claude

deliberation

Decision-making through deliberation - seeking unity through discernment rather than consensus through debate

9 on GitHubv1.0.2MITupdated 1 month ago

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin deliberation in 2389-research/deliberation. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (4)

  • deliberation:clearness

    Convenes a clearness committee of specialized perspectives to examine a question with distributed depth rather than single-context breadth. Use when a topic spans multiple domains and deserves thorough parallel analysis — complex code reviews, architecture decisions, or multi-dimensional research.

  • deliberation

    Structured deliberation support for decisions worth sitting with — ethical questions, architecture choices, trade-offs, decisions where the user wants clarity rather than a handed-down conclusion. Use when a question deserves genuine discernment; may involve clearness, discernment, or gathered depen

  • deliberation:discernment

    Runs structured internal deliberation before answering, surfacing multiple perspectives and naming tensions rather than jumping to a single conclusion. Use when a question carries ethical weight, has multiple valid approaches, involves significant trade-offs, or risks harm.

  • deliberation:gathered

    Facilitates participatory discernment where the user contributes their own voice alongside agent perspectives, finding clarity together rather than receiving analysis. Use when the user has a stake or position in a decision and wants to participate — signaled by phrases like "I'm torn," "I've been t

View source on GitHub 2389.ai

Similar plugins

andreessen

claude

Marc Andreessen-mode decision and productivity skill. Market-first operator that pressure-tests ventures/ideas/features/bets (market > team > product; product/market fit is the only milestone; bias to build) and runs the 3x5-card + Anti-Todo routine. Fixed anti-sycophancy operating prompt: counterargument first, no disclaimers, explicit confidence levels, no capitulation. Issues hard verdicts backed by deterministic stdlib tools.

1 skill · 2 commands · 1 agent

alirezarezvani/claude-skills 29,725

council

claude

18 AI personas deliberate your hardest decisions — structured multi-round deliberation with genuine model diversity. One command: /council

2 skills · 18 agents

0xNyk/council-of-high-intelligence 4,840

meeting-bots

claude

Convene a meeting of AI personas (Boss, Pusher, Rookie, Watcher, Cynic) to debate your question. 3 to 10 participants, mix teams (dev, design, product, business, life), add custom personas on the fly.

1 skill · 25 agents

davepoon/buildwithclaude 3,741

claude-subconscious

claude

A subconscious for Claude Code. A Letta agent watches your sessions, accumulates context, and whispers guidance back.

hooks

letta-ai/claude-subconscious 2,910

executive

claudecodex

Direction, capital and attention allocation, cross-functional arbitration, strategy validation, and the method for structuring the organization itself.

7 skills

cbrock84/headcount 2,573

learning-opportunities

claudecodex

Science-based learning exercises for deliberate skill development during AI-assisted coding

1 skill

DrCatHicks/learning-opportunities 2,552

Maintain deliberation?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted