AC skill-creator
Create new skills, edit existing skills, and iterate wording. Use when writing SKILL.md from scratch, improving existing skills, turning repeated workflows into reusable skills, or refining skill descriptions to improve trigger reliability.
Promises to help write, edit, and iterate skill descriptions from scratch to final SKILL.md. One instruction file, 2K tokens, no scripts or examples. Looks logical on paper: you feed it a repeating workflow, describe it in the right format, run it against your agent, and it generates a skill.
Quality scores 87, but process only 59. No critical errors found, though no actual model runs or sandbox tests either. The instruction assumes you already know how to write skills and just need help polishing the text.
Worth installing if you create skills regularly and want to automate their descriptions. If you write skills rarely or need help with the skill's logic itself, not just wording—skip it.
Create new skills, edit existing skills, and iterate wording.
As a process C 59/100 · Has gaps — weak spots: when it triggers, 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: 1. 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 59/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 60Tools and files. Uses tools (read) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 4 branches
- 100Steps. 38 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2067 tokens
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (6 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 240: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 38 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.