SKILL.md:1a Claude Code skill → file does not begin with a `---` frontmatter fence
No YAML frontmatter block found at the top of the file.
Fix Add a `---`-fenced YAML block at the very top with at least a `description` field.
overall
Correctness & Structure
33
2 fail
Triggering & Discoverability
33
2 fail
Clarity & Instructions
100
pass
Token & Context Cost
74
1 fail
Safety & Security
100
pass
Verifiability & Maintainability
53
1 fail
Top fixes — ranked by score impact
SKILL.md:1
No frontmatter to read fields from (see STRUCT-01).
Fix Add frontmatter with a `description` field.
SKILL.md:1
No description — nothing for the model to match against.
Fix Add a description that leads with the use case and the phrases a user would say.
SKILL.md:1
No description — no invocation cues possible.
Fix Add a description with explicit cues: 'Use when …' plus the phrases a user would say.
SKILL.md500-line guidance → 1070 lines
SKILL.md is 1070 lines — over the ~500-line guidance. ~10,544 tokens (rough est.); ~$0.0316 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.
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.mda one-time authoring cost → ~10,544 tokens (rough est.) per invocation
Every invocation carries this: ~10,544 tokens (rough est.) per invocation — ~$31.63 per 1,000 invocations at the $3/Mtok reference rate.
Fix Cut the entry file below ~8k tokens — move reference material into supporting files so every future invocation gets cheaper.
★ scores higher than ≈1% of 214 public skills (deterministic rubric v1.2 sample, 2026-07)
Embed this badge
Always-fresh — it re-scans and updates on its own.
Grade your own Claude Code skill — evidence-cited, file-and-line, free.
Scan your own skill →