AC advocatus
Give voice to all opposition. The Advocatus Diaboli — official adversarial challenger to every doctrine, skill, rule, and assumption in the agency. Use when: (1) a new doctrine needs its opposition recorded before it hardens, (2) running a full docket review of which doctrines have survived adversarial challenge, (3) an agent is about to act on an unchallenged assumption, (4) the two-man rule needs a voice that is structurally opposed, not just independently written. Named after the canonical Catholic canonization role: assigned specifically to argue against sainthood before anything was locked in. The Church invented the two-man rule for doctrine. Triggers on: 'advocatus', 'opposition', 'devil's advocate', 'challenge this', 'grant voice to opposition', 'what argues against'. NOT for: decision-making (Advocatus records opposition, does not resolve it), emotional venting, or external disputes.
As a process C 53/100 · 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: 5. 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 53/100
- 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
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 17 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 527 tokens
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
- +3Description length 905: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 5 headings
- +3Step-by-step instructions: 17 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.