Diagnose cookbook quality: skimmability, clarity, and reader load. Use when recipes are hard to follow or a new cookbook is starting. It does not set house voice (that's `docs-writing-style`).
71
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
Diagnose cookbook quality. Fix one state at a time. Do not rewrite a whole book in one pass.
Every structural choice must reduce the reader's load, not the author's writing effort.
| ID | Name | Symptom |
|---|---|---|
| AC1 | Structure Void | Noun titles, no TOC, dense prose |
| AC2 | Buried Takeaways | Conclusion comes after long setup |
| AC3 | Parsing Tax | Long left-branching sentences |
| AC4 | Consistency Breaks | Same idea named two ways |
| AC5 | Expertise Gap | Jargon and missing prerequisites |
| AC6 | Fragile Examples | Examples need extra pages or secrets |
| AC7 | Priority Inversion | Rare cases documented, common ones missing |
For expanded symptoms, questions, and interventions, load
references/states.md.
For triage questions and example sessions, load
references/questions-and-examples.md. For anti-patterns, loadreferences/anti-patterns.md. For recipe components, loadreferences/recipe-components.json. For reasoning, execution, and handoff notes, loadreferences/operations.md.
Generate a recipe stub:
deno run --allow-read --allow-write scripts/recipe-scaffold.ts "recipe-name"Audit a recipe folder:
deno run --allow-read scripts/coverage-audit.ts ./recipes/At the end of every session, ask: "Did this solve what you were trying to do?"
df60de1
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.