Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create, modify, generate, and deploy websites, web apps, dashboards, SaaS products, internal tools, interactive web pages, Weixin mini program , games on the Baidu Miaoda (秒哒) platform using natural-language instructions.
.claude/skills/leoyeai-miaoda-app-builder/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 243% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 305% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 343% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 276% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 466% | 0% |
Miaoda (秒哒) is a chat-driven full-stack application builder. Official website: https://www.miaoda.cn
Users describe what they want in natural language and Miaoda generates a production-ready web product, including:
Typical outputs include:
This skill enables AI agents to interact with the Miaoda(秒哒) platform to create, iterate, generate, and deploy applications.
All platform operations must be executed through the packaged CLI script:
bashpython scripts/miaoda_api.py <command> [options]
Do not call platform APIs directly. Always use the CLI commands provided by this skill.
Use this skill whenever the user wants to:
Do not use this skill for unrelated programming tasks.
Trigger this skill if the request includes concepts such as:
Examples that should route to this skill:
The CLI script is stateless.
It does not store workflow state between calls.
Application workflow state is maintained by the Miaoda platform and must be inferred from:
appIdconversationIdAgents must pass the appropriate identifiers when continuing conversations or modifying applications.
Miaoda applications follow a strict lifecycle.
Agents must follow these rules.
For a new application:
chat request describing the product.generate-app.Generation is required only once during the initial creation.
After an application has already been generated:
generate-app again.chat with the same appId and conversationId.Normal chat messages modify the existing application.
Publishing is allowed after the application has been generated at least once.
Rules:
--wait flag)Typical deployment flow:
publish → publish-status pollingOr use the --wait flag to auto-poll:
publish --waitStop polling when the status becomes:
SUCCESSFAILEDMiaoda provides two types of URLs during the lifecycle.
After the application is created, the project can be accessed at:
https://www.miaoda.cn/projects/<app_id>This URL can be shared with the user for:
The preview URL becomes available once an appId is created.
After publishing succeeds, the application is accessible at:
https://<app_id>.appmiaoda.comThis is the public production URL of the deployed application.
Only return this URL after publishing completes successfully.
chat → PRD refinement → generate-app → publishchat → chat → chat(no additional generation step required)
publish → publish-status pollingOr:
publish --waitAll commands are executed via the CLI script.
Important: Always set the MIAODA_API_KEY environment variable before running commands.
bashexport MIAODA_API_KEY="your_api_key_here"
List all applications belonging to the authenticated user.
Usage:
bashpython scripts/miaoda_api.py list-apps
Example:
bashexport MIAODA_API_KEY="sk_xxxxx" python scripts/miaoda_api.py list-apps
Returns: JSON array of applications with appId, name, type, etc.
Get detailed information about a specific application.
Usage:
bashpython scripts/miaoda_api.py app-detail --app-id <app_id>
Required Parameters:
--app-id APP_ID: Application IDExample:
bashexport MIAODA_API_KEY="sk_xxxxx" python scripts/miaoda_api.py app-detail --app-id app-abc123xyz
Returns: JSON object with application details, configuration, and status.
Start or continue a conversation to create or modify an application.
Usage:
bashpython scripts/miaoda_api.py chat --text "description" [options]
Required Parameters:
--text TEXT: The message/instruction to sendOptional Parameters:
--context-id CONTEXT_ID: Conversation ID of an existing app.--app-id APP_ID: Application ID of an existing app.--query-mode QUERY_MODE: Query mode (default: deep_mode)--input-field-type INPUT_FIELD_TYPE: Input field type (default: web)--poll-interval SECONDS: Seconds between trajectory polls (default: 2.0)--fetch-timeout SECONDS: Per-request timeout for each trajectory fetch (default: 10)--no-stream: Return raw chat POST response without trajectory polling--prompt-generate: 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 | --app-id | --context-id | > |--------|-----------|----------------| > | 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:
bashexport MIAODA_API_KEY="sk_xxxxx" python scripts/miaoda_api.py chat --text "创建一个待办事项管理应用"
Response includes appId and contextId for subsequent calls.
2. Continue conversation (refine PRD):
bashpython scripts/miaoda_api.py chat \ --text "添加优先级标记功能" \ --app-id app-abc123xyz \ --context-id conv-def456uvw
3. Modify existing generated app:
bashpython scripts/miaoda_api.py chat \ --text "把按钮颜色改成蓝色" \ --app-id app-abc123xyz \ --context-id conv-def456uvw
Important Notes:
appId and contextId from the response and save themchat creates the app and starts PRD refinementchat directly modifies the app (no generate-app needed)Poll trajectory events until the task reaches a terminal state.
Usage:
bashpython scripts/miaoda_api.py trajectory --app-id <app_id> [options]
Required Parameters:
--app-id APP_ID: Application IDOptional Parameters:
--last-event-id EVENT_ID: Start eventId; -1 = all events from beginning (default: -1)--poll-interval SECONDS: Seconds between polls (default: 2.0)--fetch-timeout SECONDS: Per-request timeout in seconds (default: 10)--sse: Use legacy SSE streaming instead of pollingExample:
bashexport MIAODA_API_KEY="sk_xxxxx" python scripts/miaoda_api.py trajectory --app-id app-abc123xyz
Use Cases:
Fetch one batch of trajectory events (single request, no polling loop).
Usage:
bashpython scripts/miaoda_api.py fetch-trajectory --app-id <app_id> [options]
Required Parameters:
--app-id APP_ID: Application IDOptional Parameters:
--last-event-id EVENT_ID: Fetch events after this eventId; -1 = all (default: -1)--fetch-timeout SECONDS: Request timeout in seconds (default: 10)Example:
bash# First call — get all events (note maxEventId from stderr) python scripts/miaoda_api.py fetch-trajectory --app-id app-abc123xyz # Subsequent calls — incremental fetch python scripts/miaoda_api.py fetch-trajectory --app-id app-abc123xyz --last-event-id 345
Events are printed to stdout as JSON lines; {"maxEventId": N, "isTerminal": bool} is printed to stderr.
Submit app-generation confirmation and return immediately with appId/conversationId.
Usage:
bashpython scripts/miaoda_api.py generate-app --app-id <app_id> --context-id <context_id> [options]
Required Parameters:
--app-id APP_ID: Application IDOptional Parameters:
--context-id CONTEXT_ID: Conversation ID (default: "")--query-mode QUERY_MODE: Query mode (default: deep_mode)--watch: Block and poll trajectory until generation completes (default: return immediately)--poll-interval SECONDS: Seconds between polls when --watch is set (default: 2.0)--fetch-timeout SECONDS: Per-request timeout in seconds when --watch is set (default: 10)Example:
bashexport MIAODA_API_KEY="sk_xxxxx" # Submit and return immediately — check status later with fetch-trajectory python scripts/miaoda_api.py generate-app \ --app-id app-abc123xyz \ --context-id conv-def456uvw # Submit and block until generation finishes python scripts/miaoda_api.py generate-app \ --app-id app-abc123xyz \ --context-id conv-def456uvw \ --watch
Important:
chat to modify the generated appTrigger deployment to production.
Usage:
bashpython scripts/miaoda_api.py publish --app-id <app_id> [options]
Required Parameters:
--app-id APP_ID: Application ID to publishOptional Parameters:
--env ENV: Target environment (default: PRODUCE)--wait: Auto-poll publish status until SUCCESS or FAILEDExamples:
1. Publish and manually check status:
bashexport MIAODA_API_KEY="sk_xxxxx" python scripts/miaoda_api.py publish --app-id app-abc123xyz
Returns releaseId immediately. Then poll with publish-status.
2. Publish and auto-wait for completion (recommended):
bashexport MIAODA_API_KEY="sk_xxxxx" python scripts/miaoda_api.py publish --app-id app-abc123xyz --wait
This polls automatically and exits when deployment succeeds or fails.
Important:
https://<app_id>.appmiaoda.comCheck the status of a deployment.
Usage:
bashpython scripts/miaoda_api.py publish-status --release-id <release_id>
Required Parameters:
--release-id RELEASE_ID: Release ID from publish commandExample:
bashexport MIAODA_API_KEY="sk_xxxxx" python scripts/miaoda_api.py publish-status --release-id app_release_record-xyz789abc
Returns: JSON with status: PROCESSING, RUNNING, SUCCESS, or FAILED
Usage Pattern:
bash# Get release ID from publish RELEASE_ID=$(python scripts/miaoda_api.py publish --app-id app-abc123xyz | jq -r '.releaseId') # Poll status while true; do STATUS=$(python scripts/miaoda_api.py publish-status --release-id $RELEASE_ID | jq -r '.status') echo "Status: $STATUS" if [[ "$STATUS" == "SUCCESS" || "$STATUS" == "FAILED" ]]; then break fi sleep 5 done
Tip: Use publish --wait to avoid manual polling.
bashexport MIAODA_API_KEY="sk_xxxxx" cd ~/.openclaw/skills/miaoda-app-builder # Step 1: Create app via chat (returns appId + conversationId on first line) FIRST=$(python scripts/miaoda_api.py chat --text "创建一个简单的计数器应用" | head -1) APP_ID=$(echo $FIRST | jq -r '.appId') CONTEXT_ID=$(echo $FIRST | jq -r '.conversationId') # Step 2: Generate the app (returns immediately; use fetch-trajectory to check progress) python scripts/miaoda_api.py generate-app \ --app-id $APP_ID \ --context-id $CONTEXT_ID # Step 3: Poll until generation finishes python scripts/miaoda_api.py trajectory --app-id $APP_ID # Step 4: Publish (with auto-wait) python scripts/miaoda_api.py publish --app-id $APP_ID --wait # Done! App is live at: echo "https://$APP_ID.appmiaoda.com"
bashexport MIAODA_API_KEY="sk_xxxxx" cd ~/.openclaw/skills/miaoda-app-builder APP_ID="app-abc123xyz" CONTEXT_ID="conv-def456uvw" # Modify the app (no generate-app needed) python scripts/miaoda_api.py chat \ --text "把背景颜色改成深色模式" \ --app-id $APP_ID \ --context-id $CONTEXT_ID # Re-publish python scripts/miaoda_api.py publish --app-id $APP_ID --wait
Used to:
For a new application, chat creates the project and begins the PRD stage.
For an existing application, chat performs iterative modifications.
Streams conversation progress and system events.
Use this to determine:
Triggers application generation.
Use only when the platform indicates the app is ready to generate.
Call once during initial creation. Do not call again for modifications.
Triggers application deployment.
Use --wait flag to auto-poll status (recommended).
Polls deployment progress until the release completes.
Not needed if using publish --wait.
Symptom:
IAM access key validation failed.Cause:
The configured MIAODA_API_KEY is invalid or missing.
Resolution:
https://www.miaoda.cn
bash export MIAODA_API_KEY="sk_xxxxx"
.env file in the skill directory:bash echo "MIAODA_API_KEY=sk_xxxxx" > ~/.openclaw/skills/miaoda-app-builder/.env
Symptom:
NotOpenSSLWarning: urllib3 v2 only supports OpenSSL 1.1.1+,
currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'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:
bashpip3 install 'urllib3<2'
Or ignore it - it doesn't affect functionality.
Agents should handle the following situations:
appId or conversationIdIf workflow state is unclear, inspect the trajectory or application detail before taking the next action.
Pro Tips:
--help when unsure about parameters--wait flag with publish to simplify deploymentappId and contextId from first chat responsegenerate-app once during initial creationchat directly for modificationsApplication Sharing Rule (IMPORTANT)
Production deployment URL format:
https://<app_id>.appmiaoda.comExample publish command:
python scripts/miaoda_api.py publish --app-id <app_id> --waithttps://www.miaoda.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:
Editor URL must NOT be used for:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 26,079 | 6,704 | -74% | 1 | 1 | 0% | 6,195 | 5,060 | -18% | 0 | 0 | — |
case-02 | fail→fail | 12,346 | 7,071 | -43% | 1 | 1 | 0% | 2,576 | 5,194 | +102% | 0 | 0 | — |
case-03 | fail→fail | 5,158 | 8,333 | +62% | 1 | 1 | 0% | 874 | 5,141 | +488% | 0 | 0 | — |
case-04 | fail→pass | 9,837 | 5,386 | -45% | 1 | 1 | 0% | 1,691 | 5,796 | +243% | 0 | 0 | — |
case-05 | fail→pass | 8,172 | 4,062 | -50% | 1 | 1 | 0% | 1,355 | 5,482 | +305% | 0 | 0 | — |
case-06 | fail→pass | 8,386 | 3,786 | -55% | 1 | 1 | 0% | 1,236 | 5,481 | +343% | 0 | 0 | — |
case-07 | pass→pass | 6,807 | 2,481 | -64% | 1 | 1 | 0% | 1,150 | 5,240 | +356% | 0 | 0 | — |
case-08 | fail→pass | 8,321 | 3,033 | -64% | 1 | 1 | 0% | 1,425 | 5,359 | +276% | 0 | 0 | — |
case-09 | fail→pass | 6,049 | 1,894 | -69% | 1 | 1 | 0% | 894 | 5,064 | +466% | 0 | 0 | — |
case-10 | fail→pass | 8,164 | 2,601 | -68% | 1 | 1 | 0% | 1,440 | 5,247 | +264% | 0 | 0 | — |
case-11 | fail→pass | 15,529 | 3,651 | -76% | 1 | 1 | 0% | 2,032 | 5,488 | +170% | 0 | 0 | — |
case-12 | pass→pass | 9,170 | 3,842 | -58% | 1 | 1 | 0% | 1,605 | 5,326 | +232% | 0 | 0 | — |
case-13 | fail→pass | 6,623 | 2,480 | -63% | 1 | 1 | 0% | 969 | 5,293 | +446% | 0 | 0 | — |
case-14 | fail→pass | 10,019 | 2,361 | -76% | 1 | 1 | 0% | 1,696 | 5,272 | +211% | 0 | 0 | — |
case-15 | fail→pass | 10,787 | 2,409 | -78% | 1 | 1 | 0% | 2,102 | 5,291 | +152% | 0 | 0 | — |
case-16 | fail→pass | 15,162 | 3,576 | -76% | 1 | 1 | 0% | 2,551 | 5,505 | +116% | 0 | 0 | — |
case-17 | fail→pass | 7,474 | 3,202 | -57% | 1 | 1 | 0% | 1,237 | 5,254 | +325% | 0 | 0 | — |
case-18 | fail→pass | 14,977 | 1,441 | -90% | 1 | 1 | 0% | 2,580 | 5,036 | +95% | 0 | 0 | — |
case-19 | pass→pass | 9,833 | 7,623 | -22% | 1 | 1 | 0% | 2,113 | 6,406 | +203% | 0 | 0 | — |
case-20 | pass→pass | 15,539 | 9,674 | -38% | 1 | 1 | 0% | 3,089 | 6,620 | +114% | 0 | 0 | — |
case-21 | pass→pass | 5,361 | 5,755 | +7% | 1 | 1 | 0% | 1,067 | 5,942 | +457% | 0 | 0 | — |
case-22 | pass→pass | 3,292 | 2,571 | -22% | 1 | 1 | 0% | 511 | 5,207 | +919% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 19 counted toward the lift figure. The other 3 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +59 percentage points is the difference between those two pass rates over the 19 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.