think-parallel-perspectives-review v0.1.0A

Immutable. This exact content never changes and is served at /api/v1/blob/98d13ecce7f8c04c.

---
name: think-parallel-perspectives-review
description: Evaluates a decision or idea through several deliberately separated lenses in turn (facts, upside, risks, intuition, alternatives, process) so that no single mode dominates, then synthesizes them into a balanced read, producing a multi-lens review. Use when a choice needs a rounded look, or when risk-aversion or optimism is drowning out the other perspectives.
license: Apache-2.0
metadata:
  id: thinking-framework-skills.parallel-perspectives-review
  family: perspective-and-multi-lens
  evidence-tier: "P"
  version: 0.1.0
  standard: "0.8"
---
<!-- thinking-framework-skills | https://github.com/product-on-purpose/thinking-framework-skills | Apache-2.0 -->
# Parallel Perspectives Review

In ordinary review one mode dominates: a cautious voice or an optimist colors everything, and facts, feelings, and alternatives blur together. This skill separates them, examining the same decision through one lens at a time - facts and information, upside and value, cautions and risks, intuition and feelings, alternatives and creative angles, and the process or big-picture view - then synthesizing. Looking through the same lens at once ("parallel") gives the quiet modes airtime instead of letting the loudest dominate. The output is a **multi-lens review** ending in a synthesis. (This is the generic mechanism behind Six Thinking Hats, used descriptively; the branded framework's marketing claims are not relied on.)

## When to Use

- A decision or idea needs a rounded, balanced look before committing.
- Risk-aversion or optimism is dominating the discussion.
- Quieter considerations (intuition, alternatives) keep getting skipped.

## When NOT to Use

- A single lens is obviously all that matters; just use it.
- For deep adversarial stress-testing of one thesis (use red team) or for failure causes (use premortem).
- When the six lenses would be performed mechanically with only two or three carrying weight.
- As consensus theater rather than genuine separation of modes.

## Instructions

When asked for a parallel perspectives review, follow these steps:

1. **State what is being reviewed** in one sentence. Optional observer pre-pass: when the reviewer is personally involved, restate the situation in the third person before passing through the lenses. This third-person framing is the distancing move studied for personal and interpersonal problems, not for impersonal business choices.
2. **Pass through each lens separately.** For each, write only what that lens surfaces, not a blended take:
   - **Facts** - what is known and what information is missing.
   - **Upside** - the value and best case.
   - **Risks** - the cautions and downside.
   - **Intuition** - the gut read and feelings, named as such.
   - **Alternatives** - other options and creative angles.
   - **Process** - the big picture and what to do next.
3. **Keep the lenses clean.** Where a fresh subagent is available, run each lens pass from step 2 in its own subagent, given only the step 1 statement (the third-person restatement, if the observer pre-pass ran) and that one lens, never another lens's output, since a subagent that never saw the other lenses beats this context merely told not to let them leak; without one, run them here and do not let one lens leak into another, because that blur is what the method prevents. Drop a lens that genuinely does not apply and say so.
4. **Synthesize.** Integrate the lenses into a balanced read and name the central tension to resolve.
5. **Emit the multi-lens review** per `references/TEMPLATE.md`.

## Output Format

Use the template in `references/TEMPLATE.md`. The deliverable is the per-lens review plus a synthesis, not prose.

## Quality Checklist

Before finalizing, verify:

- [ ] Each lens contains only its own mode; the lenses do not blur together.
- [ ] The easily-skipped lenses (intuition, alternatives) actually got a real pass.
- [ ] Lenses that do not apply are dropped with a note, not padded.
- [ ] The synthesis names the central tension, not just a summary.
- [ ] The output is the multi-lens review artifact, not prose.

## Evidence

Tier **P** (flagged). This implements the parallel-thinking mechanism behind Six Thinking Hats (de Bono, 1985, trademarked; used here descriptively). Deliberately separating modes is modestly supported (some studies show moderate gains in critical thinking), but a review of thinking-skills frameworks (Moseley et al., 2005, University of Newcastle upon Tyne) found the branded framework's evidence base sparse, and de Bono's often-quoted "493%" productivity claim is uncited and is not used. Evidence is transferred from human contexts, not AI-validated. An optional third-person observer pre-pass, folded in from distanced self-reflection (wave-4 decision D4), is graded M, narrow. It is tested only on people reflecting on their own problems: close-relationship conflicts (Grossmann and Kross, 2014) and past stressors (Murdoch et al., 2023). No study tests an agent. Full grading: `evidence/dossier.md`.

## Examples

See `references/EXAMPLE.md` for a completed multi-lens review.