菜单
First-run onboarding for the decision-evaluation-framework plugin. Interview the user about output paths, preferred frameworks, default lens-bundles, and Google Drive export settings, then write the config to the plugin user-data directory. Run before first use of /decision:analyze.
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 | onboard |
| description | First-run onboarding for the decision-evaluation-framework plugin. Interview the user about output paths, preferred frameworks, default lens-bundles, and Google Drive export settings, then write the config to the plugin user-data directory. Run before first use of /decision:analyze. |
One-time setup. Asks the user a small set of questions and writes a config file the rest of the plugin reads.
DATA_ROOT="${CLAUDE_USER_DATA:-${XDG_DATA_HOME:-$HOME/.local/share}/claude-plugins}/decision-evaluation-framework"
mkdir -p "$DATA_ROOT"
Config lives at $DATA_ROOT/config.json. Never write to ~/.claude/ or to the plugin install directory.
Ask the user:
~/decisions/ (one folder per analysis: ~/decisions/<YYYY-MM-DD>-<slug>/).Decision-Log if they don't have one). Store the path; don't auto-init the repo unless they ask.frameworks/ directory of the plugin install). Ask them to pick a default set (5-10) that runs when /decision:analyze is invoked without a --bundle or --frameworks flag.quick — cost-benefit, pre-mortem, reversibility, regret-minimizationstrategic — swot, mcda, second-order, stakeholder-map, time-horizonpersonal — regret-minimization, ten-ten-ten, reversibility, inversioncrisis — ooda, cynefin, pre-mortem, reversibilityfull — all 20 frameworks
The user can accept these, edit them, or skip.gws-personal (default) or gws-dsrholdings. Ask which (or "none — local-only output").Decisions). Optional — if blank, export prompts each time.{
"version": 1,
"outputs": {
"mode": "local | repo",
"local_root": "/home/<user>/decisions",
"repo_path": null
},
"default_frameworks": ["cost-benefit", "pre-mortem", "..."],
"bundles": {
"quick": ["cost-benefit", "pre-mortem", "reversibility", "regret-minimization"],
"strategic": ["swot", "mcda", "second-order", "stakeholder-map", "time-horizon"],
"personal": ["regret-minimization", "ten-ten-ten", "reversibility", "inversion"],
"crisis": ["ooda", "cynefin", "pre-mortem", "reversibility"],
"full": ["<all 20>"]
},
"drive": {
"mcp_server": "gws-personal | gws-dsrholdings | null",
"default_folder": "Decisions"
},
"pdf": {
"author": "<name>"
}
}
Confirm the written config to the user. Tell them they can edit $DATA_ROOT/config.json directly later, or re-run /decision:onboard to redo the interview.