Nw Sar Critique Dimensions Agent Skill
Architecture quality critique dimensions for peer review. Load when performing architecture document reviews.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/nWave-ai/nWave --skill nw-sar-critique-dimensionsThe instruction itself
19 sections, as written by the authorArchitecture Quality Critique Dimensions
Dimension 1: Architectural Bias Detection
Technology Preference Bias
Pattern: tech chosen by preference, not requirements. Detection: ADR lacks comparison matrix, choice not mapped to requirements, justified only as "best practice." Severity: HIGH.
Resume-Driven Development
Pattern: complex/trendy tech without requirement justification. Examples: microservices for 3-person team, Kafka for 100 req/day, service mesh without complexity. Detection: complexity exceeds team size/requirements, tech adds resume value not solves problem. Severity: CRITICAL.
Latest Technology Bias
Pattern: unproven tech (<6 months, small community) for production. Detection: check maturity, community, LTS, fallback plan. Severity: HIGH.
Dimension 2: ADR Quality Validation
Missing Context
ADR lacks business problem, technical constraints, or quality attribute requirements. Future maintainers cannot validate. Severity: HIGH.
Missing Alternatives Analysis
No alternatives (min 2 required). Each must be evaluated against requirements with rejection rationale. Severity: HIGH.
Missing Consequences
Omits positive/negative consequences and trade-offs. Quality attribute impact not analyzed. Severity: MEDIUM.
Dimension 3: Completeness Validation
Missing Quality Attributes
Architecture doesn't address required attributes. Verify: performance (latency, throughput) | scalability | security (auth, data protection) | maintainability (modularity, testability) | reliability (fault tolerance, recovery) | observability (logging, monitoring, alerting). Severity: CRITICAL.
Missing Performance Architecture
Performance requirements exist but no optimization strategy (caching, indexing, rate limiting, CDN). Severity: CRITICAL.
Dimension 4: Implementation Feasibility
Team Capability Mismatch
Requires expertise team lacks. Verify learning curve reasonable, training plan exists. Severity: HIGH.
Budget Constraints
Infrastructure costs exceed budget. Verify cost estimate exists and aligns. Severity: HIGH.
Testability Validation
Architecture prevents effective testing. Components must enable isolated testing with ports/adapters. Severity: CRITICAL.
Dimension 5: Priority Validation
Validate roadmap addresses largest bottleneck.
Q1: Largest bottleneck? (timing data must confirm primary problem)
Q2: Simpler alternatives considered? (rejected alternatives required)
Q3: Constraint prioritization correct? (quantified by impact, constraint-free first)
Q4: Data-justified? (key decision with quantitative data)
Failure: Q1=NO (wrong problem) | Q2=MISSING (no alternatives) | Q3=INVERTED (>50% solution for <30% problem) | Q4=NO_DATA for performance
Review Output Format
review_id: "arch_rev_{timestamp}"
reviewer: "solution-architect-reviewer"
artifact: "docs/product/architecture/brief.md, docs/product/architecture/adr-*.md"
iteration: {1 or 2}
strengths:
- "{Positive decision with ADR reference}"
issues_identified:
architectural_bias:
- issue: "{pattern detected}"
severity: "critical|high|medium|low"
location: "{ADR or section}"
recommendation: "{actionable fix}"
decision_quality:
- issue: "{ADR quality issue}"
severity: "high"
location: "ADR-{number}"
recommendation: "{add missing section}"
completeness_gaps:
- issue: "{quality attribute not addressed}"
severity: "critical"
recommendation: "{add architecture section}"
implementation_feasibility:
- issue: "{capability, budget, testability concern}"
severity: "high"
recommendation: "{simplify or add mitigation}"
priority_validation:
q1_largest_bottleneck:
evidence: "{data or NOT PROVIDED}"
assessment: "YES|NO|UNCLEAR"
q2_simple_alternatives:
assessment: "ADEQUATE|INADEQUATE|MISSING"
q3_constraint_prioritization:
assessment: "CORRECT|INVERTED|NOT_ANALYZED"
q4_data_justified:
assessment: "JUSTIFIED|UNJUSTIFIED|NO_DATA"
approval_status: "approved|rejected_pending_revisions|conditionally_approved"
critical_issues_count: {number}
high_issues_count: {number}
Severity Classification
- Critical: resume-driven dev, missing critical quality attributes, untestable, wrong problem
- High: technology bias, incomplete ADRs, feasibility concerns, missing data
- Medium: missing consequences, minor completeness gaps
- Low: documentation improvements, naming consistency
Other skills for the same job
different authors, same section of the catalogue
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
How to use it
Take nwave-ai/nw-sar-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.