Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/consequence-following
Follow a provocation's logical consequences step by step to extract viable insights and new research directions.
Passed 5 of 22 test cases with the skill, and 4 of 22 without it.
1 fixed4 passed either way17 still failing0 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.
Review the timestamped event log from last night's Kubernetes cluster crash and construct a chronological incident timeline reconstructive report detailing minute-by-minute system state changes.
| Checked | Without skill | With skill |
|---|---|---|
| The output formats the incident data into a chronological timeline of past events | Missed | Passed |
| The response is generated directly without requiring subagent spawning | Passed | Passed |
The instructions your model reads when the skill loads.
Subagent — spawned via subagent-spawning/spawn-agent.
One unit = one complete consequence chain (3-5 steps) for one provocation.
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 4 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.