agentleFS
Sign inStart free
yatukyatuk/multi-model-orchestra/skills/council/SKILL.md

council

Skill1 starsChanged 4 days agoMITView on GitHub

Ask the same question to three models from different families (GPT, Kimi, DeepSeek by default), read-only and in parallel, then judge the answers blind. Use for design decisions, risky trade-offs, root-cause hypotheses and reviews where one model's view is not enough. Needs the orchestra skill's scripts.

151 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, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 134 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write the question to a file.

    line 13
  2. Very specific:

    Read council/answer-A.md, answer-B.md, ...

    line 24
  3. Very specific:

    Check status.txt. A lane marked FAILED is not an answer and not a vote.

    line 26
  4. Distinctive:

    Write down where they agree, where they disagree, and which claims you can check.

    line 31
  5. Distinctive:

    Check the checkable claims yourself (run the code, read the file, look up the API).

    line 32

“Common” is measured: kept by at least 6 in 10 of the 134 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

Council

One model can be confidently wrong. Three models from different families are wrong in different ways, and the differences are where the useful information is.

Run it

  1. Write the question to a file. Include the evidence (code excerpts, logs, constraints) and say what a good answer looks like: a recommendation, the main risk, and what would change the recommendation.
  2. Run:
../orchestra/scripts/mmo-council --question q.md --outdir council/ -C <repo>
# custom panel:
../orchestra/scripts/mmo-council --question q.md --outdir council/ \
  --lane codex:gpt-6-astra --lane deepseek:deepseek/deepseek-v4-pro --lane kimi:kimi-code/k3.1-pro
  1. Read council/answer-A.md, answer-B.md, ... before opening key.txt. The letters are shuffled, so you judge the reasoning and not the brand.
  2. Check status.txt. A lane marked FAILED is not an answer and not a vote. If fewer than two lanes answered, say so and do not call it a council.

Judge it

  • Write down where they agree, where they disagree, and which claims you can check.
  • Check the checkable claims yourself (run the code, read the file, look up the API).
  • Agreement is a hint, not proof: models share training data and blind spots.
  • A single dissent with a concrete, checkable argument beats a majority with none.
  • Your final answer is your own synthesis. Do not paste a panelist's answer as the result.
  • Tell the user which models answered, which failed, and where the panel split.

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.

Check your setup, free