capability-taxonomy-mapping
$
npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/capability-taxonomy-mappingBuilds capability taxonomies and maps benchmark coverage to identify gaps
- Organizes domain capabilities into hierarchical taxonomies
- Analyzes existing benchmarks and their descriptions
- Matches benchmarks to taxonomy nodes using semantic analysis
- Generates annotated taxonomy with coverage metrics and gaps
SKILL.md
.github/skills/capability-taxonomy-mappingView on GitHub ↗
--- name: capability-taxonomy-mapping description: Build capability taxonomy, map existing benchmark coverage execution: subagent prompt: ./prompt.md input: domain, existing_benchmarks used-by: benchmark-archaeology --- # Capability Taxonomy Mapping SOP Build a hierarchical capability taxonomy for a domain and map existing benchmark coverage onto it to identify gaps and redundancies. ## Input - **domain**: The capability domain to taxonomize (e.g., "language understanding", "visual reasoning") - **existing_benchmarks**: List of known benchmarks in the domain with brief descriptions ## Procedure 1. Construct hierarchical capability taxonomy from literature 2. Map each benchmark to taxonomy nodes it covers 3. Compute coverage density per node 4. Identify white spaces (uncovered capabilities) 5. Identify redundancy clusters (over-covered capabilities) ## Output Annotated taxonomy tree with coverage statistics 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.