sdlc

# sdlc Turns an idea into shipped, verified code through six stages. Each stage produces one markdown artifact in `sdlc/`, committed to git. The artifact is the handoff: no stage starts until the previous one's artifact exists and the user has accepted it. Adapted from Anthropic's [AI-Native SDLC Playbook](https://claude.com/blog/the-ai-native-sdlc-playbook), trimmed for a solo developer. The org-scale layer (separation of duties, policy owners, leading/lagging metrics) lives in `references/governance.md` and is opt-in. ## When to Use Activate when the user asks to: - Capture an idea, feature, or bug as a written intent before building - Turn an intent into a requirements/design spec - Plan an implementation before writing code - Set up a verification loop so changes check themselves before review - Define review policy (`REVIEW.md`) or run policy-driven review - Add regression evals for agent configuration (`CLAUDE.md`, skills, hooks) - Wire production metrics back into the planning loop Also activate when a repo already has an `sdlc/` directory and the user references an artifact in it. ## The Artifact Chain ``` sdlc/intent/<slug>.md -> what problem, why now, constraints, open questions sdlc/spec/<slug>.md -> requirements + design, concerns flagged sdlc/plan/<slug>.md -> files to change, work order, tests required <diff> + tests -> verified before a human looks PR + REVIEW.md passes -> reviewed against the spec and plan production signal -...