菜单
Read all per-framework analysis fragments in a decision workspace and produce a cross-framework synthesis — agreement/disagreement matrix, score table, weighted verdict, and the open questions any individual framework couldn't resolve. Run after /decision:analyze, or invoke directly to re-synthesize.
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
Orchestrator — analyze a decision through multiple frameworks in parallel. Reads a decision file, fans out to N framework subagents simultaneously (one per selected framework), each produces a structured analysis fragment, then synthesis aggregates the results. Use this when the user wants a multi-lens evaluation of a major decision rather than running individual frameworks.
Apply Kahneman's outside view — define the reference class, look up the historical base rate, and benchmark the inside-view prediction against it. Produces a 0-100 score.
List, create, edit, or delete named lens-bundles (saved framework groupings) used by /decision:analyze. Bundles let the user predefine "for career decisions, run these five frameworks" without typing the list each time.
Apply Cost-Benefit Analysis to a single decision — quantify costs and benefits per option over a stated time horizon, run sensitivity, and produce a 0-100 score. Use when the user wants just this one lens, or as a building block called by /decision:analyze.
Apply Snowden's Cynefin frame — classify the decision domain (Clear, Complicated, Complex, Chaotic, Confused) and prescribe domain-appropriate action. Produces a 0-100 score.
Build a decision tree with probabilities and payoffs, roll back expected values, and report EV and variance per option. Produces a 0-100 score.
| name | synthesize |
| description | Read all per-framework analysis fragments in a decision workspace and produce a cross-framework synthesis — agreement/disagreement matrix, score table, weighted verdict, and the open questions any individual framework couldn't resolve. Run after /decision:analyze, or invoke directly to re-synthesize. |
Aggregates per-framework fragments into one document.
A workspace folder produced by /decision:analyze, with decision.md and a populated fragments/ directory. The user may pass the path or the slug; if neither, list recent workspaces and ask.
Read decision.md (for context) and every file in fragments/.
Extract the score (0-100) from each fragment. Each framework guide instructs the subagent to end with ## Score: <N>.
Build the score table:
| Framework | Score | One-line verdict |
|---|
Build the agreement matrix. Identify points where frameworks converge (e.g., "5/7 frameworks flag stakeholder-A as a blocker") and where they diverge (e.g., "MCDA prefers Option A; pre-mortem prefers Option B"). Convergence is signal; divergence is where the real work is.
Surface unresolved questions — what did multiple frameworks list as "would need to know X to decide"? These are the things to investigate before committing.
Weighted verdict. Compute a weighted average of the framework scores. By default, weight each framework equally. If the user has indicated a bundle bias (e.g., "personal" bundle suggests they care about regret-minimization more), reflect that. Always show both the equal-weighted and (if applicable) bias-weighted result.
Write synthesis.md in the workspace root. Structure:
# Synthesis: <Decision title>
## Score table
| Framework | Score | Verdict |
## Convergence
<where frameworks agree>
## Divergence
<where they disagree, and why>
## Unresolved questions
<items that need investigation before committing>
## Weighted verdict
- Equal-weighted: <score>/100, leaning <option/direction>
- <Other weightings if applicable>
## Recommendation
<one paragraph: what the integrated picture says, and what the user should do next>
## Confidence
<how robust the recommendation is — wide framework agreement vs split>
Report the synthesis path back to the user.