bloom — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited bloom (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.
Expand a topic into its question space as a tree — questions that nest and relate, not a flat enumeration, with Level 3 meta-framings that challenge how the topic is posed.
Don't: flatten the bloom into a list. Don't surface only obvious sub-questions — Level 3 reframings that challenge the topic's framing are where the value is.
task: "Vault access (bash only, no MCP tools): obsidian search query='TERM' limit=10, obsidian read file='Note Name' (no .md). Map how '[argument]' branches into sub-questions across the vault. Level 1: immediate follow-on questions. Level 2: adjacent topics and domains with shared structure. Level 3: meta-questions that challenge how '[argument]' is framed. Note which branches are already explored in the vault vs. blank. Suggest 1–2 unexplored branches most worth pursuing. Output as a structured tree, not a flat list."skill: "bloom"If Qwen is unavailable:
obsidian search query='[argument]' limit=10 via bash; read relevant notes.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.