Агенты и мультиагенты

skills — Reusable agent skills and workflows

anthropics/skills

Public repository for Agent Skills

★ 170,6KЗвёзды
⑂ 20,3KФорки
1124Открытые проблемы
MarkdownЯзык
Лицензия
Q82Редакционная оценка

Скриншоты проекта

Скриншот skills — Reusable agent skills and workflows Скриншот skills — Reusable agent skills and workflows

Обзор

anthropics/skills is an open-source project in ToolAI's Agents and multi-agent systems category. Public repository for Agent Skills The page is intended to help technical readers decide whether the project is worth a closer review; it is not an endorsement. The Markdown implementation and the repository owner anthropics are recorded from the catalog metadata.

Основные функции

  • Official repository maintained by anthropics; the repository description identifies it as reusable agent skills and workflows.
  • Primary language recorded for this editorial entry: Markdown.
  • Repository statistics and links are shown as a dated metadata snapshot, so readers can re-check them before adoption.
  • The official README, releases and issue tracker remain the source of truth for installation and compatibility details.

Требования, установка и быстрый старт

Requirements depend on the current official documentation. Start with the repository's README and pin a reviewed release before production use.

git clone https://github.com/anthropics/skills
cd skills

Use the project's documented environment manager, model weights and optional accelerators. Do not copy commands from an unverified mirror; check the release notes and lock compatible dependencies first.

Использование

This page is an objective orientation for reusable agent skills and workflows. Read the official quick-start example, run it in an isolated environment, and record the exact commit or release used. For an agent or model workflow, keep tool permissions narrow, validate external inputs, and measure latency and quality on a representative test set. The repository's README and examples should be consulted for API details that may change.

Совместимость моделей и варианты использования

The repository metadata describes the project scope but does not guarantee compatibility with every model, provider, checkpoint or accelerator. Confirm supported model identifiers, tokenizer versions, hardware requirements and license terms in the official documentation before connecting it to an LLM, agent, MCP server or RAG pipeline.

Лицензия и примечания о рисках

GitHub metadata reports the repository license as License not detected. Review the repository LICENSE and any separate model, dataset, weight or third-party dependency terms before redistribution or commercial use. A missing or NOASSERTION license is not a grant of permission.

Editorial verification 2026-08-02: official repository URL, owner, description, license field and repository statistics were reviewed. License metadata: License not detected. Re-check README, releases and dependency/model terms before production use.

Релиз и сопровождение

Snapshot: 164,178 stars, 19,493 forks and 1,050 open issues; repository creation is not stated and last pushed date is 2026-07-24 when supplied by the catalog. Check the official releases page for the current version rather than treating these numbers as a guarantee of maintenance or quality.

Firecrawl

firecrawl/firecrawl

★ 161,1KTypeScript

LangChain

langchain-ai/langchain

★ 143,6KPython

RAGFlow

infiniflow/ragflow

★ 86,7KGo