Claude-skill-registry council-chat

Use when user wants to ask the AI council a question, get multiple AI perspectives, or consult with both Codex and Gemini. Triggers on phrases like "ask council", "council opinion", "what do the AIs think", "ask both models".

install

source · Clone the upstream repo

git clone https://github.com/majiayu000/claude-skill-registry

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/council-chat" ~/.claude/skills/majiayu000-claude-skill-registry-council-chat && rm -rf "$T"

manifest: skills/data/council-chat/SKILL.md

Council Chat Skill

General consultation with both Codex (GPT-5.2) and Gemini for questions, opinions, and analysis.

When to Use

User asks for the council's opinion
User wants multiple AI perspectives
User explicitly mentions "council" or "both models"
User asks for consultation on a technical question

Reasoning Level

Default: high

If user mentions "quick" or "brief", use medium. If user mentions "deep" or "thorough", use xhigh.

Execution

Identify the question or topic
Gather relevant context (read files if needed)

Run BOTH commands in parallel:

Codex:

codex exec --sandbox read-only -c model_reasoning_effort="high" "<question with context>"

Gemini:

gemini -s -y -o json "<question with context>"

Collect both responses
Synthesize into unified response

Response Format

## AI Council Response

### Codex (GPT-5.2) Says:
[Codex's analysis]

### Gemini Says:
[Gemini's analysis]

### Council Synthesis:
**Agreement:** [Points both models agree on]
**Divergence:** [Where they differ]
**Recommendation:** [Synthesized recommendation based on both]

---
*Session IDs: Codex=[id], Gemini=[id]*