SKILL.md:45
Decorative ASCII-art / banner line — pure token cost, no instructional value.
┌─────────────────────────────────────────────────────┐
SKILL.md:49
Decorative ASCII-art / banner line — pure token cost, no instructional value.
└──────────────────────┬──────────────────────────────┘
SKILL.md:51
Decorative ASCII-art / banner line — pure token cost, no instructional value.
┌──────────────────────▼──────────────────────────────┐
SKILL.md:59
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.
Diagnose and fix .NET HTTPS dev certificate trust issues on Linux. Covers the…
Fix State the trigger explicitly: 'Use when the user says "…", "…", or wants to …'.
SKILL.mdeverything inlined in SKILL.md → 411 body lines, 0 supporting files
Large SKILL.md (411 lines) with no supporting files — all of it loads every time the skill fires.
Fix Move heavy reference material into supporting files and link to them, so the model loads it only when needed.
SKILL.md:240the skill can be verified → a prose verification step, but no runnable evals/ or tests/
Manual verification only — add eval prompts with expected outcomes to make it checkable.
# Verify
Fix Add an evals/ folder with 2–3 test prompts and the expected assertions.
