# make-it-work

Builds a structured knowledge base from your codebase so Claude works from your project's rules instead of guessing.

- plugin · `type=plugin` · Claude Code · ★ 12
- Author: insideout-ai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/insideout-ai/make-it-work
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/plugins/make-it-work

## What it does

This plugin targets teams whose repositories have years of history behind them. Claude reads code fine, yet domain rules buried in old commits and constraints nobody wrote down slip past it. `make-it-work` fixes that at the context level.

The `/make-it-work:go-deep` command walks the repo and produces two rule files: `architecture.md` for how the system is put together and `product.md` for what it does. On top of that come skills, one per functional domain and one per use case, each linking to the other side. Claude pulls a skill only when the description matches the task, so context stays lean. A rule written into `CLAUDE.md` makes Claude check before every commit whether a skill or doc has gone stale.

New projects get numbered domain skills like `domain-01-authentication`; existing ones keep their current naming. The second command, `/make-it-work:define-test-strategy`, writes a test-strategy skill and a `test-map.json` that ties use cases and domains to tests, including suites living in a separate QA repo. Run it after `go-deep` — if that step was skipped, the plugin offers to run it first. It installs no tooling and writes no tests.

## Install

### Claude Code (native platform)

**Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add anthropics/claude-plugins-community
```
In the agent chat (not a shell):
```text
/plugin install make-it-work@claude-community
```

## When to use it
- map domains and use cases across a large repository
- capture domain rules that exist only in developers' heads
- trace which use cases a domain change affects
- record where each test suite lives and how to run it
- keep the knowledge base current as commits land

## Example prompts
- Run `/make-it-work:go-deep` and build the knowledge base for this repo
- Onboard the `backend` repo with `/make-it-work:define-test-strategy`
- Refresh the test map and show me the coverage report only

## Similar
- [ponytail](https://affpapa.org/en/nevibecode/plugins/ponytail.md) — plugin · ★ 176443
- [impeccable](https://affpapa.org/en/nevibecode/plugins/impeccable.md) — plugin · ★ 88212
- [last-30-days-skill](https://affpapa.org/en/nevibecode/plugins/last-30-days-skill.md) — plugin · ★ 65508
- [claude-hud](https://affpapa.org/en/nevibecode/plugins/claude-hud.md) — plugin · ★ 28841
- [understand-anything](https://affpapa.org/en/nevibecode/plugins/understand-anything.md) — plugin · ★ 88314
- [mem0](https://affpapa.org/en/nevibecode/plugins/mem0.md) — plugin · ★ 67829

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md