Nw Rr Critique Dimensions Agent Skill
Critique dimensions and scoring for research document reviews
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/nWave-ai/nWave --skill nw-rr-critique-dimensionsThe instruction itself
7 sections, as written by the authorCritique Dimensions for Research Review
Load when reviewing research documents. Apply each dimension systematically.
Dimension 1: Source Selection Bias
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
Dimension 2: Evidence Quality
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
Dimension 3: Replicability
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
Dimension 4: Priority Validation
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"
assessment: "CORRECT|INVERTED|NOT_ANALYZED"
q4_data_justified:
assessment: "JUSTIFIED|UNJUSTIFIED|NO_DATA"
verdict: "PASS|FAIL"
Dimension 5: Completeness
Check: knowledge gaps documented (what searched, why insufficient) | conflicting info acknowledged with credibility analysis | all required sections present (summary, findings, sources, gaps, citations) | research metadata included
Flags: missing gaps section when gaps exist -> critical | conflicting sources unacknowledged -> high | missing required sections -> high | no metadata -> medium
Review Output Template
review_id: "research_rev_{timestamp}"
reviewer: "nw-researcher-reviewer (Scholar)"
issues_identified:
source_bias:
- issue: "{specific description with numbers}"
severity: "critical|high|medium"
recommendation: "{actionable fix}"
evidence_quality:
- issue: "{specific claim or location}"
severity: "critical|high|medium"
recommendation: "{actionable fix}"
replicability:
- issue: "{what is missing}"
severity: "critical|high|medium"
recommendation: "{actionable fix}"
priority_validation:
- issue: "{mismatch description}"
severity: "critical|high|medium"
recommendation: "{actionable fix}"
completeness:
- issue: "{missing element}"
severity: "critical|high|medium"
recommendation: "{actionable fix}"
quality_scores:
source_bias: 0.00
evidence_quality: 0.00
replicability: 0.00
completeness: 0.00
priority_validation: 0.00
approval_status: "approved|rejected_pending_revisions"
blocking_issues:
- "{critical issue 1}"
iteration: 1
max_iterations: 2
Other skills for the same job
different authors, same section of the catalogue
Searches across your Notion workspace, synthesizes findings from multiple pages, and creates comprehensive research documentation saved as new Notion pages. Turns scattered information into structured reports with proper citations and actionable insights.
Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.
Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.
Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.
【强制】所有技术文档查询必须使用本技能，禁止在主对话中直接使用 mcp__context7-mcp 工具。触发关键词：查询/学习/了解某个库或框架的文档、API用法、配置参数、错误解释、版本差异、代码示例、最佳实践。本技能通过 context7-researcher agent 执行查询，避免大量文档内容污染主对话上下文，保持 token 效率。
Generates rich technical documentation pages with dark-mode Mermaid diagrams, source code citations, and first-principles depth. Use when writing documentation, generating wiki pages, creating technical deep-dives, or documenting specific components or systems.
Maximum-saturation research orchestration: ALWAYS proposes the final materials first (PDF+DOCX default), then parallel explore+librarian swarms across codebase, web, official docs, and OSS repos — max-roster teammode when the harness has it — with live journaling, a recursive EXPAND loop driven by leads workers return in message text, empirical verification by running code, and a cited synthesis with charts/Mermaid/assets behind a mandatory visual-QA gate. ACTIVATES ONLY on an explicit user demand for research — the word 'ulw-research' ('/ulw-research', '$ulw-research'), any 'ulw' research wording, 'ultradebate' or 'hyperdebate' research requests, or an explicit request for research / deep research / an ultra-precise investigation, in any language. Never self-activates for ordinary questions, debugging, or implementation context-gathering. While active it overrides exploration-bounding defaults: exhaustive coverage is the goal.
"Solve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. Activates when asked to 'solve this IMO problem', 'prove this olympiad inequality', 'verify this competition proof', 'find a counterexample', 'is this proof correct', or for any problem with 'IMO', 'Putnam', 'USAMO', 'olympiad', or 'competition math' in it. Uses pure reasoning (no tools) — then a fresh-context adversarial verifier attacks the proof using specific failure patterns, not generic 'check logic'. Outputs calibrated confidence — will say 'no confident solution' rather than bluff. If LaTeX is available, produces a clean PDF after verification passes."
How to use it
Take nwave-ai/nw-rr-critique-dimensions from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.