Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/detection-scoring
Rate detectability 1-10 (inverted: 10 = hardest to detect). Estimates how likely current controls would catch the failure before impact.
Passed 15 of 21 test cases with the skill, and 11 of 21 without it.
and 6 more in the full report
5 fixed11 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
We have two failure modes: FM-API-1 (unhandled null pointer in edge router, immediate 500 log) and FM-API-2 (subtle precision loss in financial calculations, no log or metric). Evaluate both modes for detectability, justify, and list gaps.
| Checked | Without skill | With skill |
|---|---|---|
| FM-API-2 is assigned a higher detectability score than FM-API-1. | Missed | Passed |
| FM-API-2 is included in the detection gaps list. | Passed | Passed |
The instructions your model reads when the skill loads.
Rates each failure mode's detectability on an inverted 1-10 scale (10 = hardest to detect).
Subagent — spawned via subagent-spawning/spawn-agent.
Detection assessment requires reasoning about observability and monitoring independent of severity/occurrence. Isolated context ensures unbiased evaluation.
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 11 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.