# anthropics/skills

Public repository for Agent Skills

Repository: https://github.com/anthropics/skills
Canonical: https://ross.abutalabs.com/products/anthropics-skills
Language: Python
License Family: other
Topics: agent-skills
Last push: 2026-08-21T17:10:55+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 24
- inputs: {"age_days": 345, "days_push": 12, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 171833, forks 20426 (observed 2026-08-28T04:12:24.429629+00:00)

## What it is
Anthropic's public repository of Agent Skills for Claude—folders of instructions, scripts, and resources that Claude loads dynamically to perform specialized tasks. It includes example skills, a skill template, and the Agent Skills specification.

## Use cases
- teach claude to create branded documents
- write custom skills for claude code
- learn how agent skills work
- automate enterprise workflows with claude
- generate mcp servers with an agent
- find examples of skill patterns for ai agents

## When to choose
- you want ready-made or example skills for Claude or Claude Code
- you are building your own skills and need a template or the Agent Skills spec
- you want reference implementations of production skills like docx/pdf/pptx/xlsx creation

## When to avoid
- you need a general-purpose agent framework rather than Claude-specific skill definitions
- you need production-grade open-source code—the document skills are source-available, not open source
- you use an LLM platform without support for the Agent Skills standard

## Facets
- artifact type: learning-resource
- maturity: active
- function: agent-framework, prompt-engineering, developer-tools, documentation, pdf, mcp
- domain: artificial-intelligence, large-language-models, developer-tools, tutorials
- platform: python, cross-platform
- tags: agent-skills, claude, skill-templates, anthropic, skill-specification, ai-agents, automation

## Member repositories
- anthropics/skills (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:24.429629+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:10:51.400658+00:00, confidence not recorded.
  - readme: https://github.com/anthropics/skills (fetched 2026-08-28T04:12:24.429629+00:00, sha 51fc6abef975)
- Data as of 2026-08-30T08:39:29.467469+00:00.