nw-dr-review-criteria
Critique dimensions, severity framework, verdict decision matrix, and review output format for documentation assessment reviews
Install / Use
npx skills add nWave-ai/nWave --skill nw-dr-review-criteriaInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Content & MediaSupported Platforms
Our assessment of nw-dr-review-criteria
nw-dr-review-criteria scores 84/100 on our quality scale, 886th of 1,156 Content & Media skills we index.
Its SKILL.md is 5.5 KB long, well organised into 13 sections with 1 code example: a solid amount of guidance for an agent.
It has 617 GitHub stars, a meaningful sign that others use it.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so nw-dr-review-criteria is actively maintained.
- Our last check on 2026-11-06 found the source still online.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-07. Automated pattern scan on 2026-10-07. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
nw-dr-review-criteria compared with similar skills
All 4 of these similar skills score higher than nw-dr-review-criteria; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| nw-dr-review-criteria (this skill)by nWave-ai | 84 | 617 | 2mo ago | SKILL.md |
| siyuanby siyuan-note | 100 | 47.3k | today | MCP Server |
| x402by browser-use | 100 | 121.0k | 4d ago | SKILL.md |
| algorithmic-artby anthropics | 100 | 177.9k | 56d ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 56d ago | SKILL.md |
Frequently asked questions
- How do I install nw-dr-review-criteria?
- Run
npx skills add nWave-ai/nWave --skill nw-dr-review-criteria. The install tabs above show the steps for each supported agent. - Which AI agents does nw-dr-review-criteria work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is nw-dr-review-criteria safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is nw-dr-review-criteria still maintained?
- The repository was last updated about 2 months ago, so nw-dr-review-criteria is actively maintained.
Skill content
View source on GitHubname: nw-dr-review-criteria description: Critique dimensions, severity framework, verdict decision matrix, and review output format for documentation assessment reviews user-invocable: false disable-model-invocation: true
Documentation Review Criteria
Critique Dimensions
1. Classification Accuracy
Verify type assignment against DIVIO decision tree.
Questions: Do cited signals support assigned type? | Contradicting signals ignored? | Confidence appropriate? | Decision tree leads to same classification?
Verification: 1) Run decision tree independently 2) Check positive signals present 3) Check for red flags 4) Verify confidence matches signal strength
Severity: if wrong classification leads to wrong verdict = blocking.
2. Validation Completeness
Verify all type-specific criteria checked. Questions: All items checked? | Pass/fail correct? | Issues properly located? | Any criteria missed?
Tutorial (required): completable without external refs | steps numbered/sequential | verifiable outcomes | no assumed knowledge | builds confidence
How-to (required): clear goal | assumes fundamentals | single task | completion indicator | no basics teaching
Reference (required): all params documented | return values | error conditions | examples | no narrative
Explanation (required): addresses "why" | context/reasoning | alternatives considered | no task steps | conceptual model
3. Collapse Detection Correctness
Verify all five anti-patterns checked with accurate findings.
- Tutorial creep: explanation >20% | How-to bloat: teaching basics | Reference narrative: prose in entries
- Explanation task drift: steps in explanation | Hybrid horror: 3+ quadrants
Verification: independently scan, count lines per quadrant, compare to documentarist's findings, flag discrepancies.
4. Recommendation Quality
Criteria: Specific (exact what/where) | Actionable (author knows next step) | Prioritized (important first) | Justified (why it matters) | Root cause (underlying issue)
Bad: "Improve the documentation", "Make it clearer" Good: "Move explanation in section 3.2 (lines 45-60) to separate doc", "Add return value docs for login()"
5. Quality Score Accuracy
Verify six characteristics: Accuracy (factual claims verified?) | Completeness (gap analysis thorough?) | Clarity (Flesch 70-80?) | Consistency (style 95%+?) | Correctness (errors counted?) | Usability (structural assessment?)
Note: Documentarist cannot fully measure accuracy (needs expert) or usability (needs user testing). Verify limitations properly scoped.
6. Verdict Appropriateness
Verify verdict matches findings per decision matrix below.
Severity Framework
| Level | Definition | Action | |-------|-----------|--------| | Blocking | Wrong classification/verdict, missed collapse making doc unusable | Must fix | | High | Multiple criteria missed, collapse missed but usable | Should fix; may block | | Medium | Single criterion missed, miscalibrated confidence, false positive | Recommended | | Low | Format inconsistency, wording clarity | Optional |
Reject: any blocking | 3+ high | classification wrong | verdict contradicts findings Conditionally approve: 1-2 high not affecting verdict | multiple medium but core correct Approve: no blocking/high | medium noted but not blocking
Verdict Decision Matrix
- Approved: all checks pass or low-only failures | no collapse | quality gates met (Flesch 70-80, purity 80%+)
- Needs Revision: medium/low failures only | no collapse | fixable without restructuring
- Restructure Required: collapse detected | purity <80% | multiple user needs | requires splitting
Verification Algorithm
- Count issues by severity 2. Check collapse_detection.clean 3. Check quality gates 4. Apply matrix 5. Compare to documentarist verdict 6. Flag discrepancy
Review Output Format
documentation_assessment_review:
review_id: "doc_rev_{timestamp}"
reviewer: "nw-documentarist-reviewer (Quill)"
assessment_reviewed: "{path}"
original_document: "{path}"
classification_review:
accurate: [boolean]
confidence_appropriate: [boolean]
independent_classification: "[your type]"
match: [boolean]
issues: [{issue, evidence, severity, recommendation}]
validation_review:
complete: [boolean]
criteria_checked: "[X/Y required + Z/W additional]"
missed_criteria: [list]
issues: [{issue, severity, recommendation}]
collapse_detection_review:
accurate: [boolean]
independent_findings: "[anti-patterns found]"
false_positives: [count]
missed_patterns: [list]
issues: [{issue, severity, recommendation}]
recommendation_review:
quality: [high|medium|low]
actionable: [boolean]
properly_prioritized: [boolean]
issues: [{issue, severity, improvement}]
quality_score_review:
accurate: [boolean]
issues: [{score, issue, correction}]
verdict_review:
appropriate: [boolean]
documentarist_verdict: "[their verdict]"
recommended_verdict: "[your verdict]"
verdict_match: [boolean]
rationale: "{justification}"
overall_assessment:
assessment_quality: [high|medium|low]
approval_status: [approved|rejected_pending_revisions|conditionally_approved|escalate_to_human]
issue_summary: {blocking: N, high: N, medium: N, low: N}
blocking_issues: [list]
recommendations: [{priority, action}]
Review Iteration Limits
Maximum 2 revision cycles. After cycle 2: escalate to human, return approval_status: escalate_to_human with rationale.
Related Skills
siyuan
47.3kAn open-source, privacy-first, self-hosted knowledge workspace where humans and AI agents work together 开源、隐私优先、自托管的知识工作空间,让人与智能体在此协作
x402
121.0kSet up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx 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 or .potx file (even if the extracted content will be used elsewhere, like in an em…
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
