hashgraph-online/awesome-codex-plugins / plugins/boshu2/agentops/skills/council
council
VerifiedCompare independent opinions from models or contexts without inflating agreement. Use when: wanting several opinions or a debate, or summarizing several reviewers' results.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 12.2 KB |
| references/debate.md | markdown | 3.8 KB |
| references/duel.md | markdown | 1.2 KB |
| references/interview-panel.md | markdown | 1.4 KB |
| references/judge-split.md | markdown | 1.4 KB |
| schemas/council-report.v1.schema.json | config | 4.7 KB |
| scripts/validate-output.shexecutable | script | 4.3 KB |
| scripts/validate.shexecutable | script | 4.6 KB |
references/duel.md
View on GitHub# Duel: members score each other's ideas
Loaded by [Council](../SKILL.md) when the caller selects a scored duel.
[Idea Genie](../../idea-genie/SKILL.md) challenges one consequential choice for
Plan; this is the scored tournament.
Before launch the caller fixes the question, the rubric (for example
usefulness, feasibility, cost or complexity, risk), its scale, and the
per-member idea cap.
1. **Generate.** Each member returns its own ranked ideas with evidence, sealed.
2. **Score.** In fresh contexts, each member scores every other member's ideas
on each rubric line with a reason. Scores stay sealed from other scorers,
and no member sees any score of its own ideas.
3. **Reveal.** Each member sees how peers scored its ideas and concedes or
defends with evidence: one bounded round, fresh contexts, peer-informed
(see [debate](debate.md)).
4. **Synthesize.** Rank by cross-member agreement. Flag a large score gap
between members as information worth investigating; do not average it away.
Keep concessions and dissent. A score is a judgment, never proof.
Record each context's ideas, scores, concessions and defenses, with its round,
in `judges[].judgment`; no new schema.
It's working if no member sees scores of its own ideas before the reveal.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |