菜单
Three-agent adversarial debate protocol for strategic decisions. Two advocates steelman opposing positions while a moderator identifies risks and synthesizes a binding consensus. Use when choosing between alternatives, evaluating tradeoffs, or making high-stakes decisions.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/dirien/yet-another-agent-harness --skill decide命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | decide |
| description | Three-agent adversarial debate protocol for strategic decisions. Two advocates steelman opposing positions while a moderator identifies risks and synthesizes a binding consensus. Use when choosing between alternatives, evaluating tradeoffs, or making high-stakes decisions. |
| compatibility | No external tool dependencies. Requires an agent capable of spawning parallel sub-agents and performing web research. |
Run a structured three-agent debate to reach consensus on a strategic decision. Two advocates steelman opposing positions while a moderator asks hard questions, identifies risks, and synthesizes the binding consensus.
Why this works: adversarial structure surfaces arguments brainstorming misses. Evidence-grounded research prevents epistemic closure. Forced concessions in Round 2 prevent entrenchment. The moderator writes the binding consensus after hearing both sides.
Before running the debate, verify the input contains a genuine decision with at least two distinguishable options or courses of action.
If the input is a factual question, explanation request, or single-option statement, respond directly instead: "This protocol works best when choosing between alternatives. Could you rephrase with the options you're weighing, or ask me directly?"
When in doubt, proceed — err on the side of running the debate.
Read project documentation and context files to understand the decision space. Common sources include README, architecture docs, product docs, recent git history, and any files the user referenced.
From the decision topic, formulate two clear, opposing positions:
If the topic naturally implies two sides (e.g., "gRPC vs REST"), use those directly. If the topic is open-ended (e.g., "pricing strategy"), research the space and formulate the two strongest opposing approaches.
Extract hard constraints from the user's message or project docs: budget limits, timeline requirements, team size, technical constraints, business requirements, non-negotiable values.
Generate the debate brief before proceeding. Evaluate against three conditions:
If all conditions pass, present the brief and proceed to Phase 1:
Decision: [one-line summary]
Position A: [name] — [one-sentence description]
Position B: [name] — [one-sentence description]
Constraints: [list any hard constraints]
Launching Round 1...
If any condition fails, present the brief and ask the user whether to reframe or proceed as-is.
Launch three agents in parallel. Each agent runs independently and cannot read the others' output.
Compose agent prompts following
references/debate-prompts.md — Round 1 section.
After all three agents complete, present to the user:
Then immediately proceed to Round 2.
Launch three agents in parallel. Each agent receives a summary of the other agents' arguments and must respond.
Compose agent prompts following
references/debate-prompts.md — Round 2 section.
Show the user:
Ask the user if they want to save the consensus. Determine the appropriate file based on the decision type:
biz.mdARCHITECTURE.md or ADR-NNN.mdPRODUCT.md