Repository
anthropics/claude-plugins-official agent skills
- skills
- 29
- official
- 29
- GitHub stars
- 38k
GitHub description: “Official, Anthropic-managed directory of high quality Claude Code Plugins.”
- Stars
- 37,566 (4,231 forks)
- Licence
- Apache-2.0
- Last push
- Oct 2026
- Created
- Nov 2025
- Homepage
- code.claude.com/docs/en/plugins
- claude-code
- mcp
- skills
Install all skills
npx skills add anthropics/claude-plugins-officialAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in anthropics/claude-plugins-official, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart. | anthropics/ | 38k | 10 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | today |
| 2 | Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design. | anthropics/ | 38k | 7 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | today |
| 3 | Shows how Claude Code plugins keep per-project settings and state in .claude/plugin-name.local.md files with YAML frontmatter and a markdown body. | anthropics/ | 38k | 7 repos | ~3k | Automated safety check: Pass | Apache-2.0 | today |
| 4 | Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication. | anthropics/ | 38k | 11 repos | ~3.1k | Automated safety check: Pass | Apache-2.0 | today |
| 5 | Explains how to write Claude Code slash commands: Markdown files with YAML frontmatter, arguments, file references, bash context and interactive prompts. | anthropics/ | 38k | 10 repos | ~4.8k | Automated safety check: Pass | Apache-2.0 | today |
| 6 | Explains the directory layout, plugin.json manifest and component organization of a Claude Code plugin, including auto-discovery and portable paths. | anthropics/ | 38k | 10 repos | ~3.4k | Automated safety check: Pass | Apache-2.0 | today |
| 7 | Finds every CLAUDE.md file in a repository, scores each against quality criteria, shows a report, then makes targeted updates after you approve. | anthropics/ | 38k | 5 repos | ~1.5k | Automated safety check: Pass | Apache-2.0 | today |
| 8 | Scans a codebase and suggests which Claude Code hooks, subagents, skills, plugins and MCP servers fit its stack, without changing any files. | anthropics/ | 38k | 3 repos | ~2.7k | Automated safety check: Notes | Apache-2.0 | today |
| 9 | Explains how to design and write skills for Claude Code plugins: SKILL.md frontmatter, bundled scripts, references and assets, and descriptions that trigger at the right time. | anthropics/ | 38k | 9 repos | ~5.6k | Automated safety check: Pass | Apache-2.0 | today |
| 10 | Builds a personal Claude Code usage and impact report entirely from local session transcripts and git history, for self-review or justifying usage to a manager. | anthropics/ | 38k | — | ~4.3k | Automated safety check: Warn | Apache-2.0 | today |
| 11 | Explains the hookify rule file format: markdown with YAML frontmatter that watches bash commands, file edits, prompts or stop events and warns or blocks. | anthropics/ | 38k | 6 repos | ~2.1k | Automated safety check: Notes | Apache-2.0 | today |
| 12 | Entry point for building an MCP server: asks about the use case, picks a deployment model and tool-design pattern, then hands off to more specialized skills. | anthropics/ | 38k | 1 repo | ~3k | Automated safety check: Pass | Apache-2.0 | today |
| 13 | Guides building an MCP app: an MCP server that also serves interactive UI widgets such as forms, pickers and confirm dialogs, rendered inline in chat hosts like Claude and ChatGPT. | anthropics/ | 38k | — | ~4.7k | Automated safety check: Pass | Apache-2.0 | today |
| 14 | Manages who can reach Claude through a Discord channel: approve pairing codes, edit the allowlist and set direct-message and group policy. | anthropics/ | 38k | 1 repo | ~1.1k | Automated safety check: Pass | Apache-2.0 | today |
| 15 | Saves a Telegram bot token for the Telegram channel plugin and reviews who may message the bot, steering the policy toward a fixed allowlist. | anthropics/ | 38k | 1 repo | ~1.1k | Automated safety check: Notes | Apache-2.0 | today |
| 16 | Builds a single-file HTML explorer with visual controls, a live preview and a copyable prompt, using one of six templates chosen to fit the topic. | anthropics/ | 38k | 1 repo | ~949 | Automated safety check: Pass | Apache-2.0 | today |
| 17 | Bundles a local MCP server together with its runtime into one installable file, so a user doesn't need Node or Python set up themselves. | anthropics/ | 38k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | today |
| 18 | Solve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. | anthropics/ | 38k | — | ~5k | Automated safety check: Pass | Apache-2.0 | today |
| 19 | Approves iMessage pairing requests, edits the sender allowlist and sets DM or group policy, acting only on commands typed in the terminal, never on channel messages. | anthropics/ | 38k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | today |
| 20 | Adds apps to the Cardputer-Adv MicroPython bundle and pushes changed files, serial logs and one-off REPL commands to a device that is already set up. | anthropics/ | 38k | — | ~461 | Automated safety check: Pass | Apache-2.0 | today |
| 21 | Detects a newly connected M5Stack ESP32 board over USB, flashes UIFlow 2.0 firmware and installs the Claude Buddy MicroPython apps, or reruns single steps of that flow. | anthropics/ | 38k | — | ~5.9k | Automated safety check: Notes | Apache-2.0 | today |
| 22 | Scans a whole codebase or a set of changes for security issues, and turns findings into verified patch files that you apply yourself. | anthropics/ | 38k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | today |
| 23 | Saves a Discord bot token, reports channel status and steers you toward a locked-down access policy for who can reach your assistant. | anthropics/ | 38k | — | ~1.1k | Automated safety check: Notes | Apache-2.0 | today |
| 24 | Checks that iMessage can be read on a Mac, shows the access policy and sender allowlist, and helps you decide who may text your assistant. | anthropics/ | 38k | — | ~877 | Automated safety check: Notes | Apache-2.0 | today |
| 25 | Builds and publishes a tabbed status page for a project with several workstreams, kept current by refreshing the same private page. | anthropics/ | 38k | — | ~5.1k | Automated safety check: Pass | Apache-2.0 | today |
| 26 | Builds an explorable HTML report of Claude Code usage over a chosen period: tokens, cache behavior, subagents, skills and costly prompts. | anthropics/ | 38k | — | ~784 | Automated safety check: Pass | Apache-2.0 | today |
| 27 | An example user-invoked skill that demonstrates frontmatter options and the skills/<name>/SKILL.md layout | anthropics/ | 38k | — | ~306 | Automated safety check: Notes | Apache-2.0 | today |
| 28 | Solves one hard mathematics problem in a single session without subagents, keeping settled steps in a notes file and ending with a self-contained proof.md. | anthropics/ | 38k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | today |
| 29 | Work on one hard mathematics problem in rounds: each round a judge writes a few self-contained questions, independent workers answer them, and the judge keeps a ledger of what is proved, refuted and… | anthropics/ | 38k | — | ~19k | Automated safety check: Warn | Apache-2.0 | today |
Questions, answered from the data.
What is the best skill in anthropics/claude-plugins-official?
Hook Development for Claude Code Plugins (official) from anthropics/claude-plugins-official ranks first of the 29 skills in anthropics/claude-plugins-official listed here, with the highest score: its repository has 38k GitHub stars, 10 other GitHub owners carry a copy, its SKILL.md loads about 4.1k tokens and it has informational notes only in the automated safety check. Next come Claude Code Agent Development and Plugin Settings Pattern.
Are the skills in anthropics/claude-plugins-official official?
29 of the 29 skills in anthropics/claude-plugins-official are official, published by the vendor's own GitHub organization: Hook Development for Claude Code Plugins, Claude Code Agent Development, Plugin Settings Pattern, MCP Integration for Plugins, Claude Code Command Development and 24 more.
How do I install all skills from anthropics/claude-plugins-official?
Run npx skills add anthropics/claude-plugins-official in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.