CtrlK
BlogDocsLog inGet started
Tessl Logo

consult

Fans out a question across all ready AI provider CLIs in parallel and synthesizes a single recommendation. Use when comparing AI answers, asking multiple models (Claude, Codex, Antigravity / agy, Copilot, Qwen, OpenCode), seeking multi-model consensus, or aggregating opinions on read-only questions.

74

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quintet Consult

Fans out a question across ready AI provider CLIs in parallel and synthesizes a single consensus recommendation.

Workflow

  1. Check Readiness: Verify provider availability using quintet doctor if pool status is unknown.
  2. Execute Consult: Fan out the question across ready providers:
!{QBIN="$HOME/.gemini/config/plugins/quintet/bin/quintet"; [ -x "$QBIN" ] || QBIN="$HOME/.gemini/extensions/quintet/bin/quintet"; [ -x "$QBIN" ] || QBIN=quintet; "$QBIN" consult "Best approach to dedupe a 10M-row stream in Rust?" claude,codex,agy,opencode}
  1. Output Validation & Fallback:

    • Validation: Verify responses were collected from ready models.
    • Fallback: If a provider times out or errors, log the failure and synthesize from available responses.
    • Empty Pool Guard: If zero providers respond, prompt user to check CLI auth.
  2. Structured Synthesis & Deliverable Format: Format the deliverable strictly using the following structure:

Consensus (3/3): High-confidence agreement across models.
Disagreements: Surface points where models differ and note which model held which view.
Recommendation: One clear recommendation with technical reasoning.

Reference Materials

  • Complete CLI subcommands, options, and setup: references/CLI_REFERENCE.md
Repository
salemaziel/omc-octo-quintet
Last updated
First committed

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.