
Generate meaningful commit messages from scope and changed files. No story_graph — scope from conversation, changed files, and persisted state. Use when user types /commit or requests a commit.
Shape source material into an Interaction Tree and State Model (story map and domain model). Use when shaping requirements, deriving epics and stories from source documents, or building a hierarchical structure of actor exchanges and domain concepts.
Respond to client proposals (RFP, Q&A, requirements) by converting materials to memory, creating a response strategy, and answering questions iteratively. Depends on abd-context-to-memory for RAG. Use when responding to proposals, creating response plans, answering RFP questions, or iterating on proposal strategy.
Build rich OO domain models from context using a 17-step evidence pipeline. Extracts structured evidence with scripts, then uses focused AI passes to discover mechanisms, assign decision ownership, and produce validated object models. Also produces Interaction Trees (story maps). Use when synthesizing requirements into domain models, deriving objects from source documents, or building story maps with domain concepts.
# ace-foo Ace-skill. Fill content pieces and run build.
Converts documents (PDF, PPTX, DOCX, XLSX, etc.) to markdown and chunks them for agent memory. Supports vector RAG search. Use when the user wants to "add to memory", "convert and chunk", "ingest content for agent", "refresh memory", "use memory", or process a folder of documents for AI agent context.
Transforms raw context into a validated OO domain model and interaction tree. Pipeline: Guidance → Sketch → Refine. Use when the user wants to "model domain", "build interaction tree", "extract domain from rules", or "solution model".
Drives the synthesis workflow (create_strategy, run_slice, validate) using abd-story-synthesizer. Use when running orchestrated story synthesis, shaping content into interaction tree and state model, or when the user asks to run the synthesis orchestrator.
Synthesizes a map-model-spec (domain model + story map) from chunked context. Pipeline: context (Stages 1–3) then map-and-model steps per parts/process.md (scaffold, classify, deepen, integrate, evidence, structure, finalize). Use when the user wants to "synthesize map model spec", "build story map from context", or "extract domain and stories from chunks".
Agile Skill Build — Create and scale ace-skills. Scaffold new skills and assemble content into AGENTS.md. Use when creating or scaling a skill with the standard ace-skill structure.