Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/adversarial-persona
Strategy: Role-play attacks from hostile personas — competing lab researcher, hostile reviewer, funding skeptic, domain outsider — each with distinct attack motivations and blind spots.
Passed 16 of 20 test cases with the skill, and 8 of 20 without it.
and 22 more in the full report
11 fixed7 passed either way2 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
We have a quick 2-page research proposal for an AI safety grant (Project Aegis) and want a light, small-scale adversarial persona audit. What are the budget parameters for attack vectors, probing rounds, and personas?
| Checked | Without skill | With skill |
|---|---|---|
| Allocates 5 attack vectors for the small budget tier. | Missed | Passed |
| Allocates 3 probing rounds for the small budget tier. | Missed | Passed |
| Allocates 2 personas for the small budget tier. | Missed | Passed |
The instructions your model reads when the skill loads.
Construct and deploy hostile personas that attack from distinct motivational frames. Each persona has unique expertise, biases, and attack patterns.
| Parameter | S | M | L |
|---|---|---|---|
| Attack vectors | 5 | 12 | 20 |
| Probing rounds | 3 | 6 | 10 |
| Personas | 2 | 4 | 6 |
| Assumption checks | 5 | 10 | 20 |
persona-construction → [build N personas per budget]
→ [for each persona]:
attack-vector-generation (persona-specific vectors)
→ probe-execution (execute persona attacks)
→ finding-aggregation (cross-persona synthesis)
→ attack-resilience-scoring
test cases passed, vs 8 / 20 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.