Skip to content

hashgraph-online/awesome-codex-plugins / plugins/boshu2/agentops/skills/council

council

Verified

Compare independent opinions from models or contexts without inflating agreement. Use when: wanting several opinions or a debate, or summarizing several reviewers' results.

FileKindSize
SKILL.mdskill md12.2 KB
references/debate.mdmarkdown3.8 KB
references/duel.mdmarkdown1.2 KB
references/interview-panel.mdmarkdown1.4 KB
references/judge-split.mdmarkdown1.4 KB
schemas/council-report.v1.schema.jsonconfig4.7 KB
scripts/validate-output.shexecutablescript4.3 KB
scripts/validate.shexecutablescript4.6 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.
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 implementationStars: 322kUpdated Claude CodeCodexVerifiedInstall
requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 fallbackStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 alwaysStars: 322kUpdated Claude CodeCodexVerifiedInstall