AC code-refinement
Improves code quality across duplication, efficiency, and architectural fit
As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
ProcedureSoftware developmentInfrastructuretype and topics are labelled automatically from the skill text
How to improve
For the model run — optional
- 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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "triggers" - note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "source_plugin"
Process rating: all ten parameters 54/100
- 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
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (code-refinement) differs from the folder (nm-pensive-code-refinement)
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Steps. 42 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 2581 tokens
- low 12 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)
- +3Description length 75: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 26 headings
- +3Step-by-step instructions: 42 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.
External checks
ClawHub: suspicious
This code-refinement skill mostly matches its purpose, but it also enables broad repository changes, guardrail bypass phrasing, persistent execution, and external posting of code-analysis findings without clear user approval.
LLM: suspicious (high) · 26 Aug 2026