map — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited map (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.
Audit the structural health of the knowledge graph — what's well-connected, orphaned, and missing — to surface where the graph needs attention.
Don't: use this for targeted backlink audits — that's /backlinks. Don't auto-fix — surface findings for Shane to act on.
task: "Vault access (bash only, no MCP tools): obsidian search query='TERM' limit=10, obsidian read file='Note Name' (no .md), obsidian backlinks file='Note Name'. Audit the structure and health of the knowledge graph around '[argument]' (or the full vault). What's well-connected, what's orphaned, what's missing?"skill: "map"If Qwen is unavailable:
[argument] is provided, run obsidian search query='[argument]' limit=15 via bash; otherwise run broad searches across topic clusters via bash (e.g. obsidian search query='MOC' limit=10, obsidian search query='projects' limit=10, obsidian search query='ideas' limit=10)obsidian read file='[note name]' via bash for each — aim for breadth across different sections of the vault[[links]] in notes but don't have their own notes yet[argument], produce a local map of that cluster; if broad, produce a top-level structural overview~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.