connect — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited connect (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.
Surface the non-obvious bridges between two concepts the vault hasn't linked yet — the value is in connections that surprise, not the ones you'd expect.
Don't: use this to find existing links — that's /backlinks. Don't surface connections already stated in either note.
task: "Vault access (bash only, no MCP tools): obsidian search query='TERM' limit=10, obsidian read file='Note Name' (no .md). Find non-obvious bridges between '[argument]' and other concepts in the vault. What unexpected connections exist? What synthesis hasn't been made yet? Reject obvious connections — the value is in the surprising ones. Present 3–5 non-obvious connections, each framed as: '[Concept A] connects to [Concept B] because [non-obvious bridge]. The unexplored synthesis is [new insight].'"skill: "connect"If Qwen is unavailable:
obsidian search query='[argument]' limit=10 via bash and cast a wide net into adjacent domains.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.