Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nwave-ai/nw-rr-critique-dimensions
Critique dimensions and scoring for research document reviews
Passed 20 of 22 test cases with the skill, and 15 of 22 without it.
and 2 more in the full report
5 fixed15 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
In a literature review on quantum computing error mitigation, all 20 reference papers were published between January and March of 2021. What issue rating should be assigned to this publication timing pattern?
| Checked | Without skill | With skill |
|---|---|---|
| The critique assigns a medium severity flag to clustered publication dates. | Missed | Passed |
The instructions your model reads when the skill loads.
Load when reviewing research documents. Apply each dimension systematically.
Check: contradictory viewpoints included? | Multiple organizations/authors/perspectives? | Geographic/temporal diversity? | Sources truly independent (not circular)?
Flags: 60%+ from single org/author -> critical | All supporting same conclusion without counterpoint -> critical | Single geographic region -> medium | Clustered publication dates -> medium
Check: every major claim cited | sources reputable (peer-reviewed, official, established) | primary over secondary | technical sources recent (5 years) | confidence matches evidence
Flags: uncited claim -> high | blog/forum for factual claim -> high | all secondary sources -> medium | sources >5 years for tech -> medium | high confidence with 1-2 sources -> high
Check: search strategy documented | source selection criteria explicit | methodology transparent | confidence levels with rationale
Flags: no methodology section -> high | vague methodology ("searched the web") -> medium | no confidence ratings -> medium
For research driving architectural/strategic decisions.
Q1: Is this the largest bottleneck? (timing/measurement data?) | Q2: Simpler alternatives considered and rejected with evidence? | Q3: Constraint prioritization correct? (>50% solution for <30% problem = flag) | Q4: Key decision data-justified?
Flags: secondary concern addressed while larger exists -> critical | no measurement data for performance -> high | alternatives not documented -> high | prioritization not explicit -> medium
Output template:
priority_validation:
q1_largest_bottleneck:
evidence: "{timing data or 'NOT PROVIDED'}"
assessment: "YES|NO|UNCLEAR"
q2_simple_alternatives:
assessment: "ADEQUATE|INADEQUATE|MISSING"
q3_constraint_prioritization:
minority_constraint_dominating: "YES|NO"
test cases passed, vs 15 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.