Run a four-voice council to evaluate tradeoffs before making tough decisions.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "council" skill from askskill: 1. Download https://raw.githubusercontent.com/affaan-m/ECC/main/skills/council/SKILL.md 2. Save it as ~/.claude/skills/council/SKILL.md 3. Reload skills and tell me it's ready
Start a four-role council to evaluate whether we should launch the new recommendation feature this week. Let the four voices debate from user value, technical risk, business impact, and long-term strategy. First list arguments for and against, then give a final go/no-go recommendation with conditions.
A multi-perspective decision analysis with disagreements, key risks, arguments for and against, and a final launch recommendation.
Use the council mode to compare staying with a monolith versus splitting into microservices. Assign four voices to focus on delivery speed, system reliability, team coordination cost, and future scalability, then run a structured debate and recommend one option.
A clear comparison showing each path’s pros, cons, fit conditions, and the recommended choice.
Convene a four-voice council to decide whether this content growth project deserves budget next quarter. Let the four voices represent growth leadership, finance, execution team, and user research. Output the main disagreements, core evidence, and final recommendation.
A structured recommendation on whether to continue, adjust, or stop the project for faster budget decisions.
Convene four advisors for ambiguous decisions:
This is for decision-making under ambiguity, not code review, implementation planning, or architecture design.
Use council when:
Examples:
| Instead of council | Use |
|---|---|
| Verifying whether output is correct | santa-method |
| Breaking a feature into implementation steps | planner |
| Designing system architecture | architect |
| Reviewing code for bugs or security | code-reviewer or santa-method |
| Straight factual questions | just answer directly |
| Obvious execution tasks | just do the task |
| Voice | Lens |
|---|---|
| Architect | correctness, maintainability, long-term implications |
| Skeptic | premise challenge, simplification, assumption breaking |
| Pragmatist | shipping speed, user impact, operational reality |
| Critic | edge cases, downside risk, failure modes |
The three external voices should be launched as fresh subagents with only the question and relevant context, not the full ongoing conversation. That is the anti-anchoring mechanism.
Reduce the decision to one explicit prompt:
If the question is vague, ask one clarifying question before convening the council.
If the decision is codebase-specific:
If the decision is strategic/general:
Before reading other voices, write down:
Do this first so the synthesis does not simply mirror the external voices.
Each subagent gets:
Prompt shape:
You are the [ROLE] on a four-voice decision council.
Question:
[decision question]
Context:
[only the relevant snippets or constraints]
Respond with:
1. Position — 1-2 sentences
2. Reasoning — 3 concise bullets
3. Risk — biggest risk in your recommendation
4. Surprise — one thing the other voices may miss
Be direct. No hedging. Keep it under 300 words.
Role emphasis:
You are both a participant and the synthesizer, so use these rules:
Use this output shape:
## Council: [short decision title]
**Architect:** [1-2 sentence position]
[1 line on why]
**Skeptic:** [1-2 sentence position]
[1 line on why]
**Pragmatist:** [1-2 sentence position]
[1 line on why]
…
Build polished React and Next.js animations with reusable production-ready patterns.
Design security and risk controls for autonomous trading agents with transaction authority
Write and review React 18/19 components using modern best practices.
Get production-ready MySQL and MariaDB schema, query, and operations patterns.
Verify Laravel projects with environment checks, tests, security scans, and release readiness.
Audit Claude skills and commands with quick scans or full stocktakes.
Gather independent multi-model plans and debates for implementation and architecture decisions.
Argue decisions, record reasons, and return finished files.
Review contracts against playbooks with redlines, deviation flags, and impact analysis.
Aggregate many LLMs for second opinions, arbitration, and more reliable decisions.
Evaluate code review feedback rigorously before deciding whether to implement it.
Run local multi-model deliberation and synthesis for better coding decisions on Mac.