skills-link: Sync your local skills across 41+ AI coding agents with a single command

by shanliuling · Agent Tool · ★ 197

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

Featured in: Skill Creation & Meta-Tools · Multi-AI Bridge & Cross-IDE Sync

How to install skills-link

npm i -g skills-link

Taken from the project's README on GitHub.

Security audit verdict: SAFE · quality 78/100

None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

🧪 Tested by Agent Skills Hub

One of 14 tools we ran end to end on the same task for our Skill & Agent Management page (2026-10-09).

Result: Installs from GitHub only, one skill per command; removal is interactive. · Installed a skill with a curl | sh script, showing only its source · removes skills cleanly · +345 tokens per session for 20 skills

See the run → · See the whole test →

aiai-codingai-toolsautomationclaudedeveloper-toolsskillsskills-sync

Quick Facts

Stars197
Forks6
LanguageTypeScript
CategoryAgent Tool
LicenseMIT
Quality Score78/100
Open Issues1
Last Updated2026-05-14
Created2026-04-12
Platformsclaude-code, node
Est. Tokens~682k

About skills-link

Skills-Link One skills folder, every AI app. Sync your local across 41+ AI coding agents with a single command. Also supports rules sync: English | 中文 How it works Every app's becomes a symlink pointing to one master directory. Add or edit a skill once — every app sees it instantly. Install Quick start That's it. First run walks you through everything — detect apps, import skills, create links.

Compatible Skills

These tools work well together with skills-link for enhanced workflows:

  • ai-first-toolkit — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (59%)
  • vsync — semantic(0.39)+complementary+same_lang+similar_pop+shared_platform (59%)
  • skillkit — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)
  • agentfiles — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)
  • maestro — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)

skills-link alternative? Top 6 similar tools

Looking for a skills-link alternative? If you're comparing skills-link with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • claudekit by duthaho · ⭐ 97

    A verification-first engineering toolkit for Claude Code. Built for senior ICs and tech leads who already know

  • Overture by SixHq · ⭐ 641

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • spacecake by spacecake-labs · ⭐ 373

    the best interface for Claude Code

  • antigravity-workflows by harikrishna8121999 · ⭐ 187

    Community-driven workflows for Antigravity AI. Like Claude Skills - reusable prompts and automation for AI cod

  • claude-historian-mcp by Vvkmnn · ⭐ 178

    📜 An MCP server for conversation history search and retrieval in Claude Code

  • claude-code-open by kill136 · ⭐ 158

    Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools