knowledge-priming

# Knowledge Priming ## Purpose AI default = internet average. No project context → guesses framework, invents conventions, generic code not match stack. Knowledge priming fix: load concise project identity doc before design/implement/review. Not teach code principles (clean-code), structure rules (architecture), domain modeling (domain-driven-design). Answer different question: **"What is this project?"** -- tech stack, architecture style, directory layout, trusted docs, conventions other skills not infer from code. ## Config Resolution 1. Look `.lattice/config.yaml` in repo root 2. If found, check `paths.knowledge_base` for custom doc path 3. If doc exist at path, read + apply as ambient project context 4. If no config/path/doc found -- see "When No Document Exists" No embedded defaults. Every project identity unique -- no sensible generic default for "what your project." Knowledge base doc created by `knowledge-priming-refiner` skill or hand-written. ## When No Document Exists If no knowledge base doc found during config resolution, inform user: > No project knowledge base found. Without it, AI skills work from generic assumptions about tech stack, architecture, conventions. > > To create one, trigger **knowledge-priming-refiner** skill -- guided interview (~10 questions) that produces concise document (~50 lines). Once created, every Lattice skill use it as ambient context. > > Can also create `.lattice/standards/knowledge-base.md` manually and reference in `.latt...