Table of Contents
Section: From Anthropic · by Anthropic - Anthropic's official repository for Agent Skills — the SKILL.md format, a skill template, and example skills, the same format Claude Code loads natively.
FreshScore 94
Entry
docx
Appears in 9 awesome lists
by Anthropic - Anthropic's official repository for Agent Skills — the SKILL.md format, a skill template, and example skills, the same format Claude Code loads natively.
Open github.comanthropics/skills
Found in these lists
Awesome Claude Design
Section: Official Resources · the underlying skill Claude Design routes through; auto-loaded by Claude Code for UI work
ActiveScore 68
Awesome Claude Skills
Section: Document Skills · Create, edit, and analyze Word documents with support for tracked changes, comments, formatting preservation, and text extraction
ActiveScore 73
Awesome LLM Resources
Section: 技能 Skills
FreshScore 87
Awesome Llm Skills
Section: Document Processing · Create, edit, analyze Word docs with tracked changes, comments, formatting.
ActiveScore 74
Awesome Open Source AI
Section: 4. Agentic AI & Multi-Agent Systems · Official collection of Agent Skills and reference implementations for Claude Code, Claude API, and AI agents. Apache 2.0 licensed.
FreshScore 89
Awesome Prompts
Section: Agent Skills · Official collection + spec (/spec/agent-skills-spec.md)
FreshScore 90
Awesome React Native
Section: Agents & Skills · Anthropic's public repository of agent skills, usable with Claude Code and other agents.
FreshScore 87
awesome-python
Section: Other · Public repository for Agent Skills
FreshScore 81
Often listed next to it
Claude Cookbooks
Anthropic's official notebook collection covering orchestrator-worker patterns, parallel tool calling, programmatic tool calling (PTC), context compaction, and Agent SDK examples. The patterns/agents/ directory is the reference implementation of every orchestration pattern described in Building…
In 6 listsDetails
Effective Context Engineering for AI Agents
Anthropic's systematic guide to managing the full context state—system prompts, tools, MCP, and message history—as a finite, curated resource. Reframes harness design as "what configuration of context produces the desired behavior?" rather than just prompt wording.
In 5 listsDetails
Official Plugin Directory
by Anthropic - Anthropic's official, curated directory of high-quality Claude Code plugins, installable from within Claude Code.
In 3 lists
claude-code-action
by Anthropic - The official GitHub Action for running Claude Code in CI: mention @claude in issues and pull requests to delegate code changes, reviews, and fixes.
In 3 lists
Prompt engineering overview
Techniques for defining success criteria, testing prompts, and improving model behaviour.
In 3 lists
claude-code-security-review
by Anthropic - An official AI-powered security-review GitHub Action that uses Claude to analyze pull-request diffs for vulnerabilities.
In 2 lists
Building Effective Agents
by Anthropic - Anthropic's foundational taxonomy of agent patterns — prompt chaining, routing, orchestrator-workers, and evaluator-optimizer — and when to use each.
In 2 lists
How We Built Our Multi-Agent Research System
by Anthropic - A practical account of orchestrator and subagent coordination, prompt design, and evaluation that maps directly to Claude Code's subagents and agent teams.
In 2 lists