make-it-work
Deep codebase context for Claude. Solid requirements for your team. Before the first line of code.
/plugin install make-it-work@insideout-aiSkills
Three focused skills that make Claude project-aware before it touches code.
Maps your codebase and builds a structured knowledge base that Claude loads before doing any work. Two rule files: architecture.md is the how (domains, components, code areas), product.md is the what (use cases, actors, business rules). Plus one skill per functional domain and use case — minimal, precise, loaded on demand.
The cross-reference map connects everything: every domain skill points to the use cases it affects, every use case skill points to the domains it touches. Claude follows these links automatically — when planning a feature it traces which domains are involved; when planning tests it finds which use cases are affected. Part of what go-deep builds is a hard enforcement rule in CLAUDE.md: before every commit, Claude checks whether any skill or doc needs updating. Nothing ships without the knowledge base staying in sync with the code. Run it once when you onboard a project.
Use cases
- Scaffold architecture.md and product.md capturing what the code can't tell you
- Build domain and use case skills Claude loads on demand
- Cross-reference map so Claude navigates planning and testing without you mapping it out
- Hard enforcement rule keeping knowledge base in sync with every commit
Example
/make-it-work:go-deepActs as a Product Analyst before development begins. Loads the project skills relevant to the ticket, digs into the affected code, and surfaces every gap — unclear language, missing edge cases, conflicting requirements, unstated assumptions — then walks you through them one question at a time.
The output is a Gherkin-ready refined spec. Unknown unknowns become explicit. Requirements are solid before a single line of code is written. Teams use it before refinement meetings so developers arrive with focused questions — or post the output directly to the Jira ticket for product to review asynchronously.
Use cases
- Surface unclear language, missing edge cases, and conflicting requirements
- Walk through every gap one question at a time
- Output a Gherkin-ready refined spec
- Use before refinement meetings or post to Jira for async review
Example
/make-it-work:close-the-gaps TICKET-123/make-it-work:close-the-gapsActs as a senior product coach to help you write a complete, elaboration-ready epic for any work management tool. Runs five structured phases — context ingestion, discovery interview, internal analysis, criterion-by-criterion validation, and epic generation — covering value proposition, target users & permissions, KPIs, use cases with Gherkin acceptance criteria, rollout plan, and definition of done.
Use cases
- Write or improve a product epic
- Flesh out a feature idea for engineering
- Turn a rough concept into a spec ready for elaboration
Example
/make-it-work:shape-the-epicInstall
/plugin install make-it-work@insideout-aiOr browse to claude.com/plugins and search for make-it-work.
Usage
/make-it-work:go-deep # Scaffold full project docs from scratch
/make-it-work:close-the-gaps TICKET-123 # Refine a ticket by ID
/make-it-work:close-the-gaps # Paste ticket content directly
/make-it-work:shape-the-epic # Write a complete epic from scratch or improve an existing oneBuilt for engineering teams working on large, complex codebases.
Not greenfield side projects. When your codebase has history, domain rules, and legacy decisions baked in, "generally smart" isn't enough. Claude needs to know your project.
Claude reads code well. But on a large, long-lived codebase it misses things — domain rules buried in old commits, implicit constraints never documented, business logic spread across layers. It guesses. The bigger the repo, the worse it gets.
make-it-work solves this at the source.
Built by InsideOut AI
InsideOut AI helps engineering organizations adopt AI in practical, secure, and outcome-driven ways - from AI-assisted development workflows to Agile delivery and engineering leadership practices.
Visit InsideOut AISupport
For questions, issues, or feedback, contact InsideOut AI through the website or open an issue in the plugin repository.