framework-doctor — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited framework-doctor (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.
Register: DISCIPLINE Goal: Make the framework eat its own dogfood before release. Core principle: a framework that enforces evidence discipline must verify its own artifacts.
Announce: "Using framework-doctor to self-audit Super Skills before release."
python3 tools/framework_doctor.py .
python3 tools/run_framework_fixtures.py .
python3 tools/epistemic_health_check.py .If the script is unavailable, run the manual checklist below.
[ ] all SKILL.md YAML frontmatter parses
[ ] every skill has a matching .nano.md
[ ] README skill count matches actual SKILL.md count
[ ] registry skill references resolve to folders
[ ] install docs version matches README
[ ] no stale v4.2 / 19 skills references
[ ] no broken shell snippets where an OR guard is followed by echo and then an AND exit without braces
[ ] shared references required by skills exist
[ ] dps.py --help works
[ ] automation scripts compile: framework_doctor, build_kb_index, epistemic_health_check, run_framework_fixtures
[ ] framework fixtures exist and are executable with `tools/run_framework_fixtures.py`
[ ] release docs reference staleness and KB-index automation
[ ] archive can be created without changing framework formatUse claim grammar:
CLAIM: Super Skills framework self-audit passes.
EVIDENCE: T1 — ran `python3 tools/framework_doctor.py .` and `python3 tools/run_framework_fixtures.py .`, exit 0.
SOURCE: command output.
SCOPE: Verifies packaging/hygiene/control-plane integrity; does not prove real-world adoption effectiveness.
RESIDUAL RISK: Requires production cycles for behavioral validation.<!-- Populated by knowledge-compound after cycles where this skill underperformed --> <!-- New entries should follow shared/gotcha-schema.md -->
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.