brand-gen-reference — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited brand-gen-reference (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.
For Sage brand work in Pi, use the paste-ready prompt at docs/prompts/pi-sage-brand-gen-full-pipeline.md. It routes Pi through the typed brand_* tools, the brand-orchestrator subagent, exact-text gates, v2/DSPy review, GEPA-ready disagreement fields, and typed mutation loops. Keep this link instead of copying the full prompt into skill bodies.
Reference data for brand-gen — not workflow doctrine. Load individual reference files only when you need them.
Preferred CLI: bgen ... or python3 -m brand_gen ...
references/models.md.og-card (1.91:1) and x-card (2:1) require models that accept those ratios. Check bgen types for the default model per type. If the default model fails, try recraft-v4 (widest AR support) or nano-banana-2.references/social-surfaces.md, or run bgen social-specs for live data.references/file-layout.md, or run bgen show-session-summary --format json.bgen show-reference-analysis --format json.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.