Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/debate-critic
Generates structured criticism from attack stance using Toulmin model. Produces claims, grounds, warrants, and rebuttals targeting artifact weaknesses.
Passed 3 of 22 test cases with the skill, and 3 of 22 without it.
1 fixed2 passed either way18 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
Perform a single-round adversarial critique on the zero-trust network access specification text. Provide one set of structured attacks covering claim, ground, warrant, rebuttal anticipation, confidence, and escalation advice.
| Checked | Without skill | With skill |
|---|---|---|
| Executes the critique in an isolated subagent environment | Missed | Passed |
The instructions your model reads when the skill loads.
Generates structured adversarial criticism targeting artifact weaknesses.
Subagent — spawned via subagent-spawning/spawn-agent.
Attack generation requires dedicated adversarial stance without contamination from defensive reasoning. Isolated context ensures pure opposition.
One unit = one set of attacks for one round.
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |
test cases passed, vs 3 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.