Medo App Builder

Medo is a chat-driven full-stack application builder.
Official website: https://www.medo.dev

Users describe what they want in natural language and Medo generates a production-ready web product, including:

• - frontend UI
• backend services
• database schema
• integrations
• deployable hosting

Typical outputs include:

• - websites
• web applications
• dashboards
• SaaS products
• admin panels
• internal tools
• landing pages
• interactive web pages
• browser games and mini games

This skill enables AI agents to interact with the Medo platform to create, iterate, generate, and deploy applications.

All platform operations must be executed through the packaged CLI script:

CODEBLOCK0

Do not call platform APIs directly. Always use the CLI commands provided by this skill.

When to Use This Skill

Use this skill whenever the user wants to:

• * create a website
• create a webpage
• build a web application
• build a dashboard
• create a SaaS product
• build an admin panel
• build an internal tool
• create a landing page
• build an interactive web page
• create a browser game
• create a mini game
• generate an MVP web product
• modify an existing Medo project
• publish or deploy a Medo application

Do not use this skill for unrelated programming tasks.

Routing Keywords

Trigger this skill if the request includes concepts such as:

• * build a website
• create a webpage
• build a web app
• create a SaaS
• build a dashboard
• create an admin panel
• build an internal tool
• create a landing page
• build a browser game
• create a mini game
• generate a web product
• make a snake game webpage
• build a todo web app
• create a blog site

Example Requests

Examples that should route to this skill:

• * "Create a todo list web app"
• "Build a personal blog website"
• "Make a dashboard for sales analytics"
• "Create a SaaS landing page"
• "Build an admin panel"
• "Write a snake game webpage"
• "Create a browser game"
• "Build a mini web game"
• "Modify my Medo project"
• "Publish this Medo app"

Stateless Execution Model

The CLI script is stateless.

It does not store workflow state between calls.

Application workflow state is maintained by the Medo platform and must be inferred from:

• * INLINECODE0
• INLINECODE1
• application detail
• conversation trajectory events

Agents must pass the appropriate identifiers when continuing conversations or modifying applications.

Application Lifecycle Rules

Medo applications follow a strict lifecycle.

Agents must follow these rules.

Initial Creation

For a new application:

1. 1. Start with a chat request describing the product.
2. The application enters the PRD refinement stage.
3. Continue chatting to refine the specification.
4. When the trajectory contains a Generate App button (type":"button" and event":{"name":"generateApp"} in result.artifact.parts[].data.actions[]), trigger application generation using generate-app.

Generation is required only once during the initial creation.

Multi-Round Modification

After an application has already been generated:

• * Do not call generate-app again.
• Continue using chat with the same appId and conversationId.

Normal chat messages modify the existing application.

Publishing

Publishing is allowed after the application has been generated at least once.

Rules:

• * Publishing does not require another generation step
• Publishing may happen anytime after the first generation
• Publishing must be followed by status polling (or use --wait flag)

Typical deployment flow:

CODEBLOCK1

Or use the --wait flag to auto-poll:

CODEBLOCK2

Stop polling when the status becomes:

• * INLINECODE13
• INLINECODE14

Application URLs

Medo provides two types of URLs during the lifecycle.

Project Preview (Editor / Development)

After the application is created, the project can be accessed at:

CODEBLOCK3

This URL can be shared with the user for:

• * viewing the project
• editing the application
• previewing the generated result

The preview URL becomes available once an appId is created.

Production Deployment URL

After publishing succeeds, the application is accessible at:

CODEBLOCK4

This is the public production URL of the deployed application.

Only return this URL after publishing completes successfully.

Standard Workflow

Create New Application

CODEBLOCK5

Modify Existing Generated Application

CODEBLOCK6

(no additional generation step required)

Deploy Application

CODEBLOCK7

Or:

CODEBLOCK8

Available Commands

All commands are executed via the CLI script.

Important: Always set the MEDO_API_KEY environment variable before running commands.

CODEBLOCK9

list-apps

List all applications belonging to the authenticated user.

Usage:

CODEBLOCK10

Optional Parameters:

• - --brief: Output only key fields: appId, name, type, appFocus, host, updatedAt. Recommended for agents to reduce token usage.
• INLINECODE24: Filter by app name (substring)
• INLINECODE25: Page number (default: 1)
• INLINECODE26: Page size (default: 12)

Example:

CODEBLOCK11

Returns: JSON array of applications with appId, name, type, etc.

app-detail

Get detailed information about a specific application. Automatically injects conversationId into the response by default — no need to call get-context-id separately.

Usage:

CODEBLOCK12

Required Parameters:

• - --app-id APP_ID: Application ID

Optional Parameters:

• - --no-context: Skip auto-fetching conversationId from trajectory (faster, but response will not contain conversationId)

Example:

CODEBLOCK13

Returns: JSON object with application details, configuration, and status. data.conversationId is automatically populated.

get-context-id

Recover the conversationId for an existing app by reading its trajectory. Useful when the conversationId has been lost after a session reset.

Usage:

CODEBLOCK14

Required Parameters:

• - --app-id APP_ID: Application ID

Optional Parameters:

• - --fetch-timeout SECONDS: Request timeout in seconds (default: 10)

Example:

CODEBLOCK15

Returns: INLINECODE41

Use Cases:

• - Need to modify a previously created app in a new session but conversationId is lost
• Use the returned conversationId with chat --app-id --context-id to resume modification

conversation-history

Show a human/agent-readable summary of past interactions for an app. More convenient than trajectory or fetch-trajectory for quickly understanding what happened in previous sessions.

Usage:

CODEBLOCK16

Required Parameters:

• - --app-id APP_ID: Application ID

Optional Parameters:

• - --full: Show full content instead of truncated summaries (default: truncate at 200 chars)
• INLINECODE49: Only show the last N conversation turns
• INLINECODE50: Request timeout in seconds (default: 10)

Example:

CODEBLOCK17

Returns: JSON Lines, one entry per meaningful turn:

CODEBLOCK18

Use Cases:

• - Quickly understand what happened in previous sessions before resuming work
• Determine which phase the app is in (PRD refinement / generated / modified)
• Check for unfinished modifications or cancelled tasks

chat

Start or continue a conversation to create or modify an application.

Usage:

CODEBLOCK19

Required Parameters:

• - --text TEXT: The message/instruction to send

Optional Parameters:

• - --context-id CONTEXT_ID: Conversation ID of an existing app.
• INLINECODE53: Application ID of an existing app.
• INLINECODE54: Query mode (default: deep_mode)
• INLINECODE55: Input field type (default: web)
• INLINECODE56: Seconds between trajectory polls (default: 2.0)
• INLINECODE57: Per-request timeout for each trajectory fetch (default: 10)
• INLINECODE58: Return raw chat POST response without trajectory polling
• INLINECODE59: After polling, interactively ask whether to submit app generation if text was returned

⚠️ IMPORTANT — --app-id and --context-id must always be used together.

Intent	INLINECODE62	INLINECODE63
Create a brand-new app	omit	omit
Continue / modify an existing app

required | required (conversationId) |
Passing --app-id without --context-id will NOT modify the existing app.
The platform will silently create a new app every time. The CLI will now raise an error in this case to prevent accidental app proliferation.

Examples:

1. Create a new application:

CODEBLOCK20

Response includes appId and contextId for subsequent calls.

2. Continue conversation (refine PRD):

CODEBLOCK21

3. Modify existing generated app:

CODEBLOCK22

Important Notes:

• - Extract appId and contextId from the response and save them
• Use these IDs for all subsequent operations on the same app
• The first chat creates the app and starts PRD refinement
• After generation, chat directly modifies the app (no generate-app needed)

trajectory

Poll trajectory events until the task reaches a terminal state.

Usage:

CODEBLOCK23

Required Parameters:

• - --app-id APP_ID: Application ID

Optional Parameters:

• - --last-event-id EVENT_ID: Start eventId; -1 = all events from beginning (default: -1)
• INLINECODE75: Seconds between polls (default: 2.0)
• INLINECODE76: Per-request timeout in seconds (default: 10)
• INLINECODE77: Use legacy SSE streaming instead of polling

Example:

CODEBLOCK24

Use Cases:

• - Monitor conversation / generation progress
• Detect when PRD refinement is complete (look for Generate App button in result.artifact.parts[].data.actions[])
• Verify generation has completed

fetch-trajectory

Fetch one batch of trajectory events (single request, no polling loop).

Usage:

CODEBLOCK25

Required Parameters:

• - --app-id APP_ID: Application ID

Optional Parameters:

• - --last-event-id EVENT_ID: Fetch events after this eventId; -1 = all (default: -1)
• INLINECODE81: Request timeout in seconds (default: 10)

Example:

CODEBLOCK26

Events are printed to stdout as JSON lines; {"maxEventId": N, "isTerminal": bool} is printed to stderr.

Generate App readiness: Inspect result.artifact.parts[].data.actions[] for an action with "type":"button" and "event":{"name":"generateApp"}. Example:

CODEBLOCK27

When this button appears, PRD is ready and generate-app may be called.

generate-app

Submit app-generation confirmation and return immediately with appId/conversationId.

Usage:

CODEBLOCK28

Required Parameters:

• - --app-id APP_ID: Application ID

Optional Parameters:

• - --context-id CONTEXT_ID: Conversation ID (default: "")
• INLINECODE91: Query mode (default: deep_mode)
• INLINECODE92: Block and poll trajectory until generation completes (default: return immediately)
• INLINECODE93: Seconds between polls when --watch is set (default: 2.0)
• INLINECODE95: Per-request timeout in seconds when --watch is set (default: 10)

Example:

CODEBLOCK29

Important:

• - Only call this once during initial creation
• Call only when trajectory contains a Generate App button in result.artifact.parts[].data.actions[]: an action with "type":"button" and "event":{"name":"generateApp"} (label may vary by locale; use event name for the check). This indicates PRD is ready.
• Do not call again for modifications after the first generation
• After this command, use chat to modify the generated app

publish

Trigger deployment to production.

Usage:

CODEBLOCK30

Required Parameters:

• - --app-id APP_ID: Application ID to publish

Optional Parameters:

• - --env ENV: Target environment (default: PRODUCE)
• INLINECODE103: Auto-poll publish status until SUCCESS or FAILED

Examples:

1. Publish and manually check status:

CODEBLOCK31

Returns releaseId immediately. Then poll with publish-status.

2. Publish and auto-wait for completion (recommended):

CODEBLOCK32

This polls automatically and exits when deployment succeeds or fails.

Important:

• - Application must be generated at least once before publishing
• After successful publish, the app is live at: INLINECODE106

publish-status

Check the status of a deployment.

Usage:

CODEBLOCK33

Required Parameters:

• - --release-id RELEASE_ID: Release ID from publish command

Example:

CODEBLOCK34

Returns: JSON with status: PROCESSING, RUNNING, SUCCESS, or INLINECODE112

Usage Pattern:

CODEBLOCK35

Tip: Use publish --wait to avoid manual polling.

Complete Workflow Examples

Example 1: Create and Deploy a New App

CODEBLOCK36

Example 2: Modify an Existing App

IMPORTANT — Always update CONTEXT_ID from each chat response.
Each chat call prints a JSON header line {"appId": "...", "conversationId": "..."}.
The platform may return an updated conversationId in this response.
Always capture it and use it for the next chat call, or the next round will create a brand-new app.

CODEBLOCK37

Command Semantics

chat

Used to:

• * create a new application
• refine PRD specifications
• modify an existing generated application

For a new application, chat creates the project and begins the PRD stage.

For an existing application, chat performs iterative modifications.

trajectory

Streams conversation progress and system events.

Use this to determine:

• * whether PRD generation is ongoing
• whether the app is ready for generation (see generate-app condition below)
• whether generation has completed

generate-app

Triggers application generation.

Call only when trajectory contains a Generate App button in result.artifact.parts[].data.actions[]: an action with "type":"button" and "event":{"name":"generateApp"}. This indicates PRD is ready. Do not rely on text alone—the button structure is the authoritative signal.

Call once during initial creation. Do not call again for modifications.

publish

Triggers application deployment.

Use --wait flag to auto-poll status (recommended).

publish-status

Polls deployment progress until the release completes.

Not needed if using publish --wait.

Error Handling

IAM AccessKey Validation Failed

Symptom:

CODEBLOCK38

Cause:

The configured MEDO_API_KEY is invalid or missing.

Resolution:

1. 1. Go to the Medo official website:

https://www.medo.dev

1. 2. In the left navigation panel, apply for an available access key.

1. 3. Set the key as the environment variable:

CODEBLOCK39

1. 4. Or create a .env file in the skill directory:

CODEBLOCK40

NotOpenSSLWarning

Symptom:

CODEBLOCK41

Cause:

macOS uses LibreSSL by default, but urllib3 v2 recommends OpenSSL.

Impact:

This is a warning only. API calls still work correctly.

Resolution (optional):

If you want to suppress the warning:

CODEBLOCK42

Or ignore it - it doesn't affect functionality.

Error Handling Guidance

Agents should handle the following situations:

• * generation requested before the platform indicates readiness
• publish requested before generation has completed
• missing appId or conversationId (use get-context-id to recover a lost conversationId)
• interrupted trajectory stream
• failed deployment status
• incorrect or missing parameter values

If workflow state is unclear, inspect the trajectory or application detail before taking the next action.

Pro Tips:

• - Always check command --help when unsure about parameters
• Use --wait flag with publish to simplify deployment
• Save appId and contextId from first chat response
• Only call generate-app once during initial creation
• After generation, use chat directly for modifications

Application Sharing Rule (IMPORTANT)

• - You must share your application only using the production deployment URL (after it has been published). Do not share the editor (development) URL.

Production deployment URL format:

CODEBLOCK43

• - If the application has not been published, you must publish it before sharing with others.

Example publish command:

CODEBLOCK44

• - The project editor URL (https://www.medo.cn/projects/<app_id>) is visible only to yourself. Other users cannot access your editor environment. Never use the editor URL for sharing with others.

Editor URL is for:

• - your own development
• preview
• internal editing only

Editor URL must NOT be used for:

• - external/public sharing
• distribution to others or end users