Council

Assess a proposal from multiple perspectives when the user requests a council, debate or adversarial assessment.

9 starsOther Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add borkweb/skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add borkweb/skills --skill council
Manual install
git clone --depth 1 https://github.com/borkweb/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/core/council ~/.claude/skills/council

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Council

Assess a proposal from several useful perspectives and return a reasoned verdict. Default to simulated seats in one response; these are not independent evidence or actual expert experience. Delegate read-only seats only when the user requests parallel agents and the runtime supports them. When seats or councils are delegated, start independent ones in the same step, give each the evidence up front so it does not re-investigate, and have each return its output once.

## Frame and select

Identify the idea, decision, constraints and stakes from the request. Ask only for a consequential missing input. Use only the seats that add a distinct lens: Visionary (opportunity), Devil's Advocate (failure/falsifier), Pragmatist (feasibility), Ethicist (values/impact), Jester (reframing), or a requested domain, steward or user lens.

Options: `-q` gives openings and verdict only; `-r N` selects 1–4 rounds (default 2 for a full council); `-f X` selects a focus. Use quick mode for a small decision unless a full debate was requested. A single-seat request stays single-seat.

## Assess

Each seat gives its strongest evidence-based case without pre-answering another. Separate facts, inference and speculation. In full mode, challenge a specific claim per round, record meaningful position changes and preserve real unresolved disagreements. No disagreement is a valid outcome; do not manufacture tension or pretend convergence proves correctness.
Read the full skill on GitHub

Details

Skill name
council
Repository
borkweb/skills
Path
skills/core/council/SKILL.md
License
MIT
Repo updated
18 November 2026

FAQ

What does the Council skill do?

Assess a proposal from multiple perspectives when the user requests a council, debate or adversarial assessment.

How do I install the Council skill?

Claude Code plugin: /plugin marketplace add borkweb/skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Council popular?

It lives in borkweb/skills, which has 9 GitHub stars and 0 forks.

Related skills

Prototype

9

borkweb/skills

Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

Frontend & DesignIn 1 list

Agents Md Lint

9

borkweb/skills

Audit and trim AI agent instruction files (AGENTS.md, CLAUDE.md, CONVENTIONS.md, .cursorrules, etc.) by testing which facts an AI agent can discover from code alone. Use when asked to lint, audit, optimize, prune, or trim any agent instruction file in a repository. Removes redundant documentation that wastes context tokens. Supports a dry-run mode that reports findings without modifying files.

AI, LLMs & Agents

Auto Scope

9

borkweb/skills

Scopes a coding task before implementation — names the handful of files actually relevant (read/edit these), the areas to leave alone, and any open scope questions, so work doesn't start by reading the whole repo. Fires proactively at the start of substantive, multi-file, or unfamiliar-area work; stays silent on single-file edits, one-line fixes, questions, and continued work in an area already scoped this session. Use when beginning a feature, bug fix, or refactor that could plausibly touch several files or an area not yet seen this session.

Software Development

Discernment

9

borkweb/skills

Assess the evidence, uncertainty and failure conditions of a decision or claim when the user requests discernment, calibration or a high-stakes judgment check.

Other

Caveman

9

borkweb/skills

Speak in a terse caveman style only when explicitly requested by name. Supports lite, full and ultra; persists until stopped. Ordinary brevity or token-efficiency requests do not activate it.

Other

Plan Deep Review

9

borkweb/skills

Review a plan’s strategy and execution risks in expansion, selective expansion, hold-scope or reduction mode. Preserve settled scope and load only relevant domain checks. Use only when the user asks for it, directly or through bork:do.

Other

Browse the most popular Claude skills, all other skills, or write your own with the skills generator.