agentleFS
akimisri17akimisri17/idea-to-app-kit/.agents/skills/go-live/SKILL.md

go-live

Skill0 starsChanged 40 days agoMITView on GitHub

Gets the app safely online and announced. Use when the person says "put it online", "launch it", "share the link", or when the wave that goes online is about to start.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Final check: run the check-wave skill on the live link, as each kind of person, on a phone if they use phones.

    line 15
  2. Distinctive:

    The announcement: write it in the customer voice from doc 2: what's new, what they do now, who to contact.

    line 18
  3. Distinctive:

    How to undo: write the exact steps to switch it off or go back, before anyone needs them.

    line 23

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Go live

Work through this checklist with the person. Do what you can yourself, ask before signing up for anything or spending money, and tick each item in the handoff.

Before the link goes public

  1. Terms and cost: re-check the host's price and business-use terms on the official page (researcher role), and record them in doc 4.
  2. Logins and secrets: set real passwords and keys in the host's settings, never in the code.
  3. Existing data: enter anything already in progress (e.g. orders sitting in chats), so the app starts with the true picture.
  4. Backups: confirm they run, and do one test restore.
  5. Final check: run the check-wave skill on the live link, as each kind of person, on a phone if they use phones.

Telling people 6. The announcement: write it in the customer voice from doc 2: what's new, what they do now, who to contact. The person sends it; never send it yourself. 7. Their own instructions: a step-by-step note for each person who runs the app (e.g. the owner's daily routine).

After launch 8. Week-1 watch: what to check each day (new entries arriving, errors, the M# numbers) and what would mean "undo". 9. How to undo: write the exact steps to switch it off or go back, before anyone needs them. 10. Results date: confirm the "Check results on" date in doc 1. The start-up check will raise it when it's due.

Reply in the step-by-step shape for anything the person must do, then save a checkpoint and use the write-handoff skill.


Adapted from pm-toolkit by Martin Foerster (MIT). See THIRD_PARTY_NOTICES.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.