Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> c8103784f8 feat(nous-branding): split SKILL.md into focused references ...

Body was ~24k chars, past the new 20k token-budget gate. Moves the
style-lane grammar + prompt cues + asset catalog into
references/style-lanes.md, the full visual system (palettes, mascot,
typography, textures, art style) into references/visual-system.md, and
post-processing modes/intensity calibration into
references/post-processing.md. SKILL.md keeps triggers, the negative
boundary, prompt templates, API notes, anti-patterns, compliance
checklist, and a Loading Guide table; body is now 12,042 chars.

Also adds evals/evals.json (6 output-quality cases incl. one
should-not-trigger case) to satisfy the eval-coverage ratchet, and adds
a "When not to use" section so the changed-skill quality gate passes.

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

2026-08-22 22:47:16 -04:00

..

evals.json

feat(nous-branding): split SKILL.md into focused references

2026-08-22 22:47:16 -04:00