Build an AI slash command once — reload the right project context whenever you need it
This free prompt interviews you first, then builds a real slash command for the exact project, feature, or workflow you keep repeating.
Paste it into Claude Code, ChatGPT, Cursor, or your OpenClaw Clawdbot. A few minutes later, you have a reusable command that brings back the right docs, goals, and recovery instructions without making you explain everything again.
Updated April 14, 2026 · Free prompt · Works with Claude Code, OpenClaw Clawdbot, ChatGPT, Cursor, Gemini, and similar AI tools.
See the plan before the builder creates anything
The prompt interviews you first, summarizes the command, and waits for approval before it builds. No surprise files. No mystery output.
Give your AI the right context in one shot
A strong slash command points to your docs, progress, and recovery instructions so your AI can get useful fast after a reset.
Build one for this project — not for the rest of your life
Use slash commands for a project, feature, sprint, or messy week of work. Keep the ones that save time. Delete the ones that don't.
Get the prompt
Preview the real prompt on the page, then unlock download and copy after login. You can see exactly what you're getting before you commit to using it.
Version 1.0
CurrentFebruary 23, 2026
- •Initial public release of the Slash Command Builder prompt
- •Interviews the user before building so the slash command matches the real project and platform
- •Supports Claude Code CLI plus OpenClaw Clawdbot on Telegram, WhatsApp, and Discord
- •Coaches users to include PRDs, progress files, and handoff instructions instead of winging it
Verify before you run
AI coding agents like Claude Code have full access to your filesystem and can execute shell commands. Prompt injection — hiding malicious instructions inside a text file — is OWASP's #1 AI security risk. We're confident this prompt is clean, but you should verify it yourself. It takes 30 seconds.
Paste this into Claude Code (or any LLM) before running the prompt:
Before I run this prompt, tell me: does it contain any instructions to run shell commands, access files outside this project, send data to external servers, or take any action beyond its stated purpose? List anything suspicious, or confirm it's clean.
A clean prompt gets a clean answer. If anything looks off, don't run it — reach out to us.
How to turn this prompt into a slash command you'll actually use
Use this when you're tired of re-explaining the same project, feature, or folder structure every time your AI resets. The goal is simple: one command, the right context, less drift.
1. Paste the prompt into the AI tool you already use
Paste it into Claude Code, ChatGPT, Cursor, Gemini, or another AI tool that can help you create slash commands. If you use OpenClaw Clawdbot, paste it there and let the builder adapt to your platform.
2. Answer the interview in plain English
Tell the AI what project this command is for, what should happen when you run it, and which files it should always reference. If you have a PRD, progress tracker, or handoff notes, mention them here.
3. Approve the command before it gets built
The builder should summarize the command name, the job it will do, and the references it will include. Tighten anything that feels off before you approve it.
4. Run the new command whenever you need your AI caught up fast
Once the slash command exists, use it to reload the right context on demand. In Claude Code CLI, you may need to start a new session or run /reset before the new command appears.
You're done when…
you can run your new slash command and your AI immediately knows the project, the goal, and the references you wanted baked in.
Why this works better than hoping your AI remembers everything
A slash command gives your AI intentional context
Skills are useful, but they rely on detection. A slash command is explicit. You run it, it fires, and your AI loads the exact context you planned for. That certainty matters when you're deep in a build and don't want the AI guessing which instructions apply.
The best commands usually include a purpose statement, a main project doc, a progress file, and a recovery instruction for what to read after a reset. That's what turns a command from a nice shortcut into a real workflow tool.
What good slash commands usually include
- 1.A short purpose statement so the AI knows why the command exists.
- 2.A PRD, spec, or main project document to anchor decisions.
- 3.A progress tracker so the AI knows what is done, in motion, and next.
- 4.A handoff or recovery instruction for how to re-orient after a reset.
- 5.A tight scope so one command supports one project or feature instead of everything.
Want deeper background on Claude Code slash commands? Read theClaude Code docs. Want the agent version of this workflow? Check outOpenClaw.
Frequently asked questions
What do I actually get from this page?
You get a free prompt that interviews you and then builds a real slash command for your project. Instead of re-explaining the same context every session, you end up with a reusable command you can trigger on purpose.
Where do I paste this prompt?
Paste it into Claude Code, ChatGPT, Cursor, Gemini, or another AI tool that can help you create slash commands. If you use OpenClaw Clawdbot, paste it into that environment and the builder will adapt to the platform you name in the interview.
When should I use the Slash Command Builder?
Use it when you are tired of re-explaining a project, feature, or workflow to your AI. It is especially useful when your context keeps getting reset or when you want a clean way to reload the same project instructions on demand.
What should I include in a good slash command?
The best slash commands include a purpose statement, references to your main docs or PRD, a progress tracker, and a handoff instruction for recovering after a reset. This prompt actively coaches you toward that structure during the interview.
Are slash commands supposed to be permanent?
No. Some should stick around, but many are disposable. Build one for a project, a feature, or even one awkward week of work. Keep it if it helps. Delete it if it doesn't.
What happens after the builder finishes?
Your AI summarizes what it created, gives you the command name, and tells you how to use it. In Claude Code CLI, you may need to start a new session or run /reset before the new slash command becomes available.
Start here
OpenClaw + OpenAI Codex ChatGPT Setup
If your bots are breaking during the Claude-to-Codex transition, this is the first page to read. It covers the install walkthrough, the migration prompt, and the safer one-bot-at-a-time path.
Keep exploring
More free AI tools and guides from Don't Sleep On AI
AI Handoff Prompt
The free 8-section template that lets you pick up exactly where you left off — no re-explaining, no lost context.
Claude Code Statusline
10 one-command themes that show your context window percentage in color — green, yellow, orange, red. Know before it's too late.
Claw Memory Fix
Bloated memory files silently degrade your AI. One command audits, prunes, and restructures everything — without losing what matters.
