byglitchwerks· 15 skills
Use when the user wants a judgment-level read on whether a Claude Code session stayed on task — did the agent do what was originally asked, and what did it acknowledge skipping. This is the interpretive (LLM) complement to the deterministic session-audit CLI: 1a extracts ask-vs-done for free; this skill adds the Variance and What was NOT done judgment that a parser can't compute, then persists a combined record for drift analysis.
$npx -y skills add glitchwerks/claude-prospector --skill session-analysisInstalls into the current project.
Run `npx skills use "https://github.com/glitchwerks/claude-prospector" --skill "glitchwerks/claude-prospector/session-analysis"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/glitchwerks/claude-prospector" that are relevant to the current task. Run `npx skills add "https://github.com/glitchwerks/claude-prospector"` and select the relevant skills, then follow their instructions.