skills
anthropics
Public repository for Agent Skills
REVIEW SCORECARD
✓ 无Risky检出 · 自动化扫描结果仅供参考,非官方背书
AI DEEP REVIEW
A well-documented, actively maintained tool that solves config drift for multi-agent AI coding setups with local-first,
README describes a deterministic, LLM-free scoring system, diff-based proposals, backups to .caliber/backups/, and an undo command, indicating deliberate engineering rigor, though no test or CI details are visible.
Bootstrap is stated to be 100% local with no code sent anywhere and generation uses the user's own API key, but the install command is unknown and the README's curl-pipe-bash mention for Cursor Agent CLI warrants mild caution.
Directly addresses the common pain point of stale hand-written CLAUDE.md/.cursorrules files by auto-refreshing configs on every commit across Claude Code, Cursor, Codex, OpenCode, and Copilot.
Last updated 2026-07-26 with 1268 stars, an active npm package, and no archive flag, indicating ongoing development.
README covers install steps, Windows caveats, a before/after score example, and the audit-first workflow, but the install command field is unknown and the excerpt is truncated mid-section.
Generated by AI after reading the project README, as a decision aid; neutral scores are given when information is thin. Not an official endorsement.
正在读取 GitHub README...
README 暂时无法读取。
前往仓库PROJECT TOPICS
VALIDATION LADDER
FAQ
Continuously sync your AI setups with one command. Codebase tailor suited agent skills, MCPs and config files for Claude Code, Cursor, and Codex.
ai-setup has 1,268 stars and 123 forks on GitHub, last updated 2026-07-26.
ai-setup is distributed under the MIT license.
ai-setup 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
System reads GitHub Topics first, then compares against the in-site category dictionary and word-root rules. Current match:skills。