Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/critic-attack
Attack an advocate's case with multiple arguments rated by severity.
Passed 9 of 22 test cases with the skill, and 3 of 22 without it.
and 5 more in the full report
6 fixed3 passed either way13 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our lead DBA published a case for migrating our Postgres cluster to a proprietary vendor database, highlighting cost savings as the core driver. Provide a critique listing bullet-point headlines without detailed explanations.
| Checked | Without skill | With skill |
|---|---|---|
| Includes reasoning or evidence for every identified weakness rather than bare headlines. | Missed | Passed |
| Rates each argument's severity using exclusively HIGH, MEDIUM, or LOW. | Missed | Passed |
| Attacks the core cost-savings claim made by the lead DBA. | Missed | Passed |
The instructions your model reads when the skill loads.
Attacks an advocate's case from multiple angles, producing rated arguments that expose weaknesses, logical gaps, and unsupported claims. The critic's job is to find every legitimate vulnerability.
Spawns a subagent with the critic role. The subagent receives the winner context and the advocate's case, then attacks the case systematically.
Output must include:
= 3 distinct attack arguments
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.