BC Recipes
Captures, standardizes, scales, and files recipes into a personal collection that stays searchable and cookable. Use when the user pastes a recipe URL, photo, screenshot, video, voice note, or handwritten card to save; asks to halve, double, or triple a dish, or fit it to a different pan or tin; converts cups to grams, ounces to millilitres, Fahrenheit to Celsius, or gas marks, or adjusts for a fan oven or altitude; asks what to cook from what is saved, or searches by ingredient, tag, time, or rating; builds a week from the collection with one combined shopping list; swaps a missing, disliked, or off-limits ingredient; rewrites a dish for a pressure cooker, air fryer, or slow cooker; works out cost per serving; writes or tests an original recipe; preserves a family recipe; or moves a collection between apps. Not for stove-side rescue (`cooking`), general cooking help (`chef`), household meal systems (`meal-planner`), calories and macros (`calories`), or pantry lists (`grocery`).
Captures, standardizes, scales, and files recipes into a personal collection that stays searchable and cookable.
As a process C 62/100 · Has gaps — weak spots: inputs and preconditions, consistency, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 6111 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 62/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 10 mutating operations with no state check
- 40Consistency. Frontmatter name (Recipes) differs from the folder (recipe)
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 6111 tokens
- 100Steps. 42 steps
- 100When it triggers. States when to use and when not to
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 993: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 42 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.