AB red-team
Adversarial multi-agent debate engine for stress-testing decisions, ideas, and strategies. Orchestrates multiple AI agents with conflicting worldviews (bull, bear, operator, contrarian, etc.) to debate a question through structured rounds, then synthesizes results into a decision brief. Use for: red team analysis, adversarial debate, stress testing ideas, devil's advocate, "what could go wrong" analysis, decision validation, pre-mortem exercises.
Adversarial multi-agent debate engine for stress-testing decisions, ideas, and strategies.
As a process B 67/100 · 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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Risky intent
intent-offensive-securityREADME.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# 🔴 Red Team — Adversarial Multi-Agent Debate Engine
-
low Risky intent
intent-offensive-securityreferences/personas.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Red Team Persona Library
-
low Risky intent
intent-offensive-securitySKILL.md:7Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Use for: red team analysis, adversarial debate, stress testing ideas, devil's advocate,
-
low Risky intent
intent-offensive-securitySKILL.md:11Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Red Team — Adversarial Debate Engine
-
low Risky intent
intent-offensive-securitySKILL.md:52Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)When the user asks you to "red team" something, "stress test" an idea, play "devil's advocate", or asks "what could go wrong":
quoted
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 67/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 29 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1248 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
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 450: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 29 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.