agentleFS
Sign inStart free
ArchieeRArchieeR/claude-skills/skills/counsel/SKILL.md

counsel

Skill0 starsChanged 3 months agoMITView on GitHub

Fire multiple LLM panels in parallel (e.g. OpenAI/Codex, Gemini/Antigravity, Grok, Perplexity) for sense-checks on architectural decisions, design reviews, hard problems. Synthesise their findings into agree/disagree table + net recommendation. Use when one model's opinion isn't enough — when the decision is structurally important and you want multiple voices to expose blind spots.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. chrislacey89/content-to-skill★ 1same name
    2. JorgeMenaDev/skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    When the user runs /counsel <question>, you orchestrate a panel of external LLMs, then synthesise.

    line 6
  2. Distinctive:

    Make sure CLI commands are non-interactive / headless-safe.

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

When the user runs /counsel <question>, you orchestrate a panel of external LLMs, then synthesise.

Default panels

  1. Codex / Azure GPT — via Agent subagent or CLI (codex exec --skip-git-repo-check -s read-only "...").
  2. Antigravity (Gemini) — via CLI (agy -p "<prompt>" 2>&1 | tail -120).
  3. Grok (xAI) — via CLI (grok -p "<prompt>").

Fail-fast rules (parallel + fail-fast council ≈ 30-40s total):

  • If a panel CLI is missing or errors with auth/quota, mark ⚠️ unavailable (<reason>) and proceed.
  • Any panel taking past 180s: abandon it, synthesise without it.
  • Never serialize panels; run them in parallel.

Process

  1. Dispatch all panels in parallel — single turn, multiple tool calls, run_in_background: true where supported.
  2. Collect outputs from each panel as they complete.
  3. Synthesise — create an agree/disagree table, then state a net recommendation with confidence level.

Flags

  • --quick — Codex + Grok only (drop Gemini)
  • --research — add Perplexity or deep-research search panel
  • --raw — append full panel outputs verbatim below the synthesis
  • --no-agy — drop the Antigravity panel

Synthesis format

## Counsel: <question>

| Dimension / Issue | Codex / GPT | Antigravity (Gemini) | Grok | Consensus |
|-------------------|-------------|----------------------|------|-----------|
| ...               | ...         | ...                  | ...  | ...       |

**Net recommendation:** ...

**Confidence:** <high/med/low> — <why>

(If a panel is unavailable, keep its column and write ⚠️ unavailable so the gap is visible. Never hide a missing voice.)

Notes

  • Each panel runs independently; one failing shouldn't block the others.
  • Synthesise faithfully — don't let one loud panel dominate. Flag genuine disagreements.
  • Make sure CLI commands are non-interactive / headless-safe.

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