agentsclimarketplace

Think parallel perspectives review

Skill product-on-purpose/thinking-framework-skills/skills/think-parallel-perspectives-review

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.From its SKILL.md

Install
npx -y skills add product-on-purpose/thinking-framework-skills --skill think-parallel-perspectives-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

4.0 KB, 770 tokens by cl100k_base, as published. Nobody here has run it

<!-- 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.
  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. 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.
  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 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

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

What ships with it: 5 files

13.2 KB alongside SKILL.md

eval/

evidence/

references/

Keep looking

Skills are one crate of 326,679. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.