AC diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. On non-trivial cases, Phase 3 spawns parallel `Explore` sub-agents — each defending a distinct hypothesis with falsifiable predictions and `file:line` evidence — then a cross-examination round drops the ones whose defender couldn't find support, breaking the single-chain anchoring trap. Trivial bugs skip the council. Use this skill whenever the user says "diagnose this", "debug this", "/diagnose", reports a bug, says something is broken / throwing / failing / flaky / hanging / leaking, or describes a performance regression — even if they don't explicitly ask for a "diagnose skill".
As a process C 61/100 · Has gaps — weak spots: result and completion, 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: 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 61/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 8 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 66 steps
- 100Failures and branches. 13 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3803 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 The skill ranks results itself: that belongs to the system behind the tool, not the model
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 731: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 66 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.