Best for Claude Code
Top-rated skills optimized for Claude Code workflows
Showing 1,741–1,800 of 2,771 skills · Page 30 of 47
AtomGraph / Web-Algebra
46Suite of generic Linked Data/SPARQL as well as LinkedDataHub-specific MCP tools
BetaBots-LLC / callimachus
46One local, searchable index of your AI coding-agent history Claude Code, Codex, Cursor, Gemini & more. Keyword + semantic search, MCP server, CLI & VS Code extension.
yogthos / wavescope-mcp
45Wavelet-based multi-resolution context management for LLMs via MCP
xiaour / yolo-data
45先进且稳定的企业级智能分析平台；面向企业问数、洞察分析的Data Agent，基于数据分析方法论打造可审计、可治理、可复现workflow
dizlexic / moo-tasks
45A simple multiuser multiboard task MCP server managed via kanban board interface. Created to allow simple self hosted agent task management.
EnhydrInk / tasogare
44Read the same book with your AI. A collaborative reader with text-anchored two-color highlights and an MCP server so an AI companion can flip through, mark up, and comment alongside you.
YZBRH / keyrealm
10Local-first credential manager & validator for red teams / pentest：致力于 ALL IN ONE 的本地凭据管理与验证平台。 允许将红队渗透测试中获取的散落在各处的 API Key、云厂商 AK/SK、机器人 Token、邮箱授权码、登录态等集中加密保管、便捷验证与快速利用。多插件多类别，单条·批量·定时验证，内置 MCP Server；AES-256-GCM 字段级加密，每凭据可选代理出口，加密/明文备份可跨库还原；数据只存本机、不联网同步，Windows / macOS / Linux。
n2ns / MCPxHub
10MCP bridge that auto-discovers VS Code-family (VS Code, Cursor, Windsurf, Antigravity) and JetBrains IDE MCP servers and proxies Claude Desktop's tool calls to them, reconnecting as ports change.
tse-wei-chen / hs-sql-agent
10.NET SQL Agent MCP server featuring raw SQL input, strict AST validation, and an embedded Admin UI. Eliminates LLM hallucinations and security risks across 6 major databases.
megamen32 / gptadmin_opensource
10One MCP hub — any AI controls any infrastructure. Self-hosted, works with ChatGPT, Claude, Codex, DeepSeek, Qwen, Alice, GigaChat.
tosin2013 / documcp
10DocuMCP is an intelligent Model Context Protocol (MCP) server that revolutionizes documentation deployment for open-source projects. It provides deep repository analysis, intelligent static site generator recommendations, and automated GitHub Pages deployment workflows.
HeathHowren / Pointer-Lab
10Free, open-source memory scanner and debugger for Windows, for 32- and 64-bit targets: pointer scanner, find-what-writes, auto-assembler, speed hack, Lua, and an MCP server for AI agents
Typewise / mcp-chaos-rig
10A local MCP server that breaks on demand. Test your client against auth failures, disappearing tools, flaky responses, and token expiry, all from a web UI.
Microck / every-style-editor
399This skill should be used when reviewing or editing copy to ensure adherence to Every's style guide. It provides a systematic line-by-line review process for grammar, punctuation, mechanics, and style guide compliance.
anthropics / configure
43.1kSet up the Discord channel — save the bot token and review access policy
Gentleman-Programming / rdd-advisory-transport
7.9kLoad when changing how any runtime (Claude Code, OpenCode, Codex, future) invokes an RDD reviewer, refuter, or fix validator, or when touching reviewer prompts, lens evidence, result schemas, adapters, or transport capability policy.
Ryze-AI-Adgent / seo-audit
6.3kFull SEO audit of a site from its real Search Console + GA4 data — indexation health, CTR anomalies, decaying pages, striking-distance keywords, quick wins
davepoon / uctm-init
3.7kInitialize uc-taskmanager for the current project. Creates works/ directory and configures Bash permissions in .claude/settings.local.json
jeremylongshore / adobe-ci-integration
2.8kBuild deterministic CI gates for Adobe adapters without giving fork jobs credentials or spending against live creative/document APIs
jeremylongshore / adobe-sdk-patterns
2.8kCreate narrow, version-pinned Adobe SDK and REST adapters with typed contracts, redaction, bounded polling, and compatibility evidence
jeremylongshore / alchemy-cost-tuning
2.8kGovern Alchemy compute usage and spend with current account evidence, workload attribution, budgets, and reversible optimizations
jeremylongshore / alchemy-rate-limits
2.8kDesign account-aware Alchemy throttling, bounded retries, and admission control from observed throughput rather than stale plan constants
jeremylongshore / alchemy-security-basics
2.8kAnalyze and secure Alchemy credentials, browser access, wallet authority, webhook verification, and untrusted chain data
jeremylongshore / analyzing-dependencies
2.8kAnalyze dependencies for known security vulnerabilities and outdated
spencermarx / bottleneck-detect
368Analyze performance bottlenecks in swarm operations and suggest optimizations.
spencermarx / auto-agent
368Automatically spawn and manage agents based on task requirements.
spencermarx / pr-manager
368Comprehensive pull request management with ruv-swarm coordination for automated reviews, testing, and merge workflows.
spencermarx / sparc-ask
368❓Ask - You are a task-formulation guide that helps users navigate, ask, and delegate tasks to the correc...
spencermarx / sparc-code
368🧠 Auto-Coder - You write clean, efficient, modular code based on pseudocode and architecture. You use configurat...
spencermarx / sparc-devops
368🚀 DevOps - You are the DevOps automation and infrastructure specialist responsible for deploying, managing, ...
spencermarx / orchestrator
368Multi-agent task orchestration with TodoWrite/TodoRead/Task/Memory using MCP tools.
spencermarx / sparc-refinement-optimization-mode
368🧹 Optimizer - You refactor, modularize, and improve system performance. You enforce file size limits, dependenc...
spencermarx / browser
368Web browser automation with AI-optimized snapshots for claude-flow agents
spencermarx / ocr
368AI-powered multi-agent code review. Simulates a team of Principal Engineers reviewing code from different perspectives
vinvcn / git-guardrails-claude-code
4.4k设置 Claude Code hooks，在危险 git commands（push、reset --hard、clean、branch -D 等）执行前阻止它们。适用于用户想防止破坏性 git 操作、添加 git safety hooks，或在 Claude Code 中阻止 git push/reset 时。
brycewang-stanford / newproject
4.4kScaffold a new research project with standard directory structure, CLAUDE.md template, and documented README. Use this at the start of every new project to ensure consistent organization.
parcadei / agentica-claude-proxy
3.9kGuide for integrating Agentica SDK with Claude Code CLI proxy
parcadei / agentica-server
3.9kAgentica server + Claude proxy setup - architecture, startup sequence, debugging
parcadei / slash-commands
3.9kCreate and use Claude Code slash commands - quick prompts, bash execution, file references
parcadei / sub-agents
3.9kCreate and configure Claude Code sub-agents with custom prompts, tools, and models
sanyuan0704 / skill-review
3.9kQuality review and audit for Claude Code skills. Analyzes skill structure, description quality, workflow design, token efficiency, and anti-patterns against best practices
rohitg00 / token-efficiency
2.9kReduce token waste by 40-60% through anti-sycophancy rules, tool-call budgets, one-pass coding, task profiles, and read-before-write enforcement. Inspired by drona23/claude-token-efficient.
softaworks / daily-meeting-update
2.5kInteractive daily standup/meeting update generator
pedrohcgs / context-status
1.6kShow current context status and session health. Use to check how much context has been used, whether auto-compact is approaching, and what state will be preserved.
daymade / local-conversation-history
1.4kEntry point for local AI conversation history across Claude Code, Codex and Kimi CLI: routes each request to the reader or continuation skill that owns it and keeps the cross-provider inventory
AI-Builder-Club / open-agent-teams
1.3kDelegate tasks to ANY CLI agent (claude, codex, aider, ...) running in a detached tmux session, with a race-safe done-signal protocol and multi-turn iteration
indranilbanerjee / competitor-monitor
832Monitor competitors over time: baseline sites, pricing and ads by script, flag changes. \"track our competitors over time\"
indranilbanerjee / localize-campaign
832Localize a whole campaign for several markets with transcreation. One text → translate-content. \"take the Q3 campaign multilingual\"
indranilbanerjee / segment-audience
832Build audience segments in CRM, email or ad platforms with consent checks, approval-gated. \"create a segment of lapsed customers\"
indranilbanerjee / send-email-campaign
832Send an email campaign via a connected ESP with spam and compliance checks, approval-gated. \"send this newsletter to the active list\"
indranilbanerjee / send-report
832Send a performance report to Slack, email or Sheets from connected analytics, approval-gated. \"send the weekly report to Slack\"
Ark0N / codeman
768Drive Codeman, the session manager this agent is running inside, over its HTTP API: list sessions, start worker sessions, send them prompts, block until they finish (wait / wait-output / send-and-wait), read their output, and clean up; where available, message claude workers directly (Claude Code cr…
tzachbon / speckit.specify
550Create or update the feature specification from a natural language feature description.
tzachbon / speckit.tasks
550Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
aiskillstore / structural-search
428Search code by AST structure using ast-grep. Find semantic patterns like function calls, imports, class definitions instead of text patterns. Triggers on: find all calls to X, search for pattern, refactor usages, find where function is used, structural search, ast-grep, sg.
tobihagemann / create-project-skills
405Scans an existing codebase and generates project-specific skills that capture inferred conventions such as naming, file organization, framework usage, data access, error handling, and testing style.
tobihagemann / create-skill
405Create a new skill or update an existing skill that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations
hypnguyen1209 / using-offensive-claude
377Use when starting any offensive-security engagement or task — establishes how to find and invoke the right skill before any action (including clarifying questions, recon, exploitation, or reporting)
zereight / gitlab-mcp
2.1kMCP server for GitLab: 277 tools for projects, MRs, issues, pipelines, wikis and more via the GitLab REST/GraphQL API
Piebald-AI / claude-code-system-prompts
13.0kAll parts of Claude Code's system prompt, 27 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, security review, agent creation). Updated for each Claude Code version.