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
Section titled “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
Section titled “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
Section titled “Instructions”When asked for a parallel perspectives review, follow these steps:
- State what is being reviewed in one sentence.
- 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.
- Keep the lenses clean. Do not let one lens leak into another; that blur is what the method prevents. Drop a lens that genuinely does not apply and say so.
- Synthesize. Integrate the lenses into a balanced read and name the central tension to resolve.
- Emit the multi-lens review per
references/TEMPLATE.md.
Output Format
Section titled “Output Format”Use the template in references/TEMPLATE.md. The deliverable is the per-lens review plus a synthesis, not prose.
Quality Checklist
Section titled “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
Section titled “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 Cambridge-led review 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. Full grading: evidence/dossier.md.
Examples
Section titled “Examples”See references/EXAMPLE.md for a completed multi-lens review.
Deep dive: worked example
Section titled “Deep dive: worked example”A full worked run (the shared Northwind scenario)
Multi-Lens Review - Worked Example
Section titled “Multi-Lens Review - Worked Example”A completed run of think-parallel-perspectives-review, on the shared Northwind scenario. This is the quality bar a generated review should meet.
Northwind is a B2B SaaS weighing a self-serve free-tier launch. Here the skill gives the decision a rounded look before committing.
Under review
Section titled “Under review”- Launching a self-serve free tier in 6 weeks to hit the Q3 growth target.
Lenses
Section titled “Lenses”| Lens | What it surfaces |
|---|---|
| Facts | Trial-to-paid is down 6 points QoQ; a competitor launched a free tier; current free-to-paid conversion is unknown; the 6-week timeline is fixed by the board date. Missing: cost-per-free-user model, ICP-fit data on free signups. |
| Upside | If conversion holds, a free tier could 3x top-of-funnel and create a durable self-serve growth motion that compounds. |
| Risks | Cannibalizes paid; floods Sales with unqualified users; infra and support cost breaks unit economics; a rushed 6-week build ships an insecure billing path. |
| Intuition | The team is reaching for a competitor’s move under board pressure; it feels reactive rather than chosen, and “free tier” may be a proxy for “do something visible about growth.” |
| Alternatives | Fix the trial funnel; gated reverse-trial; outbound plus free pilots; extend the trial. Several are cheaper and more reversible. |
| Process | This is a near-one-way door. The big-picture move is to de-risk the two load-bearing unknowns (ICP conversion, cheaper alternatives) before committing the 6 weeks. |
Synthesis
Section titled “Synthesis”The upside is real but rests entirely on a conversion assumption the facts cannot yet confirm, and the intuition lens flags that the decision is board-pressure-reactive rather than chosen. The central tension: speed (a fixed Q3 date) versus reversibility (a free tier is hard to unwind). Resolve it by running a small gated pilot to test ICP conversion and a one-day comparison of the cheaper alternatives before committing the build, rather than treating the free tier as decided.
Note: the value is the intuition and alternatives lenses, which a risk-or-upside-only debate would have skipped. Together they reframed the choice from “build it fast” to “de-risk it first.”
Grounding: the full evidence dossier
Section titled “Grounding: the full evidence dossier”What the research does and does not show, with graded sources
Evidence Dossier: Parallel Perspectives Review
Section titled “Evidence Dossier: Parallel Perspectives Review”Single source of truth for the
parallel-perspectives-reviewskill. The SKILL.md, sidecar, and evals derive from this. If a claim is not here, it does not belong in the skill.
| Skill | thinking-framework-skills.parallel-perspectives-review (installable name think-parallel-perspectives-review) |
| Family | perspective-and-multi-lens |
| Evidence tier | P (flag: trademark lineage; branded version’s headline claims are uncited) |
| Confidence | Moderate that separating modes reduces blur; the branded productivity numbers are not credible |
| Status | draft (authored 2026-05-31 from the discovery corpus) |
1. The mechanism (what actually does the work)
Section titled “1. The mechanism (what actually does the work)”In ordinary review, one mode dominates: a risk-averse voice, or an optimist, colors everything, and facts, feelings, and alternatives blur together. Parallel perspectives review separates them: look at the same decision through one lens at a time - the facts and information; the upside and value; the cautions and risks; the intuition and feelings; the alternatives and creative angles; and the process or big-picture view - then synthesize. “Parallel” means everyone (or the agent) adopts the same lens at the same moment, which reduces adversarial cross-talk and makes sure the quiet modes (feelings, alternatives) actually get airtime. The work is done by forcing separation so no single mode crowds out the rest.
2. Lineage and trademark
Section titled “2. Lineage and trademark”- The branded version is Six Thinking Hats (Edward de Bono, 1985), a registered trademark. This skill implements the underlying mechanism - parallel thinking through separated lenses - under a descriptive name, citing de Bono as lineage. It does not use the trademarked “hat” branding as the product.
3. What the evidence shows, and what it does NOT show
Section titled “3. What the evidence shows, and what it does NOT show”Mixed / weak (hence the flag):
- A Cambridge-led review of thinking-skills frameworks (Moseley et al.) found the evidence base for the branded framework sparse.
- Some studies (for example with nursing students and managers) report moderate positive effects on critical thinking and cognitive complexity from deliberately separating modes.
- Do not repeat de Bono’s often-quoted “493% productivity improvement” claim. It is uncited and unsupported. Flagging this is part of the point: the mechanism (separating modes) is reasonable; the branded marketing numbers are not credible.
Net grade: P with a flag. The separation mechanism is plausible and modestly supported; the branded framework’s strong claims are not. Present the mechanism honestly and do not borrow the marketing.
4. Transferred-evidence flag
Section titled “4. Transferred-evidence flag”Evidence is from human group and educational contexts, not AI-augmented use. Transferred, not AI-validated. The AI value: a model defaults to one blended take; forcing it to produce a genuinely separate pass per lens (especially the easily-skipped feelings and alternatives lenses) yields a more rounded review and a structured artifact.
5. When it works / when it fails
Section titled “5. When it works / when it fails”Works best when: a decision or idea needs a rounded look; risk-aversion or optimism is dominating the discussion; quieter considerations (intuition, alternatives) keep getting skipped.
Fails or misleads when (poor-fit / anti-patterns):
- The lenses blur together in the output - the exact failure the method exists to prevent.
- All six lenses are performed mechanically when only two or three carry weight (padding).
- Used as consensus theater rather than genuine separation.
- A single lens is obviously all that matters (just use it).
- For deep adversarial stress-testing of one thesis (use red-team) or failure causes (use premortem).
6. Output artifact
Section titled “6. Output artifact”A multi-lens review: a row per lens (facts, upside, risks, intuition, alternatives, process) with what that lens surfaces, followed by a short synthesis that integrates them into a balanced read and names the tension to resolve.
7. Sources
Section titled “7. Sources”- de Bono, E. (1985). Six Thinking Hats - the branded lineage (trademarked; mechanism used descriptively).
- Moseley, D. et al. - Cambridge review of thinking-skills frameworks (sparse evidence base for the branded framework).
- Practitioner/education studies reporting moderate effects of deliberate mode separation.
Verification status: the de Bono lineage and the “493% is uncited” point are well-attested and are deliberately surfaced as an honesty demonstration. Treat the positive effect studies as moderate and context-specific; do not generalize them into a quantified product claim.