AB verse-craft
This skill should be used when the user asks to "write a poem", "write a limerick", "write a sonnet", "haiku", "villanelle", "ballad", "song lyrics", "a song for my character", "a rhyme", "rhyming couplets", "does this scan", "check the meter", "fix the rhythm of this poem", "rhyme scheme", "iambic pentameter", "a prophecy in verse", "a nursery rhyme", "rhyming picture book", or wants verse written, scanned, or revised, whether inside a story project or as a standalone poem. NOT for accidental rhymes in prose (use line-editing) or permissions for quoting someone else's poem (use editorial-review).
This skill should be used when the user asks to "write a poem", "write a limerick", "write a sonnet", "haiku", "villanelle", "ballad", "song lyrics", "a song…
As a process B 66/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
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: 4. 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 66/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 32 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1987 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 17 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 604: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 97.