documentation-audit
$
npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/documentation-auditEvaluates benchmark documentation completeness using BetterBench and Datasheets standards
- Identifies missing documentation required for benchmark evaluation
- Uses BetterBench 46-criterion framework and Datasheets for Datasets
- Analyzes documentation for reproducibility and completeness
- Produces a scored report with prioritized gaps and recommendations
SKILL.md
.github/skills/documentation-auditView on GitHub ↗
--- name: documentation-audit description: Assess documentation completeness against BetterBench/Datasheets standards execution: subagent prompt: ./prompt.md input: benchmark_documentation used-by: benchmark-archaeology --- # Documentation Audit SOP Assess benchmark documentation completeness against established standards: BetterBench 46-criterion framework, Datasheets for Datasets, and Data Statements for NLP. ## Input - **benchmark_documentation**: All available documentation for the benchmark (paper, README, website, datasheet) ## Procedure 1. Check documentation against BetterBench 46 criteria 2. Check against Datasheets for Datasets questions 3. Identify critical missing information 4. Assess reproducibility from documentation alone 5. Grade overall documentation quality ## Output Documentation completeness score with per-criterion pass/fail and prioritized gaps.
More from yogsoth-ai/de-anthropocentric-research-engine
- abductive-hypothesis-generationStrategy: 面对异常的最佳解释推理
- ablation-brainstormRemove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.
- ablation-component-mappingMap system architecture to ablatable units for ablation studies
- ablation-designDesign ablation studies to isolate component contributions in ML systems
- ablation-executionRemove components one by one from a system, record the response/impact of each removal.
- abp-vulnerability-classificationClassify assumptions on 2 axes — load-bearing (how much conclusion depends on it) × vulnerable (how likely to be false). Focuses attention on High-Load × High-Vulnerable quadrant.
- abstraction-extractionExtract abstract principles from concrete domain cases. Strips domain-specific details to reveal transferable mechanisms.
- abstraction-ladderPerform bisociation at multiple abstraction levels
- abstraction-ladderingMove between concrete and abstract framings — 3 levels up (Why?) and 3 levels down (How?) to find the most productive research level.
- abstraction-to-designAbstract biological principle to design principle. Bridge from biology to engineering.