Summary
You install a bunch of skills but your agents don't know when to reach for them. This fixes that by scanning your project context, scoring installed skills for relevance, and generating trigger-based guidance that goes into CLAUDE.md or AGENTS.md. Run it when you first set up a project with skills, after installing new ones, or when your guidance feels stale. It's built around three TypeScript scripts that analyze your project type, scan skill metadata, and generate categorized "when to use this" sections. The honest take: this is infrastructure for infrastructure, solving the cold start problem where skills sit unused because nobody documented when they apply.
Install to Claude Code
npx -y skills add jwynia/agent-skills --skill skill-integrator --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
