AA self-improving-prompt
Refines ambiguous or high-risk user requests before execution. Trigger when the request is underspecified, likely to benefit from clearer constraints or verification, or when the user explicitly asks to refine, improve, optimize, refactor, or compare approaches. Skip clear single-step instructions and already-well-scoped tasks.
As a process A 83/100 · Runs to the end — weak spots: 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: 6. 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 83/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 71 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1899 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 14 top-level sections: this looks like several domains in one skill
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)
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 329: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 71 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (3 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.