skills
anthropics
Public repository for Agent Skills
evalstate/fast-agent
fast-agent is a tool for DeepSeek Harness. Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
A mature, actively maintained Python agent framework with broad MCP/ACP/A2A support and strong docs, worth installing fo
README shows a CI badge (main-checks.yml), PyPI packaging, a docs helper script, and claims of end-to-end tested MCP feature support including Sampling and Elicitations.
Install is via standard PyPI/uv tooling with no download-and-execute curl pipes, and OAuth secrets use KeyRing storage, though no explicit security policy or audit is shown.
Solves real agent-building pain points with CLI-first workflows, shell mode, skills, MCP client/server, ACP integration, and multi-provider model support.
Last updated 2026-09-11, not archived, 3918 stars, active CI badge, and a Discord community indicate ongoing development.
README provides concrete install and usage commands plus a dedicated fast-agent.ai site and in-repo docs/ directory, though depth beyond the excerpt is unverified.
Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.
Loading GitHub README...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryINSTALL REFERENCE
uv tool install -U fast-agent-mcpThis command was extracted from an explicit README install reference and is display-only; the DSH host will not execute it automatically.
PROJECT TOPICS
VALIDATION LADDER
FAQ
Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support
fast-agent has 3,918 stars and 443 forks on GitHub, last updated 2026-09-11.
fast-agent is distributed under the Apache-2.0 license.
fast-agent is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:agent-skills、skills。