Tachi Orchestration Skill

Domain knowledge extracted from the tachi orchestrator agent to support the OWASP four-step threat modeling pipeline. This skill provides reference material that the orchestrator loads on-demand at specific workflow phases, keeping the agent definition focused on orchestration logic.

Domain Coverage

This skill contains six categories of domain knowledge:

1. Format Detection -- Input format recognition patterns for ASCII, Free-text, Mermaid, PlantUML, and C4 architecture descriptions with priority ordering and heuristic matching rules.

2. DFD Classification -- DFD element type classification signals for External Entity, Process, Data Store, and Data Flow with ambiguous-classification defaults and format-specific extraction guidance.

3. Trust Boundaries -- Format-specific boundary notation for Mermaid subgraph, ASCII dashes, PlantUML boundary, C4 boundaries, and Free-text prose markers.

4. Dispatch Rules -- STRIDE-per-Element normalization table mapping DFD element types to applicable threat categories, AI keyword dispatch rules with keyword-to-category mappings and matching semantics, dispatch table format specification, and the five correlation rules with detection algorithm and group assembly instructions.

5. Coverage Requirements & Matrix -- Required STRIDE+AI categories per component type (external-entity, process, data-store, data-flow, llm-process, mcp-server), category-to-agent mapping for targeted re-analysis, three-state coverage matrix cell model, deduplication rules, and footnote conventions.

6. Output & SARIF -- Output format specification for threats.md (frontmatter fields, all 7 required sections plus Section 4a), SARIF 2.1.0 generation specification with fingerprint preservation and taxonomy passthrough rules, structural validation checklist, and error handling templates.