AB design-red-team-audit
Adversarial design audit that stress-tests a game feature, system, pitch, roadmap item, or product idea by assuming failure and identifying the most credible reasons it would fail. Use when pressure-testing a concept before production, performing a pre-mortem, challenging a feature that sounds good on paper, exposing blind spots in design thinking, or getting a hostile-but-constructive critique with concrete failure mechanisms and de-risking moves.
Adversarial design audit that stress-tests a game feature, system, pitch, roadmap item, or product idea by assuming failure and identifying the most credible…
As a process B 74/100 · Nearly there — weak spots: failures and branches, running it twice, progress reporting
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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Risky intent
intent-offensive-securityreferences/workflow.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Workflow: Design Red Team Audit
-
low Risky intent
intent-offensive-securityskill-card.md:31Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- [Workflow: Design Red Team Audit](references/workflow.md)
-
low Risky intent
intent-offensive-securitySKILL.md:6Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Design Red Team Audit
Files scanned: 4. 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 74/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 85 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1451 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 452: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 85 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.