菜单
Surfaces stronger decisions through structured multi-agent debate across competing perspectives. Use when several plausible approaches exist and the tradeoffs need to be argued, not just listed.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Stress-tests an idea through adversarial analysis, steelmanning, and concrete counterarguments. Use when claims need pressure-testing, failure modes may be subtle, or security and robustness matter.
Pressure-tests a proposed design through research, architecture, engineering, and cold-reader review before implementation. Use when a non-trivial plan exists and you want to find weak assumptions before writing code.
Runs the hypothesis → benchmark → keep/discard protocol for an autoresearch iteration. Use when executing a `shaka autoresearch` loop; it is loaded automatically on each iteration.
Evaluates an external source (repo, tool, article, talk) against the current project and produces a report-only steal/adapt/reject decision table with named rejections. Use when mining another system for ideas worth adopting without copying its scope.
Creates the benchmark harness for a new autoresearch run from a natural-language objective. Use when starting an interactive `shaka autoresearch start` setup session.
Expands the solution space with structured creative exploration and divergent thinking. Use when the task benefits from novel options, brainstorming, or deeper exploration beyond the first obvious answer.
| name | council |
| description | Surfaces stronger decisions through structured multi-agent debate across competing perspectives. Use when several plausible approaches exist and the tradeoffs need to be argued, not just listed. |
| key | council |
| include_when | Multiple valid approaches exist. Design decisions with no clear winner. |
Multi-agent debate system where specialized agents discuss topics in rounds, respond to each other's points, and surface insights through intellectual friction.
Key Differentiator from red-team: Council is collaborative-adversarial (debate to find best path), while red-team is purely adversarial (attack the idea). Council produces visible conversation transcripts; red-team produces steelman + counter-argument.
Route to the appropriate workflow based on the request.
When executing a workflow, output this notification directly:
Running the **WorkflowName** workflow in the **council** skill to ACTION...
| Trigger | Workflow |
|---|---|
| Full structured debate (3 rounds, visible transcript) | Workflows/Debate.md |
| Quick consensus check (1 round, fast) | Workflows/Quick.md |
| Pure adversarial analysis | red-team skill |
| Workflow | Purpose | Rounds | Output |
|---|---|---|---|
| DEBATE | Full structured discussion | 3 | Complete transcript + synthesis |
| QUICK | Fast perspective check | 1 | Initial positions only |
| File | Content |
|---|---|
CouncilMembers.md | Agent roles, perspectives, voice mapping |
RoundStructure.md | Three-round debate structure and timing |
OutputFormat.md | Transcript format templates |
Origin: Best decisions emerge from diverse perspectives challenging each other. Not just collecting opinions - genuine intellectual friction where experts respond to each other's actual points.
Speed: Parallel execution within rounds, sequential between rounds. A 3-round debate of 4 agents = 12 agent calls but only 3 sequential waits. Complete in 30-90 seconds.
"Council: Should we use WebSockets or SSE?"
-> Invokes DEBATE workflow -> 3-round transcript
"Quick council check: Is this API design reasonable?"
-> Invokes QUICK workflow -> Fast perspectives
"Council with security: Evaluate this auth approach"
-> DEBATE with Security agent added
Works well with:
Last Updated: 2026-02-02