AC regression-hunt
Find what a change can break in the code that did NOT change — trace a diff, branch, commit range, or named feature outward through callers, consumers, shared state, and contracts, rank the concrete regression scenarios by blast radius, and prove or clear each one with an observed test run. Zero regressions is a valid outcome. Use this skill whenever the user says "look for regressions", "what could this break", "did this change break anything", "regression check", "impact of this change", "blast radius", "what else uses this", "is anything else affected", or "/regression-hunt" — even if they don't name the skill. Not for reviewing the diff's own quality (code-review) or a bug already observed (diagnose).
Find what a change can break in the code that did NOT change — trace a diff, branch, commit range, or named feature outward through callers, consumers, shared…
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 4 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 28 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2389 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (4 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
- +3Output format is not stated: the model decides each time
- -213 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 714: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.