yogsoth-ai 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
- Construct hierarchical capability taxonomy from literature
- Map each benchmark to taxonomy nodes it covers
- Compute coverage density per node
- Identify white spaces (uncovered capabilities)
- Identify redundancy clusters (over-covered capabilities)
Output
Annotated taxonomy tree with coverage statistics and prioritized gaps.
Available SOPs
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |