AB promoter-draft
Turn one recurring pattern from a promoter scan into a complete, reusable skill in this library's format: a SKILL.md with a strong trigger description, required inputs, a framework, an output template, quality checks, anti-patterns, and three worked examples derived from the user's real prompts, plus the bundle manifest. Use when asked to draft a skill from this pattern, promote this pattern into a skill, write the SKILL.md for what I keep asking, or as the second step of the promote loop. Produces a ready-to-test skill folder that anyone, not just the original user, can use.
Turn one recurring pattern from a promoter scan into a complete, reusable skill in this library's format: a SKILL.md with a strong trigger description…
As a process B 74/100 · Nearly there — weak spots: when it triggers, 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 74/100
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 28 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1154 tokens
- 100Progress reporting. Reports progress
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 582: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 28 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.