SkillAgentSearch skills...
All collections
🆕

New This Week

Skills added or updated in the last 7 days

Showing 301360 of 914 skills · Page 6 of 16

openclaw / clawhub

389.2k

Search ClawHub for skills when a requested capability is not already available; install, verify, update, uninstall, publish, or sync skills.

📄 SKILL.mdclaude codeuniversal
skillrust
89
Updated 1h ago

openclaw / coding-agent

389.2k

Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.

📄 SKILL.mdclaude codeuniversal+1
skillgitapi+3
89
Updated 1h ago

openclaw / control-ui

389.2k

Operate and troubleshoot the OpenClaw Control UI: navigate connected clients, organize sessions, build session dashboards, and handle direct or Tailscale-hosted Gateways.

📄 SKILL.mdclaude codeuniversal
skillapiautomation+2
89
Updated 1h ago

openclaw / gh-issues

389.2k

Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.

📄 SKILL.mdclaude codeuniversal
skillgitapi+3
89
Updated 1h ago

openclaw / node-connect

389.2k

Diagnose OpenClaw Control UI browser and native Android, iOS, or macOS node connection failures across route, auth, pairing, QR/setup-code, and reconnect states.

📄 SKILL.mdclaude codeuniversal
skillreviewrust+1
89
Updated 1h ago

openclaw / obsidian

389.2k

Work with Obsidian vaults using the official obsidian CLI: read/search/create/edit notes, tasks, links, properties, plugins.

📄 SKILL.mdclaude codeuniversal
skillreview
89
Updated 1h ago

openclaw / taskflow

389.2k

Run approval-gated workflows with durable TaskFlow state; distinguish workflow execution from linking real detached tasks.

📄 SKILL.mdclaude codeuniversal+2
skillgitapi+5
89
Updated 1h ago

openclaw / weather

389.2k

Current weather and forecasts with web_fetch, falling back to wttr.in curl for locations, rain, temperature, travel planning.

📄 SKILL.mdclaude codeuniversal
skillapirest
89
Updated 1h ago

openclaw / xurl

389.2k

xurl CLI for authenticated X posts, replies, reads/search, DMs, media upload, followers, auth status, or raw v2 API calls.

📄 SKILL.mdclaude codeuniversal
skillapiimage
89
Updated 1h ago

openclaw / acp-router

389.2k

Route plain-language requests for Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or explicit ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow).

📄 SKILL.mdclaude codegemini cli+4
skillgitapi+2
89
Updated 1h ago

openclaw / browser-automation

389.2k

Use when controlling web pages with the OpenClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.

📄 SKILL.mdclaude codeuniversal+1
skilltestingmcp+5
89
Updated 1h ago

openclaw / diffs

389.2k

Use the diffs tool to produce real, shareable diffs (viewer URL, file artifact, or both) instead of manual edit summaries.

📄 SKILL.mdclaude codeuniversal
skillpdfrust
89
Updated 1h ago

openclaw / feishu-drive

389.2k

Feishu cloud-storage and comment workflows. Activate when the user mentions cloud space, folders, Drive files, or document comments.

📄 SKILL.mdclaude codeuniversal
skill
89
Updated 1h ago

openclaw / feishu-perm

389.2k

Feishu collaborator and permission workflows. Activate when the user explicitly asks to inspect or change sharing, permissions, or collaborators.

📄 SKILL.mdclaude codeuniversal
skill
89
Updated 1h ago

openclaw / imsg

389.2k

Use the imsg CLI from OpenClaw agents for iMessage/SMS DMs, groups, replies, reactions, polls, watching, and private-API actions.

📄 SKILL.mdclaude codeuniversal
skillapisql+4
89
Updated 1h ago

openclaw / lobster

389.2k

Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation | User intent | Use Lobster?

📄 SKILL.mdclaude codeuniversal
skillautomation
89
Updated 1h ago

openclaw / block-kit

389.2k

Use proactively for structured or interactive Slack replies, and when asked to author or validate native Slack Block Kit JSON.

📄 SKILL.mdclaude codeuniversal
skilldocumentationslack
89
Updated 1h ago

anthropics / frontend-design

144.5k

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

📄 SKILL.mdclaude code
skillgitapi+5
89
Updated 3h ago

anthropics / Writing Hookify Rules

144.5k

This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.

📄 SKILL.mdclaude code
skilltestinggit+5
89
Updated 3h ago

anthropics / Agent Development

144.5k

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or…

📄 SKILL.mdclaude code
skilldevelopmenttesting+5
89
Updated 3h ago

anthropics / Command Development

144.5k

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs gu…

📄 SKILL.mdclaude codezed
skilldevelopmenttesting+5
89
Updated 3h ago

anthropics / Hook Development

144.5k

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse,…

📄 SKILL.mdclaude codezed
skilldevelopmenttesting+5
89
Updated 3h ago

anthropics / MCP Integration

144.5k

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket).

📄 SKILL.mdclaude code
skilldevelopmenttesting+5
89
Updated 3h ago

anthropics / Plugin Settings

144.5k

This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable.

📄 SKILL.mdclaude code
skilldevelopmentgit+5
89
Updated 3h ago

anthropics / Plugin Structure

144.5k

This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin director…

📄 SKILL.mdclaude codezed
skilltestinggit+5
89
Updated 3h ago

anthropics / Skill Development

144.5k

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

📄 SKILL.mdclaude codezed
skilldevelopmenttesting+5
89
Updated 3h ago

google-gemini / agent-tui

106.9k

Main Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the `tui_tester` subagent. Drive terminal UI (TUI) applications programmatically for testing, automation, and inspection

Gemini Rulesgemini cli
geminitestinggit+5
89
Updated 1h ago

google-gemini / async-pr-review

106.9k

Trigger this skill when the user wants to start an asynchronous PR review, run background checks on a PR, or check the status of a previously started async PR review.

Gemini Rulesgemini cli
geminigitdesign+1
89
Updated 1h ago

google-gemini / ci

106.9k

A specialized skill for Gemini CLI that provides high-performance, fail-fast monitoring of GitHub Actions workflows and automated local verification of CI failures. It handles run discovery automatically—simply provide the branch name.

Gemini Rulesgemini cli
geminidevelopmentgit+1
89
Updated 1h ago

google-gemini / code-reviewer

106.9k

Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.

Gemini Rulesgemini cli
geminidevelopmentgit+4
89
Updated 1h ago

google-gemini / docs-writer

106.9k

Always use this skill when the task involves writing, reviewing, or editing files in the `/docs` directory or any `.md` files in the repository.

Gemini Rulesgemini clized
geminidevelopmentgit+5
89
Updated 1h ago

google-gemini / github-issue-creator

106.9k

Use this skill when asked to create a GitHub issue. It handles different issue types (bug, feature, etc.) using repository templates and ensures proper labeling.

Gemini Rulesgemini clized
geminigitapi+2
89
Updated 1h ago

google-gemini / pr-address-comments

106.9k

Use this skill if the user asks you to help them address GitHub PR comments for their current branch of the Gemini CLI. Requires `gh` CLI tool.

Gemini Rulesgemini cli
geminigitreview+1
89
Updated 1h ago

google-gemini / pr-creator

106.9k

Use this skill when asked to create a pull request (PR). It ensures all PRs follow the repository's established templates and standards.

Gemini Rulesgemini cli
geminigitapi+2
89
Updated 1h ago

google-gemini / review-duplication

106.9k

Use this skill during code reviews to proactively investigate the codebase for duplicated functionality, reinvented wheels, or failure to reuse existing project best practices and shared utilities.

Gemini Rulesgemini clized
geminiapidocumentation+4
89
Updated 1h ago

google-gemini / string-reviewer

106.9k

Use this skill when asked to review text and user-facing strings within the codebase. It ensures that these strings follow rules on clarity, usefulness, brevity and style.

Gemini Rulesgemini cli
geminireviewvoice
89
Updated 1h ago

NousResearch / hermes-agent

243.4k

The agent that grows with you

🤖 CLAUDE.mdclaude codecodex
claude
89
Updated 2h ago

slopus / happy

23.7k

Mobile and Web client for Codex and Claude Code, with realtime voice, encryption and fully featured

🤖 CLAUDE.mdclaude codecodex
claudevoice
89
Updated 1d ago

mksglu / context-mode

21.4k

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

🤖 CLAUDE.mdclaude codecursor+3
claudemcp
89
Updated 12h ago

jnMetaCode / agency-agents-zh

20.4k

🎭 267 个即插即用的 AI 专家角色 — 支持 Hermes Agent/Claude Code/Cursor/Copilot 等 18 种工具,覆盖工程/设计/营销/金融等 20 个部门。含 52 个中国市场原创智能体(小红书/抖音/微信/飞书/钉钉等)。搭配编排器 agency-orchestrator,一句话即可让多位专家按 DAG 自动协作。

🤖 CLAUDE.mdclaude codecursor+1
claude
89
Updated 1d ago

wanshuiyin / Auto-claude-code-research-in-sleep

15.9k

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

🤖 CLAUDE.mdclaude codecodex
claudemcpautomation+1
89
Updated 2d ago

Kuberwastaken / claurst

10.3k

Agentic Coding for Builders who Ship

🤖 CLAUDE.mdclaude codegemini cli+1
clauderust
89
Updated 6d ago

getsentry / XcodeBuildMCP

6.4k

A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.

🔌 MCP Serverclaude codeclaude desktop
mcp
89
Updated 1d ago

atlassian / atlassian-mcp-server

1.0k

Official remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucket, and Compass to Claude, ChatGPT, Cursor, VS Code, and other AI tools using OAuth 2.1 or API tokens.

🔌 MCP Serverclaude codeclaude desktop+2
mcpapi
89
Updated 3h ago

qixing-jk / all-api-hub

4.8k

All-in-one New-API/Sub2API account hub: balance/usage dashboard, auto check-in, one-click keys, price comparison, health checks, plus advanced channel management | 一站式 New-API/Sub2API 等中转站账号管理:余额/用量看板、自动签到、密钥一键使用、价格对比、可用性测试,另提供高级渠道管理

🤖 CLAUDE.mdclaude codecodex
claudeapi
89
Updated 2h ago

utensils / mcp-nixos

827

MCP-NixOS - Model Context Protocol Server for NixOS resources

🔌 MCP Serverclaude codeclaude desktop
mcppython
89
Updated 3d ago

rekog-labs / MCP-Nest

706

A NestJS module to effortlessly create Model Context Protocol (MCP) servers for exposing AI tools, resources, and prompts.

🔌 MCP Serverclaude codeclaude desktop
mcp
89
Updated 1d ago

cyanheads / obsidian-mcp-server

674

Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.

🔌 MCP Serverclaude codeclaude desktop
mcptypescript
89
Updated 4d ago

provos / ironcurtain

602

A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

🔌 MCP Serverclaude codeclaude desktop
mcpsecurityrust
89
Updated 3d ago

StuMason / coolify-mcp

586

MCP server for Coolify — 42 optimized tools for managing self-hosted PaaS through AI assistants

🔌 MCP Serverclaude codeclaude desktop+1
mcptypescript
89
Updated 10h ago

hetpatel-11 / Adobe_Premiere_Pro_MCP

528

Adobe Premiere Pro MCP. Tools for AI-driven video editing via MCP, for Codex, Claude, and other MCP clients.

🔌 MCP Serverclaude codeclaude desktop+2
mcpautomation
89
Updated 5d ago

RekklesNA / ProxmoxMCP-Plus

524

Use MCP and OpenAPI to safely control Proxmox VE VMs, LXCs, backups, and snapshots from LLMs and AI agents.

🔌 MCP Serverclaude codeclaude desktop
mcpapiautomation
89
Updated 4d ago

shinpr / claude-code-workflows

679

Development workflows for Claude Code that keep broad exploration focused on the outcome you approved.

📄 SKILL.mdclaude code
skilldevelopmentreview
89
Updated 1d ago

bjgreenberg / senior-engineering-partner

148

A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/Apps Script/JS). Security-first, phase-aware engineering discipline with a spec→plan→TDD→verify workflow.

📄 SKILL.mdclaude code
skillsecurityreview+1
89
Updated 3d ago

ara-mkr / Wonder-Pill

122

A Claude skill that turns brainstorming into an interactive mind map of inverted assumptions — no answers, no ranking, just provocations.

📄 SKILL.mdclaude codecodex
skill
89
Updated 6d ago

skymanbp / cc-tree

107

Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit) for divergent ideation, adversarial critique, and design-space exploration. 12 framings × hard-ban-on-incomplete-leaves × stable convergence.

📄 SKILL.mdclaude code
skilldesignsecurity+1
89
Updated 5d ago

praneybehl / llm-wiki-plugin

100

Andrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-maintaining, scalable markdown knowledge base.

📄 SKILL.mdclaude codegemini cli+2
skill
89
Updated 5d ago

Sylinko / Everywhere

6.3k

On-screen aware AI assistant for your desktop. Uses current app context, multiple LLMs, and MCP tools to help you act across apps.

🔌 MCP Serverclaude codeclaude desktop+1
mcp
89
Updated 10h ago

nimbalyst / nimbalyst

1.7k

Nimbalyst - The open-source visual workspace for Claude Code, Codex, and OpenCode. Run multiple coding agents in parallel, edit their work visually in markdown, mockups, and diagrams, and track tasks.

📦 Otherclaude codecodex
mcp
89
Updated 1d ago

decodingai-magazine / building-a-coding-agent-from-scratch-course

373

From agent user to agent builder: build a Claude Code-style coding agent from scratch in Python: 8 articles, 4 videos, one codebase

📦 Otherclaude code
python
89
Updated 10h ago