CC RedTeam
Adversarial analysis deploying parallel expert agents to stress-test ideas, strategies, and plans — attacks atomic claims, then steelmans and counter-argues, with severity-ranked findings and remediation; also tests an idea or investment against 11 persistent world models from 6 months to 50 years (Fast/Standard/Deep), and refreshes and reports on those models. USE WHEN red team, attack idea, counterarguments, critique, stress test, devil's advocate, find weaknesses, break this, poke holes, strongest objection, world threat model, world model, test idea against the future, how will this hold up in 10 or 20 years, time horizon, long-term risk, update world models, show world models. NOT FOR collaborative debate to find best path (use Council), or threat modeling your own estate (ThreatModel).
Adversarial analysis deploying parallel expert agents to stress-test ideas, strategies, and plans — attacks atomic claims, then steelmans and counter-argues…
As a process C 57/100 · 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 · 9
✓ No critical or high findings
Medium and low: 9
-
low Risky intent
intent-offensive-securityIntegration.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Red Team Integration Guide
-
low Risky intent
intent-offensive-securityIntents/ParallelAnalysis.md:34Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# RED TEAM: [what was attacked]
-
low Risky intent
intent-offensive-securityIntents/ParallelAnalysis.md:70Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# RED TEAM VERDICT
-
low Risky intent
intent-offensive-securityPhilosophy.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Red Team Philosophy
-
low Risky intent
intent-offensive-securityPhilosophy.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Red teaming comes from the military: dedicated teams that attack plans, strategies, and assumptions to find vulnerabilities before the enemy does.
-
low Risky intent
intent-offensive-securitySetup.md:7Offensive-security / dual-use content (legitimate for authorised testing; review intended use)The red team skill attacks an idea, plan or design to find its weak points before reality does. Attacking an argument (`ParallelAnalysis`) and designing by competition (`AdversarialValidation`) work f
-
low Risky intent
intent-offensive-securitySKILL.md:10Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)description: "Adversarial analysis deploying parallel expert agents to stress-test ideas, strategies, and plans — attacks atomic claims, then steelmans and counter-argues, with severity-ranked finding
quoted -
low Risky intent
intent-offensive-securitySKILL.md:34Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (documentation table row)| **ParallelAnalysis** | "red team this", "poke holes", "strongest objection", "quick adversarial pass", "inline, no agents": stress-test existing content | `Intents/ParallelAnalysis.md` |
table -
low Risky intent
intent-offensive-securitySKILL.md:68Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)User: "red team this microservices migration plan"
quoted
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "evals"
Process rating: all ten parameters 57/100
- 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
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1759 tokens
- 100Running it twice. No mutating operations
- 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
- +3Description length 802: 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: 7 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.