BB omh-adversarial-consensus
[omh] Technical proposal facing adversarial scrutiny: independent perspectives attack a proposal, then distill into a bundle a separate planner consumes. Use when the user says: adversarial-consensus, adversarial planning, adversarial plan review, red team this plan, red-team this plan, red team the proposal, multi-perspective review, multiple perspectives.
[omh] Technical proposal facing adversarial scrutiny: independent perspectives attack a proposal, then distill into a bundle a separate planner consumes.
As a process B 70/100 · Nearly there — weak spots: result and completion, failures and branches, running it twice
The same skill appears in 1 more place: oh-my-hermes
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)description: "[omh] Technical proposal facing adversarial scrutiny: independent perspectives attack a proposal, then distill into a bundle a separate planner consumes. Use when the user says: adversar
quoted -
low Risky intent
intent-offensive-securitySKILL.md:66Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)Strong routing signals: `adversarial-consensus`, `$adversarial-consensus`, `adversarial planning`, `adversarial plan review`, `red team this plan`, `red-team this plan`, `red team the proposal`, `mult
quoted
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 359 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
Process rating: all ten parameters 70/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Consistency. The Hermes dialect needs category and tags
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 45 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 2642 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 359: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.