AC plan-to-eat-cli
Use when the user wants to interact with Plan to Eat (plantoeat.com) — meal plan, recipes, planner notes/ingredients/leftovers, freezer, shopping list — and the `plan-to-eat` CLI is available but the plan-to-eat MCP server is NOT connected. Same capabilities as the MCP server, driven through the shell. Triggers on "what's on my meal plan", "plan X for Wednesday dinner", "add a note to Tuesday breakfast", "move dinner to Friday", "freeze leftovers", "what's in the freezer", "what's on my shopping list", "add milk to the shopping list" — when those must be answered with shell commands.
com) — meal plan, recipes, planner notes/ingredients/leftovers, freezer, shopping list — and the plan-to-eat CLI is available but the plan-to-eat MCP server…
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 61/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 16 mutating operations with no state check
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 20 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3361 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 590: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 20 items
- +4Has examples (23 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.