AI Engineering

OpenSpec Explore helps you think through ideas, investigate problems, and clarify requirements before or during a change. It is for exploration and codebase reading, not implementation.

Openspec Propose creates a new change and generates proposal, design, and task artifacts in one step. Use it when you want to turn a change idea into implementation-ready specs quickly.

Project Discovery builds a map of a codebase by tracing structure, detecting the tech stack, and checking documentation against implementation. Use it when onboarding, finding entry points, or verifying docs.

Specify creates a full implementation specification from a brief description. It gathers requirements, designs the solution, and routes decomposition to Direct, Incremental, or Factory based on complexity.

Specify Factory decomposes complex requirements and solution designs into unit specs, holdout scenarios, and an execution manifest. Use it for multi-feature work, multi-component changes, or parallelizable workstreams.

Specify Solution creates and validates solution design documents for architecture, interfaces, and technical decisions. Use it when designing system structure, tracing PRD requirements, or working in solution.md files.

Brain Bootstrap seeds a new brain with durable project knowledge by reading code, docs, and git history or by interviewing the user. It is used after brain-setup to draft the first root pages and record key decisions through the brain CLI.

Brain Ingest turns conversation, documents, or research into structured brain pages through the `brain` CLI. Use it when knowledge should be classified, placed, and written into persistent project memory.

Brain Page defines how to read and write a project brain through the bundled brain CLI. Use it when creating, updating, or reading brain pages and root pages; never hand-edit brain files.

Claim Matrix Rewriter rewrites outline/claim_evidence_matrix.md as a bullet-only index driven by evidence packs instead of outline placeholders. Use it when you need the matrix to preserve the legacy claim/evidence format while reflecting evidence-first inputs.

Concept Graph builds a deterministic prerequisite DAG from an approved tutorial spec and writes it to outline/concept_graph.yml. Use it when tutorial concepts need stable ordering before module planning.

Reference-First Template provides a reusable shape for skills built around a lean router, reference files, machine-readable assets, and a deterministic script. Use it when creating or refactoring a skill into this repository's reference-first structure.