Built & maintained byRuntime

Best practices

What PMs shipping fastest with Claude Code do differently.

Ten practices, one per page. Read in order or jump to the one that fixes the problem you have today.

01Practice

Write the PRD before the prompt

A PRD answers the four things a chat prompt skips: problem, user, done, and out-of-scope.

Read
02Practice

Use plan mode for anything non-trivial

Plan mode forces Claude to think before it edits. Approve the plan, then implementation gets boring.

Read
03Practice

Make CLAUDE.md the single source of truth

Product, voice, architecture, and conventions live in one file Claude reads on every session.

Read
04Practice

Author skills, not prompts

Skills auto-load by trigger phrase. Stop re-typing the same instructions in chat.

Read
05Practice

Ship a DESIGN.md with brand tokens

Tokens at the source level so contributors can’t reach default indigo by accident.

Read
06Practice

Wire up the right MCPs early

GitHub, Linear, Notion, PostHog. The model can read real data, not your paraphrase of it.

Read
07Practice

Never commit a secret

.env.example in repo, .env in .gitignore, MCP tokens loaded from the shell.

Read
08Practice

Treat the design system as a skill

Colors, type, voice, surfaces. Claude defaults to indigo and mesh gradients without it.

Read
09Practice

Generate product animations with Remotion

Programmatic video lets one PM ship feature demos and onboarding walkthroughs faster than waiting for the design team.

Read
10Practice

Onboard the agent like a teammate

First-day reading list, code map, voice doc. Treat the agent like a new hire who reads fast.

Read
11Practice

Log every session so Claude can pick up where you left off

Two files per task — requirements and a running work log — so Claude starts each session with full context instead of a blank slate.

Read

Get started

Clone the repo. Open it in Claude Code.

Two minutes from clone to your first PRD. Fill in three files and ship.

git clone https://github.com/runtm-ai/claudecode-for-pms.git
Open on GitHub

MIT licensed. Star the repo if it saves you an afternoon.