ubiquitous-language-4c9454 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ubiquitous-language-4c9454 (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.
Remove naming drift. Make domain terms crisp enough that humans and agents stop using one word for multiple concepts or multiple words for one concept.
Workflow does not use a top-level CONTEXT.md convention today. Durable term definitions belong in the existing truth surfaces:
PLAN.md for architectural terms and stable conceptsSTATUS.md only for active live concerns, not permanent glossary entriesDo not create a parallel glossary system unless the repo explicitly adopts one.
Collect candidate terms from:
PLAN.md, specs, and design notesFlag:
For each conflict, define:
If the choice affects architecture or public behavior, route the durable record into PLAN.md or a design note instead of leaving it in chat.
Check whether code, docs, and user language agree. If not, say which one is current, which one is historical, and which one should become canonical.
Rename only in the requested or justified scope. Large sweeps need approval. Prefer boundary-first cleanup over repo-wide cosmetic churn.
Use a compact table or bullet list:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.