Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/convergence-check
Evaluate whether the ranking has stabilized by analyzing rating history and computing stability metrics.
Passed 20 of 22 test cases with the skill, and 7 of 22 without it.
and 17 more in the full report
13 fixed7 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
A pairwise comparison sequence for candidate images shows stability_score = 0.30. Formulate the output JSON.
| Checked | Without skill | With skill |
|---|---|---|
| Includes a concrete recommendation advising further comparisons focusing on high-variance candidates | Missed | Passed |
The instructions your model reads when the skill loads.
Evaluates whether the current ranking has converged by analyzing the trajectory of ratings over recent iterations. Computes stability metrics and determines if further comparisons would meaningfully change the ranking.
Runs as a subagent. Receives the full rating history and returns convergence status with metrics.
Convergence assessment requires analyzing trends across multiple snapshots and applying statistical tests. Isolating this prevents the orchestrator from needing to hold the full history in working memory.
Output MUST contain a boolean converged field and a numeric stability_score in [0, 1]. If converged=false, MUST include recommendation for what to do next.
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 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.