skill-gap-detector

To detect missing skills from repeated-instruction patterns, analyze clustered inline instructions from transcripts to surface recurring tasks that lack dedicated skills. This process identifies gaps by comparing repeated instruction clusters against your existing skill catalog to highlight redundancies.

A skill-gap detector works by reading repeated-instruction clusters from evolution-engine reports and comparing them against existing skills to surface missing capabilities. It operates within maintenance workflows or cron-driven loops to identify when users repeatedly reinvent instructions that should be formalized into skills.

No, you cannot automatically install proposed skills because the detector drafts new SKILL.md scaffolds strictly for human review without auto-installation. It writes draft files under the proposed-skills directory, ensuring a human manually reviews and approves each new skill scaffold before activation.

To draft new SKILL.md scaffolds from repeated instruction clusters, run the detector pipeline to compare clustered instructions against existing skills and generate kebab-case scaffold files. These drafts are written to the proposed-skills directory for human review without automatic installation.

The skill-gap detector relies on evolution-engine outputs because it is triggered after the evolution-engine reports clusters of repeated instructions. It reads these clusters to compare against existing skills and propose new kebab-case skill scaffolds, making the evolution-engine reports a necessary input.

A limitation of automated skill scaffolding is that it cannot auto-install proposed skills, requiring manual human review of every draft SKILL.md file. Additionally, it depends on pre-existing evolution-engine cluster reports to function, limiting standalone use in maintenance workflows.