agentleFS
chatmaxima-comchatmaxima-com/chatmaxima-skills/skills/whatsapp-flow/SKILL.md

whatsapp-flow

Skill0 starsChanged 9 days agoMITView on GitHub

Create or edit a WhatsApp Flow, a multi-screen form shown inside WhatsApp or the ChatMaxima website chat. Use when the user wants a booking form, lead or sign-up form, survey, feedback form, or appointment request that customers fill in without leaving the chat.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask whether the flow is for WhatsApp or for the website chat.

    line 10
  2. Very specific:

    Call get_flow_schema for the exact format.

    line 17
  3. Distinctive:

    Keep it short. Ask only for what the business will use, and put the most important question first.

    line 28
  4. Very specific:

    Call create_whatsapp_flow.

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Create a WhatsApp Flow

1. Ask where it will be used

Ask whether the flow is for WhatsApp or for the website chat. This choice is permanent:

  • whatsapp: created on WhatsApp as a Draft. The user publishes it from the WhatsApp Flows page, and only a published flow can be sent. It needs a WhatsApp number from list_whatsapp_accounts.
  • web: works in the website chat straight away, but can never be published to WhatsApp.

2. Design the screens

Call get_flow_schema for the exact format. Use the Form Builder (screens) unless the user wants later questions to depend on earlier answers in ways the Form Builder cannot express, in which case use the Dynamic Data Flow (steps_config).

Form Builder rules:

  • 1 to 8 screens. Screen ids use uppercase letters and underscores only, no digits, for example DETAILS.
  • The first screen is the entry. Every screen must be reachable from it.
  • Inputs: text input, text area, dropdown, radio buttons, checkboxes, date picker and opt-in. Each input's name must be unique across the whole flow, because the answers arrive under those names.
  • Text and images: heading, subheading, body text, caption, and public images up to 300 KB.
  • At most one Nav Button (Footer) per screen. It can go to a fixed screen, or branch on a dropdown or radio answer.
  • The last screen ends the flow. Answers from every screen are sent together at the end.

Keep it short. Ask only for what the business will use, and put the most important question first.

3. Create and hand over

  1. Show the user the screens as a simple outline and get a yes.
  2. Call create_whatsapp_flow. It returns the flow alias, status and a link.
  3. For a WhatsApp flow, remind the user to publish it from the WhatsApp Flows page.
  4. To send it in a bot, add a WhatsApp Flow block (see the build-chatbot skill). The flow itself can only be tested on WhatsApp, by messaging the connected number.

Editing a flow

Read it with get_whatsapp_flow, then call update_whatsapp_flow with the complete new screens. Editing a published Form Builder flow creates a new draft of the same flow on WhatsApp, which the user publishes again. A published Dynamic Data Flow cannot change its steps. Never create a copy to edit unless the user asks for a new flow.

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.