Summary
When you need to verify that a Claude Code skill actually did what it was supposed to, this parses session logs and compares them against the SKILL.md spec. It digs through your ~/.claude/ debug logs to extract SubAgent calls, hook triggers, and artifact changes, then builds a pass/fail report. Honestly most useful when you're debugging why a skill isn't behaving right or when you're building new skills and want to confirm the hooks and SubAgents fired in the right order. The scripts handle the grep patterns for you, which saves time since the log format isn't exactly intuitive. Think of it as a test suite for skills that already ran.
Install to Claude Code
npx -y skills add ai-native-camp/camp-2 --skill session-analyzer --agent claude-codeInstalls into .claude/skills of the current project.
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor makes coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
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
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Capacitor makes coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
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 →
