SKILL.md:1the skill works → no evals/, tests/, or verification section found
No way to prove the skill does what it claims.
Fix Add an evals/ folder (test prompts + expected outcomes) and a '## Verify' step in the body.
SKILL.md:226
Decorative ASCII-art / banner line — pure token cost, no instructional value.
┌──────────────────────────────────────────┐
SKILL.md:228
Decorative ASCII-art / banner line — pure token cost, no instructional value.
├──────────────────────────────────────────┤
SKILL.md:230
Decorative ASCII-art / banner line — pure token cost, no instructional value.
│ ↓ │
SKILL.md:232
Decorative ASCII-art / banner line — pure token cost, no instructional value.
│ ↓ │
SKILL.md:234
Decorative ASCII-art / banner line — pure token cost, no instructional value.
│ ↓ │
SKILL.md:242
Decorative ASCII-art / banner line — pure token cost, no instructional value.
│ ↓ │
SKILL.md:243
Decorative ASCII-art / banner line — pure token cost, no instructional value.
│ Return to AUDIT ←───────────────────────│
SKILL.md:244
Decorative ASCII-art / banner line — pure token cost, no instructional value.
└──────────────────────────────────────────┘
SKILL.md:302
Decorative ASCII-art / banner line — pure token cost, no instructional value.
┌──────────────────────────────────────────┐
SKILL.md:303
Decorative ASCII-art / banner line — pure token cost, no instructional value.
│ ┌───────────────────────────────────┐ │
SKILL.md:304
Decorative ASCII-art / banner line — pure token cost, no instructional value.
│ │ ┌─────────────────────────────┐ │ │
SKILL.md:307
Decorative ASCII-art / banner line — pure token cost, no instructional value.
│ │ └─────────────────────────────┘ │ │
SKILL.md:310
Decorative ASCII-art / banner line — pure token cost, no instructional value.
│ └───────────────────────────────────┘ │
SKILL.md:313
Decorative ASCII-art / banner line — pure token cost, no instructional value.
└──────────────────────────────────────────┘
Fix Delete decorative banners and persona filler; keep instructions plain and imperative.
SKILL.md:1description will match user requests → no explicit cue ('use when …', 'triggers on …', quoted user phrases) found
Pure what-it-does prose — the model has to guess when to invoke it.
[00] TnR ABSOLUTE RIGOR — Systemic Verification Doctrine. Forced cognitive ex…
Fix State the trigger explicitly: 'Use when the user says "…", "…", or wants to …'.
SKILL.md500-line guidance → 675 lines
SKILL.md is 675 lines — over the ~500-line guidance. ~7,620 tokens (rough est.); ~$0.0229 per load at $3/Mtok reference rate.
Fix Move heavy reference material into supporting files and link to them (progressive disclosure), keeping SKILL.md lean.