self-improve — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited self-improve (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
This skill is the workflow backbone for the self-improve plugin. It is invoked indirectly via slash commands. Each command in commands/*.md calls into this skill with a specific sub-task.
coupling.json, report missing impacted artifacts.See the following files in references/:
lesson-template.mdcoupling-template.mdcontradiction-check.mdcuration-prompt.mdscope-judge-prompt.mdbootstrap-scan-prompt.mdimprove-skill-prompt.mdWhen you load a lesson file (because its Use when ... description matched the current task), inspect the body for inline file/symbol references. Heuristic: backtick-quoted strings matching:
\.(ts|tsx|js|jsx|md|json|yml|yaml|py|sh|sql)$/, ./, ~/, or containing /(For each detected reference:
$HOME for path-like ~/...).📌 Lesson \<slug>\ references missing \<symbol-or-path>\ — \/curate <slug>\ to fix.Do not surface this for every lesson — only when a missing reference is detected. Skip the check on lessons that don't have inline file/symbol references.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.