decision-evaluation-framework

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.

Classify decision items by urgency and importance on the 2x2 matrix and prescribe quadrant-appropriate action. Produces a 0-100 score.

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.

Export a rendered decision-analysis PDF — upload to Google Drive via the configured gws MCP server, copy to a chosen local path, or both. Run after /decision:render-pdf.

Apply Munger's inversion — invert the goal, list failure paths, and design avoidance behaviours and tripwires. Produces a 0-100 score.

Apply Kepner-Tregoe Decision Analysis — define MUST objectives as knockout filters and weighted WANT objectives, then assess adverse consequences. Produces a 0-100 score.

Apply weighted Multi-Criteria Decision Analysis — derive criteria, weight them, score each option, and compute weighted totals with sensitivity. Produces a 0-100 score.

Scaffold a new decision file with the canonical structure — title, context, options, constraints, stakeholders, timeline, open questions — ready to feed to /decision:analyze. Use this when the user describes a decision verbally rather than handing over an existing decision file.

Apply Boyd's OODA loop — observe, orient, decide, act — emphasising fast iteration over deep deliberation. Best for fast-moving or adversarial decisions. Produces a 0-100 score.

Surface the next-best foregone use of the resources committed by the decision, and benchmark against it. Produces a 0-100 score.

Apply Klein's Pre-Mortem to a single decision — imagine catastrophic failure 12 months out and work backwards to identify failure modes, early-warning signals, and mitigations. Produces a 0-100 score.

Adopt a red-team / devil's-advocate stance against the leading option — steel-man the case against, surface hidden assumptions, identify disconfirming evidence. Produces a 0-100 score.

Apply Bezos's Regret Minimization — project to a long-horizon future self and ask which option will be most regretted if not taken. Produces a 0-100 score.

Render a decision-analysis workspace into a polished Typst PDF — cover page, executive summary, decision context, per-framework sections, comparison table, and synthesis. Output goes to <workspace>/analysis.pdf. Run after /decision:synthesize.

Classify the decision as Type 1 (one-way door, hard to reverse) or Type 2 (two-way door) per Bezos, and prescribe deliberation depth accordingly. Produces a 0-100 score.

Apply second-order thinking — past the immediate effect, ask 'and then what?' through second and third-order consequences and reactions. Produces a 0-100 score.

Apply de Bono's Six Thinking Hats — deliberately move through factual, emotional, cautious, optimistic, creative, and process modes. Produces a 0-100 score.

Map stakeholders by interest and influence, predict positions, identify hidden veto holders, and design an engagement plan. Produces a 0-100 score.

Run a SWOT analysis on the decision — strengths, weaknesses, opportunities, threats — with cross-quadrant strategic moves. Produces a 0-100 score.

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.

Apply Suzy Welch's 10/10/10 — how will you feel about this decision in 10 minutes, 10 months, and 10 years. Debiases short-horizon thinking. Produces a 0-100 score.

Stress-test the decision across now / near / medium / long time horizons and surface horizon conflicts. Produces a 0-100 score.