Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/failure-mode-extraction
Extract structured failure mode list from raw scenarios or artifact analysis. Produces standardized failure mode records.
Passed 13 of 21 test cases with the skill, and 3 of 21 without it.
and 8 more in the full report
11 fixed3 passed either way8 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our data platform team evaluated potential failure points in our Apache Kafka telemetry pipeline based on the system architecture design. We have five raw breakdown cases. Structure these into records. Which field name should hold the brief title of the failure mode in the structured record list?
| Checked | Without skill | With skill |
|---|---|---|
| Uses the field name 'name' for the brief title attribute in each structured record | Missed | Passed |
The instructions your model reads when the skill loads.
Converts raw failure scenarios or artifact analysis into structured failure mode records.
Subagent — spawned via subagent-spawning/spawn-agent.
Extraction requires systematic decomposition without creative bias. Isolated context ensures consistent structuring.
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 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.