research — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited research (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.
User provides a theme for research, or research is needed before generation.
references/research-protocol.mddata/brain/pmm_brain.json (pmm_value_landscape section)Use WebSearch tool to research the theme from 5-8 angles:
Synthesize into a Research Brief with:
Cross-reference research against:
data/user/my_posts.docx context or ChromaDB)Identify: already said, white space, user unique angles, recommended angles.
Score every candidate insight on the 1-5 Insight Novelty Scale (see references/research-protocol.md).
Assign evidence anchors to 3 recommended angles:
Show the Research Brief summary:
━━━━ RESEARCH BRIEF: "{theme}" ━━━━
SATURATION: [Low/Medium/High] — [what's been covered vs. what hasn't]
EVIDENCE ANCHORS:
1. [type] [content] — [source]
2. ...
RECOMMENDED ANGLES:
1. OPINIONATED REFRAME: [angle] — Novelty: [4-5]/5 — Evidence: [anchors]
2. FRAMEWORK: [angle] — Novelty: [4-5]/5 — Evidence: [anchors]
3. STORY: [angle] — Novelty: [4-5]/5 — Evidence: [anchors]
Proceed with these angles? (yes / adjust)See also: skills/generate/ (consumes research output) | skills/suggest-themes/ (alternative entry point for theme discovery)
See also: skills/generate/ (consumes research output) | skills/suggest-themes/ (Brain-informed alternatives) | skills/_index.md for full data flow
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.