Search skills/

Claude skill creator and other skills that build skills

62 skills and skill packs reviewed. Sorted by verdict, then depth — how much real expertise ships with the skill — not by popularity.

Our picks

skill-creator

skill in anthropics/skills

Anthropic's skill for writing new skills and improving them with test prompts, graders, a review viewer and trigger-description optimization.

Recommended Check first Depth 5/5

Lark CLI (lark-cli)

larksuite/cli

The official Lark/Feishu command-line tool with 200+ commands and about 29 agent skills for messaging, docs, Base, sheets, calendar, mail, tasks and more.

Recommended Check first Depth 4/5

Anthropic Agent Skills

anthropics/skills

Anthropic's reference skills repo: 20 skills including document tools (docx, pptx, xlsx, pdf), frontend-design, skill-creator and mcp-builder.

Recommended Check first Depth 4/5

All 62 reviewed

How we review
Skill Verdict Security Depth Stars Installs
skill-creator skill in anthropics/skills Anthropic's skill for writing new skills and improving them with test prompts, graders, a review viewer and trigger-description optimization.
Recommended Check first 5/5 185K 418K
Lark CLI (lark-cli) larksuite/cli The official Lark/Feishu command-line tool with 200+ commands and about 29 agent skills for messaging, docs, Base, sheets, calendar, mail, tasks and more.
Recommended Check first 4/5 18K 12M
Anthropic Agent Skills anthropics/skills Anthropic's reference skills repo: 20 skills including document tools (docx, pptx, xlsx, pdf), frontend-design, skill-creator and mcp-builder.
Recommended Check first 4/5 185K 3.6M
UI UX Pro Max nextlevelbuilder/ui-ux-pro-max-skill A design skill backed by searchable style, palette and font catalogs, with a design-system generator and five companion design skills.
Recommended Check first 4/5 142K 421K
google-agents-cli-workflow skill in google/agents-cli The entry skill of agents-cli: a phased agent-development lifecycle from design dialogue through scaffold, build, eval, deploy, publish and observe.
Recommended Check first 4/5 6.2K 520K
google-agents-cli-eval skill in google/agents-cli Teaches an agent to evaluate ADK agents: dataset schema, built-in and custom metrics, LLM-as-judge scoring and an eval-fix loop.
Recommended Check first 4/5 6.2K 519K
SkillSpector NVIDIA/SkillSpector NVIDIA's open-source security scanner for agent skills, with 71 detection patterns, optional LLM review and a skill-inspector skill.
Recommended Check first 4/5 23K —
task-observer (One Skill to Rule Them All) rebelytics/one-skill-to-rule-them-all A meta-skill that watches your sessions, logs corrections and repeated work, and proposes improvements to your other skills for you to approve.
Recommended Check first 4/5 3.6K —
Cisco Skill Scanner cisco-ai-defense/skill-scanner Cisco AI Defense's open-source scanner for agent skills: YARA and YAML rules, dataflow analysis and an optional LLM judge, with SARIF output and a pre-commit hook.
Recommended Check first 4/5 2.7K —
delegate-skills amElnagdy/delegate-skills Twenty skills that hand a coding task to another agent CLI (Codex, Cursor, Aider, Claude and many more) in the background, then leave the diff review and commit to you.
Recommended Broad access 4/5 2.5K —
skills (the npx skills CLI) vercel-labs/skills Vercel Labs' open-source CLI (npx skills) for installing, updating and removing agent skills across Claude Code, Codex, Cursor, OpenCode and dozens more agents.
Recommended Check first 3/5 37K 4.1M
writing-for-agents skill in mattpocock/skills A guide to writing skills, AGENTS.md/CLAUDE.md and other agent-read docs: context pointers, progressive disclosure, completion criteria.
Recommended No issues 3/5 306K 488K
google-agents-cli-adk-code skill in google/agents-cli A reference skill for writing Agent Development Kit code in Python or Go: agent types, tools, callbacks, state, orchestration and recipes.
Recommended Check first 3/5 6.2K 521K
google-agents-cli-scaffold skill in google/agents-cli Covers agents-cli scaffold create, enhance and upgrade: choosing a template, deployment target, CI/CD runner and session storage for a new agent project.
Recommended Check first 3/5 6.2K 519K
google-agents-cli-observability skill in google/agents-cli Covers monitoring deployed agents: Cloud Trace, prompt-response logging, BigQuery Agent Analytics and third-party tools such as Phoenix or AgentOps.
Recommended Check first 3/5 6.2K 519K
Google Antigravity SDK skill google-antigravity/antigravity-sdk-python A skill that teaches a coding agent to build, configure and debug agents with Google's Antigravity Python SDK, with reference docs and starter examples.
Recommended Check first 3/5 3.9K —
ask-matt skill in mattpocock/skills A router over the other skills in the repo: describe your situation and it recommends which skill or flow fits.
Recommended No issues 2/5 306K 787K
intellectronica agent skills intellectronica/agent-skills A personal collection of 44 mostly small skills: API wrappers for Notion, Todoist, Anki and Context7, image generation, Mermaid rendering and git setup.
Recommended Check first 2/5 298 96K
Markstream skills Simon-He95/markstream-vue Eleven integration skills for the Markstream streaming Markdown renderers (Vue, Nuxt, React, Svelte, Angular) used in AI chat interfaces.
Recommended Check first 2/5 3.0K —
Google agents-cli google/agents-cli Google's CLI and seven skills that teach a coding agent to scaffold, build, evaluate, deploy and observe ADK agents on Google Cloud.
With caveats Check first 4/5 6.2K 3.6M
Paperclip paperclipai/paperclip A self-hosted app for orchestrating teams of AI agents with org charts, budgets and approvals; its skills are mostly maintainer workflows.
With caveats Broad access 4/5 108K —
google-agents-cli-deploy skill in google/agents-cli Guides an agent through deploying ADK and other agents to Agent Runtime, Cloud Run or GKE, with Terraform, CI/CD, secrets and rollback.
With caveats Check first 4/5 6.2K 520K
NanoClaw nanocoai/nanoclaw A small self-hosted assistant that runs Claude agents in Docker containers and connects to chat apps, extended by about 35 Claude Code setup skills.
With caveats Broad access 4/5 31K —
Distilly titanwings/distilly Skill that distills a person's messages, documents and public material into a reusable Person Profile packaged as an agent skill.
With caveats Broad access 4/5 26K —
memU NevaMind-AI/memU Memory layer that mines agent session logs into a shared markdown wiki and re-injects it across Codex, Claude Code, Cursor and others, locally or via memU Cloud.
With caveats Broad access 4/5 15K —
ModLens liustack/modlens Gives text-only models (DeepSeek, GLM) the ability to read pasted images, converting them to structured JSON (OCR, layout, semantics) via ten vision backends.
With caveats Broad access 4/5 4.6K —
Claude Octopus nyldn/claude-octopus An escalation layer that runs tasks past up to twelve external AI providers (Codex, Copilot, Ollama, Grok, more) with a consensus gate, plus 63 skills.
With caveats Check first 4/5 4.3K —
Babysitter a5c-ai/babysitter An npm-installed orchestration runtime that makes coding agents follow workflows defined in JS code, with quality gates, approval breakpoints and a run journal.
With caveats Broad access 4/5 1.9K —
daymade Claude Code Skills daymade/claude-code-skills A marketplace of about 120 skills from one author: skill-creator fork, audio and transcription tools, Claude Code and Codex ops, research, QA and more.
With caveats Broad access 4/5 1.5K —
Caveman JuliusBrussee/caveman A token-saving pack that makes agents answer in terse "caveman" prose, plus an optional CLI with output trimming, model routing and usage telemetry.
With caveats Broad access 3/5 116K 4.4M
ECC (Everything Claude Code) affaan-m/ECC A very large Claude Code harness: 311 skills, 71 agents, commands, hooks, memory, rules and a scanner, with adapters for Codex, Cursor and others.
With caveats Broad access 3/5 292K —
hyperframes-cli skill in heygen-com/hyperframes A command guide for the HyperFrames CLI: scaffold, check, snapshot, edit the timeline, preview, render locally or in the cloud, and recover from failures.
With caveats Broad access 3/5 75K 1.3M
Browser Use browser-use/browser-use Seven skills around the Browser Use browser agent: drive local Chrome over CDP, use the paid cloud API, run QA scoring, or pay by crypto wallet.
With caveats Broad access 3/5 119K 98K
OmO (oh-my-openagent) code-yeongyu/oh-my-openagent An agent harness and CLI (omo) with multi-model orchestration; its .agents/skills folder holds mostly maintainer workflows for the project itself.
With caveats Broad access 3/5 70K —
Agentic Awesome Skills (AAS) sickn33/agentic-awesome-skills A catalog of roughly 2,900 community SKILL.md playbooks, with a local CLI, MCP server and plugin bundles for searching and installing them.
With caveats Check first 3/5 49K —
Claude Plugins Official anthropics/claude-plugins-official Anthropic's official Claude Code plugin marketplace: first-party plugins such as skill-creator and plugin-dev, plus external channel plugins.
With caveats Broad access 3/5 45K —
Awesome GitHub Copilot github/awesome-copilot GitHub's community-contributed library of 466 skills plus agents, instructions, hooks and plugins for Copilot, installable per plugin from a marketplace.
With caveats Check first 3/5 41K —
Claude Code Templates davila7/claude-code-templates A large catalog and npx installer (aitmpl.com) of agents, commands, hooks, MCP configs and skills for Claude Code, much of it collected from other authors.
With caveats Broad access 3/5 33K —
Context Mode mksglu/context-mode MCP server plus hooks that keep bulky tool output out of the context window, index it in local SQLite, and restore session state after compaction.
With caveats Broad access 3/5 33K —
Claude Skills (alirezarezvani) alirezarezvani/claude-skills A 400+ skill library of agents, personas and commands for engineering, marketing, product, compliance and C-level work, mirrored for 13 coding agents.
With caveats Check first 3/5 29K —
Skill Seekers yusufkaraaslan/Skill_Seekers Python tool and MCP server that converts documentation sites, repos, PDFs and other sources into agent skills and RAG-ready knowledge, with 22 export targets.
With caveats Check first 3/5 15K —
Claude Code Infrastructure Showcase diet103/claude-code-infrastructure-showcase A reference setup for Claude Code: hooks that auto-activate skills, a skill-rules.json config, and Node/Express/React stack guides to copy into your project.
With caveats Broad access 3/5 10K —
HTML Anything nexu-io/html-anything Local agentic HTML editor with 75 skills across 9 surfaces (magazine, deck, social cards) that drives a logged-in coding-agent CLI to write and preview HTML.
With caveats Broad access 3/5 9.3K —
Harness revfactory/harness A Claude Code meta-skill that designs a project-specific agent team, writes the agent definitions and skills for it, and has an evolve skill to refine them from feedback.
With caveats No issues 3/5 9.3K —
universal-modder rehan-remade/universal-modder A 13-skill pack and `um` CLI for modding PC games: game recon, reverse engineering, fal-generated art, in-game testing, video and a field-notes knowledge base.
With caveats Check first 3/5 9.2K —
awesome-agentic-ai-zh WenyuChiou/awesome-agentic-ai-zh A trilingual (CN/EN) learning roadmap for agentic AI with 240+ curated links, hands-on exercises and one example skill, tool-calling-tutor.
With caveats Check first 3/5 8.1K —
Snyk Agent Scan snyk/agent-scan Snyk's CLI scanner that discovers installed agents, MCP servers and skills on your machine and checks them for prompt injection and other risks.
With caveats Check first 3/5 3.2K —
ScienceClaw beita6969/ScienceClaw A research agent system built on the OpenClaw gateway whose Skills and typed Operators are updated only after a replay-verified execution; ships with 319 skills.
With caveats Check first 3/5 1.0K —
retro skill in mattpocock/skills After a session, reviews the logs and suggests fixes to the agent's environment: navigation, automated checks, standards and steering files.
With caveats No issues 2/5 306K 295K
Orca stablyai/orca An open-source desktop and mobile app for running several coding agents in parallel git worktrees, plus 11 thin skills that hand agents the app's CLI.
With caveats Check first 2/5 109K 948K
Google Workspace CLI (gws) googleworkspace/cli A command-line tool for Drive, Gmail, Calendar, Sheets, Docs and Chat that builds its commands from Google's Discovery Service, plus about 40 thin agent skills.
With caveats Check first 2/5 32K 361K
wshobson/agents wshobson/agents A multi-harness plugin marketplace with 94 plugins, 202 agents, 185 skills and 105 commands for Claude Code, Codex, Cursor, OpenCode, Copilot, Antigravity and Pi.
With caveats Check first 2/5 42K 165K
google-agents-cli-publish skill in google/agents-cli Explains how to register a deployed agent with Gemini and manage agents in Agent Registry using agents-cli publish gemini.
With caveats Check first 2/5 6.2K 520K
herdr herdrdev/herdr A Rust terminal multiplexer for coding agents, with a skill that lets one agent split panes, start other agents and wait on them.
With caveats Check first 2/5 46K 75K
Agentix CEO skill agentix-cloud/skills One skill that turns your agent into a manager of remote Claude Code workers on the Agentix hosted platform, using your Anthropic and GitHub tokens.
With caveats Broad access 2/5 1 75K
Internet Court Skill internet-court/internet-court-skill A router skill plus connectors and vendored crypto-protocol skills (x402, ERC-7710, escrow, GenLayer) for agents that pay and contract with other agents.
With caveats Broad access 2/5 7.0K —
Claude Code Guide (zebbern) zebbern/claude-code-guide A long community README guide to Claude Code plus 79 mixed skills: general developer helpers, document tools and a large group of security-testing playbooks.
With caveats Check first 2/5 4.7K —
Tons of Skills jeremylongshore/tons-of-skills-marketplace A very large marketplace of Claude Code plugins and skills (about 430 plugins, thousands of skills) with its own ccpi package manager.
With caveats Broad access 2/5 2.9K —
Best Agent Skills (Linkly) LinklyAI/best-skills A one-skill pack plus daily-updated CSV rankings of the top 100 agent skills, merged from skills.sh, ClawHub, Tencent SkillHub and social mentions.
With caveats Check first 2/5 676 —
Awesome Claude Skills (Composio) ComposioHQ/awesome-claude-skills A curated list of Claude skills plus hundreds of templated app-automation skills that run through Composio's hosted Rube MCP.
With caveats Broad access 1/5 78K —
Claude Code Best Practice shanraisshan/claude-code-best-practice A large reference repo of Claude Code tips, concept guides and sample agents, commands and skills; a guide to read, not a skill pack to install.
With caveats Check first 1/5 68K —
anbeime Skill Store anbeime/skill A Chinese-language skill store: 63 local skills (content, video, e-commerce, PPT) plus daily-synced mirrors of other authors' skills.
Skip Broad access 2/5 8.9K —

The Claude skill creator is Anthropic’s skill-creator, a skill for writing other skills and testing them. It belongs to a category we call agent tooling: skills and tools that build, install, route or evaluate other skills and agents. We reviewed 61: 19 get an install verdict, 41 come with caveats and one gets a skip.

This is the category where “skill about skills” meets real software. Some entries are prompts about prompts. Others are package managers, scanners and full agent frameworks, and they carry the permissions to match.

What to look for in a Claude skill creator or tooling skill

Ask what the tool actually does. A creator that only reformats your notes into SKILL.md adds little. One that runs your prompts, grades the results and tunes the description is a different thing. Anthropic’s format is simple: per the official docs, a skill is a folder with a SKILL.md, and the description tells Claude when to use it. The Agent Skills specification sets the field rules. See also our guide to creating a Claude skill.

Check for telemetry and installers. Package-manager style tools write into your agent folders on every install, so you want to know what they send. Check whether a router skill depends on others: it is useless without them. And check scale. Of the 61 skills, 4 are clean, 35 are marked “review” and 22 have broad access. The security page explains the labels.

  • skill-creator is Anthropic’s tool for writing and improving skills. It has a 33 KB SKILL.md, 10 Python scripts, grader and comparator prompts, a local review viewer and a train and test loop for trigger descriptions. It runs your prompts through claude -p, so run it in a project you trust. It is the most complete official option.
  • skills (the npx skills CLI) installs, updates and removes skills across Claude Code, Codex, Cursor, OpenCode and dozens of other agents. It is MIT licensed and has about 4.1 million recorded installs. It sends anonymous usage events to skills.sh by default; the review notes say you can opt out with environment variables. See how to install Claude skills.
  • writing-for-agents is clean. It is a guide to writing skills, AGENTS.md, CLAUDE.md and other documents agents read, covering progressive disclosure and completion criteria.
  • ask-matt is a clean router that recommends which skill from that repository fits your situation. It is useful if you install the whole set, and useless without the other skills.
  • google-agents-cli-workflow is the entry skill for Google’s agents-cli: a phased lifecycle from design through scaffold, build, eval, deploy, publish and observe. It tells the agent to install agents-cli, which we did not review.

Two entries to treat carefully. Lark CLI appears here because of its size, but its skills drive a workplace suite under your account; see productivity. And anbeime’s skill store is the one skip: a mirror of other authors’ work whose Chrome automation skill pre-approves any shell command and copies your real Chrome profile. Install the originals instead.

Related categories: memory skills for context tooling and security skills for scanners that check third party skills before you install them. The category page lists all 61, and how we review explains the scoring.