Skip to content
Back to skills

Round Decision

ASecurity

Decide whether to continue iterating or stop based on consensus score, round number, and stability.

  • 417 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added May 27, 2026
researchdocumentation

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned May 27, 2026

npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill round-decision --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Round Decision?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Round Decision
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yogsoth-ai-round-decision/badge)](https://www.skillsdirectory.com/skills/yogsoth-ai-round-decision)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: round-decision
description: Decide whether to continue iterating or stop based on consensus score, round number, and stability.
execution: subagent
prompt: ./prompt.md
input: consensus_score, round_n, stability
used-by: structured-consensus
---

# Round Decision

Decide whether to run another Delphi round or stop the iteration. Uses consensus score, current round number, and stability (whether scores changed from prior round) to make the continue/stop decision.

## Execution

Spawn a subagent that evaluates the stopping criteria and returns a clear continue/stop decision with rationale.

## Why Subagent

- Decision logic is a pure function of three inputs
- Rationale documentation is important for audit trail
- Keeps orchestration logic clean

## HARD-GATE

Output MUST contain: `decision` (continue/stop), `reason` (string), and `next_action` (what to do next). Decision must be exactly one of "continue" or "stop".

Files in this skill

  • SKILL.md937 B
  • prompt.md1.6 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.