agentleFS
Sign inStart free
yogsoth-aiyogsoth-ai/convergence/skills/iterative-convergence-round/SKILL.md

iterative-convergence-round

Skill2 starsChanged 6 months agoApache-2.0View on GitHub

Execute one full Delphi round — collect judgments, distribute anonymous feedback, measure consensus, decide whether to continue.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Stop conditions: consensus threshold met OR stability detected OR max rounds reached

    line 33
  2. Distinctive:

    If stopping without consensus, document which items remain unresolved

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Iterative Convergence Round

Execute one complete iteration of the Delphi convergence cycle: collect independent judgments from all perspectives, distribute anonymized feedback showing the group distribution, allow revision, measure consensus level, and decide whether another round is needed.

Stages

  1. Collect — Run judgment-collection to gather independent ratings/estimates from each perspective
  2. Feedback — Run feedback-distribution to create anonymized summary of group responses
  3. Measure — Run consensus-measurement to compute agreement level (IQR, % agreement, Kendall's W)
  4. Decide — Run round-decision to determine continue/stop based on threshold and stability

Available SOPs

SOPRole in Tactic
judgment-collectionGather independent judgments from all perspectives
feedback-distributionCreate and distribute anonymized feedback report
consensus-measurementCompute consensus score using appropriate method
round-decisionDetermine whether to run another round or stop

Execution Guidance

  • Judgments MUST be collected independently (no cross-contamination)
  • Feedback MUST be anonymized (no attribution to specific perspectives)
  • Consensus measurement method should match data type (IQR for continuous, % for categorical)
  • Stop conditions: consensus threshold met OR stability detected OR max rounds reached
  • If stopping without consensus, document which items remain unresolved

Minimum Yield

  • Consensus items list (items that reached consensus)
  • Non-consensus items (items that did not converge, with reasons)
  • Round log (round-by-round progression of scores)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free