structured frameworks for process improvement, automation, and productivity optimization based on Lean, Six Sigma, and modern operations management principles. Operational excellence is the foundation of scalable growth. This skill helps you identify bottlenecks, streamline workflows, reduce waste, ...
 48
23300 educates-course-design educates/educates-course-design-skill
Educates Course Design Skill This skill guides the design of Educates courses, which are structured collections of workshops, from initial requirements through to detailed per-workshop implementation plans. The output is a set of planning documents that serve as blueprints for workshop creation using the educates-workshop-authoring skill. The workflow progresses through six steps, from establishing requirements down to per-workshop implementation plans. Each step produces a planning document in ...
 48