AC slop-score
Measure how much a repository's structure taxes ordinary development: unclear contracts, information owned in several places, misplaced responsibilities, disproportionate design. Produces a state card (rates with denominators) and a ranked maintenance map with owners, by scanning the whole tree deterministically, asking a model only the judgment questions, and having fresh agents implement real past changes while their cost is measured. Use for explicit slop or maintainability assessments of a git repository with a buildable toolchain; not for ordinary code review or bug hunting.
Measure how much a repository's structure taxes ordinary development: unclear contracts, information owned in several places, misplaced responsibilities…
As a process C 57/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, 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: 14. 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 57/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 6 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 15 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1278 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
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 586: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 15 items
- +4Reference files are cited in the instructions (2 of 2)
- +3All 5 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.