AF adversarial-review
Run a structured adversarial multi-agent review loop on any significant document. Spawns parallel Opus reviewers with different critical lenses, collects structured redlines, then guides farsight through agree/disagree positioning and v2 production. SELF-TRIGGERING: load this skill and run the complexity self-assessment whenever you are about to produce or have just produced any substantial document — score it and offer the review loop if it qualifies. Also load when the user says things like: 'use the review team', 'get the review team on this', 'spin up the reviewers', 'have the team look at this', 'red-team this', 'redline this', 'challenge this', 'critique this', 'tear this apart', 'poke holes in this', 'stress test this', 'pressure test this', 'sanity check this', 'validate this', 'get a second opinion', 'before we build/implement/ship this'.
As a process F 46/100 · Will not run — References files that are not bundled: references/model-notes.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securityreferences/reviewer-personas.md:171Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**Lens:** Threat surface, access control gaps, data exposure, privilege escalation paths
-
low Risky intent
intent-offensive-securityreferences/reviewer-personas.md:189Offensive-security / dual-use content (legitimate for authorised testing; review intended use)5. Privilege escalation: Can a lower-privileged operation write to a higher-privileged field?
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/model-notes.md
Process rating: all ten parameters 46/100
- 0Tools and files. 1 referenced file(s) missing: references/model-notes.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 4 branches
- 100Steps. 8 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1535 tokens
- 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
- +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 859: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.