make-it-work

Refines a requirement into an AI-ready ticket: a Product Analyst session that fetches the ticket, loads project skills, explores affected code, asks gap-analysis questions in dependency-ordered batches, and outputs a Gherkin-format refined ticket. Supports an offline mode: export every question to a file to answer outside the session, then re-invoke with that file to inject the answers and resume. Use when refining a ticket before dev starts.

Bootstraps a per-project test strategy file and an initial regression baseline once per project, the same way go-deep bootstraps the knowledge base — generating a starting test-strategy doc, scaffolding placeholder tests for confirmed-uncovered critical flows, and wiring a UC/domain test-tagging convention with a re-runnable coverage-check mode. Use when a project needs its test strategy and baseline coverage established after go-deep has already run.

Implements a plan `plan-the-work` produced, step by step: writes each step's code, re-runs that step's named test(s) to green with a 5-attempt retry limit before escalating, and applies the test-vs-product-behavior guardrail — halting the entire plan on a real product-behavior question rather than guessing. Once every step is green, runs `run-regression` as a completion gate. This is the execute step of the spec → plan-the-work → execute → review-the-pr pipeline. Use when implementing a plan that plan-the-work already wrote.

Makes any codebase AI-ready with a 3-tier doc system (CLAUDE.md, orientation maps, domain & UC skills). Use when onboarding a project to Claude Code or auditing/updating existing docs after the project evolves.

Turns a spec or refined ticket into a concrete, execution-ready implementation plan — the plan-the-work step of the spec → plan-the-work → execute → review pipeline. Loads the project's skills, investigates the affected code across one or more repos, and writes an atomic, per-step plan file with no placeholders. When the target project has a test framework configured, it also writes and confirms per-step progression (red) and regression (currently-passing) tests. Use when planning how to implement a ticket, epic, or spec before any code is written.

Reviews a pull request in three documentation-grounded passes (business correctness, regression safety, coding standards) and emits an evidence-dense, verdict-first report. Use when reviewing a PR or diff in any repo that keeps CLAUDE.md plus uc-*/domain-* skills and .claude/rules docs.

Runs a project's regression suite — full or scoped to specific domains/use-cases — and reports pass/fail results; the shared implementation `execute` calls at the end of a plan. Use when running or checking a project's test suite, full or scoped to specific domains/use-cases.

Turns a rough idea into a complete, elaboration-ready epic via a guided interview session, PM-coach style. Use when writing or improving a product epic, drafting acceptance criteria, or documenting a feature for engineering.

Slices a large requirement into small, AI-ready, value-driven slices. Use when the user asks to split, slice, right-size, or write stories from a requirement.