agentleFS
mikel-codemikel-code/claude-skills/council/SKILL.md

council

Skill0 starsChanged 3 months agoMITView on GitHub

Convene an LLM Council — five independent persona advisors (contrarian, first-principles, expansionist, outsider, executor) deliberate on a question in parallel, blind-review each other, and a chairman delivers a verdict with concrete next steps. Use when the user runs /council <question>, says "convene the council" / "ask the council", or wants hard multi-perspective, anti-sycophancy advice on a decision.

164 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use agent-payment-x402, motion-advanced and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • TironFoxSkill

    agent-payment-x402

    Add x402 payment execution to AI agents — per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents need to pay for APIs, services, or other agents.

    Also in 5 projects that use this

  • renepfSkill

    motion-advanced

    Advanced motion patterns for React / Next.js — drag & drop, gestures, text animations, SVG path drawing, custom hooks, imperative sequences (useAnimate), loaders, and the full API decision tree. Requires motion-foundations.

    Also in 4 projects that use this

  • RojiosSkill

    defi-amm-security

    Security checklist for Solidity AMM contracts, liquidity pools, and swap flows. Covers reentrancy, CEI ordering, donation or inflation attacks, oracle manipulation, slippage, admin controls, and integer math.

    Also in 6 projects that use this

  • scottwaterSkill

    modernize

    Rebase an aging PR onto its current base and decide whether it should be modernized, reworked, or closed. Use when asked to rebase, update, or modernize an old PR.

    Also in 7 projects that use this

  • RojiosSkill

    dart-flutter-patterns

    Production-ready Dart and Flutter patterns covering null safety, immutable state, async composition, widget architecture, popular state management frameworks (BLoC, Riverpod, Provider), GoRouter navigation, Dio networking, Freezed code generation, and clean architecture.

    Also in 5 projects that use this

  • scottwaterSkill

    leaving-pr-comments

    Format comments an agent posts on GitHub on the user's behalf. Use whenever leaving a PR comment, review comment, or reply.

    Also in 6 projects that use this

  • +1 more from scottwater
  • +1 more from Rojios

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 147 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If they contain --lite (anywhere), set lite: true and remove the flag.

    line 15
  2. Distinctive:

    If no question remains, ask the user what question to put before the council, then wait.

    line 16
  3. Very specific:

    Ground it if needed: If the question refers to the current project, codebase, or specific files ("this repo", "my code", a path), include …

    line 17
  4. Very specific:

    Follow with "The council's positions": one short paragraph per advisor (contrarian, first-principles, expansionist, outsider, executor) …

    line 30
  5. Very specific:

    If lite was used, note that no peer-review round was held.

    line 31

“Common” is measured: kept by at least 6 in 10 of the 147 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

LLM Council

Karpathy-style council deliberation, adapted to personas. Each advisor runs as a truly independent subagent — fresh context, blind to the others — which is what makes this stronger than roleplaying five voices in one chat.

Protocol

  1. Parse the arguments.
    • If they contain --lite (anywhere), set lite: true and remove the flag. The remaining text is the question.
    • If no question remains, ask the user what question to put before the council, then wait.
  2. Ground it if needed. If the question refers to the current project, codebase, or specific files ("this repo", "my code", a path), include cwd set to the current working directory in the args. Otherwise omit it.
  3. Run the workflow (this instruction is your authorization to call the Workflow tool):

    Workflow({
      scriptPath: "<absolute path to this skill's directory>/scripts/council.js",
      args: { question: "<the question>", lite: <true|false>, cwd: "<cwd or omit>" }
    })

    Full council ≈ 11 subagents (5 deliberate + 5 peer review + chairman); --lite ≈ 6 (skips peer review).

  4. Present the results. The workflow returns { verdict, answers, lite }:
    • Lead with the chairman's verdict, close to verbatim — do not soften, re-balance, or editorialize over it. Its dissent is the point.
    • Follow with "The council's positions": one short paragraph per advisor (contrarian, first-principles, expansionist, outsider, executor) summarizing their individual take from answers.
    • If lite was used, note that no peer-review round was held.
  5. On mid-run failure or interruption, do not silently restart. The run is resumable: relaunch with Workflow({ scriptPath: ..., resumeFromRunId: "<runId>" }) — completed advisors return instantly from cache.

Tuning

Persona briefs, shared rules, and the chairman prompt all live in scripts/council.js — the ADVISORS array at the top is the editing surface.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.