manus
Manus API for AI agent task execution. Use when user mentions "Manus", "run an agent task", "AI agent", or needs to automate multi-step research, analysis, or content tasks via Manus.
What this skill does
## Troubleshooting
If requests fail, run `zero doctor check-connector --env-name MANUS_TOKEN` or `zero doctor check-connector --url https://api.manus.ai/v2/task.detail?task_id= --method GET`
## Tasks
### Create a Task
Write to `/tmp/manus_task.json`:
```json
{
"message": {
"content": [
{
"type": "text",
"text": "<your task prompt>"
}
]
}
}
```
Then run:
```bash
curl -s -X POST "https://api.manus.ai/v2/task.create" --header "x-manus-api-key: $MANUS_TOKEN" --header "Content-Type: application/json" -d @/tmp/manus_task.json
```
Response includes `task_id` and `task_url` to track the task.
### Create a Task with Options
Write to `/tmp/manus_task.json`:
```json
{
"message": {
"content": [
{
"type": "text",
"text": "<your task prompt>"
}
]
},
"title": "<custom task title>",
"locale": "en",
"agent_profile": "manus-1.6",
"share_visibility": "private",
"interactive_mode": false
}
```
Then run:
```bash
curl -s -X POST "https://api.manus.ai/v2/task.create" --header "x-manus-api-key: $MANUS_TOKEN" --header "Content-Type: application/json" -d @/tmp/manus_task.json
```
**`agent_profile` options:**
- `manus-1.6` — default, balanced performance
- `manus-1.6-lite` — faster, lower cost
- `manus-1.6-max` — highest quality, more thorough
### Create a Task with File Attachments
First upload the file (see Files section), then include the `file_id` in the task:
Write to `/tmp/manus_task.json`:
```json
{
"message": {
"content": [
{
"type": "text",
"text": "<your task prompt>"
},
{
"type": "file",
"file_id": "<your-file-id>"
}
]
}
}
```
Then run:
```bash
curl -s -X POST "https://api.manus.ai/v2/task.create" --header "x-manus-api-key: $MANUS_TOKEN" --header "Content-Type: application/json" -d @/tmp/manus_task.json
```
### Create a Task in a Project
Write to `/tmp/manus_task.json`:
```json
{
"project_id": "<your-project-id>",
"message": {
"content": [
{
"type": "text",
"text": "<your task prompt>"
}
]
}
}
```
Then run:
```bash
curl -s -X POST "https://api.manus.ai/v2/task.create" --header "x-manus-api-key: $MANUS_TOKEN" --header "Content-Type: application/json" -d @/tmp/manus_task.json
```
### Create a Task with Connectors
Pass connector UUIDs from your Manus integrations page to give the agent access to external tools (Gmail, Notion, Google Calendar, etc.):
Write to `/tmp/manus_task.json`:
```json
{
"message": {
"content": [
{
"type": "text",
"text": "<your task prompt>"
}
],
"connectors": ["<connector-uuid-1>", "<connector-uuid-2>"]
}
}
```
Then run:
```bash
curl -s -X POST "https://api.manus.ai/v2/task.create" --header "x-manus-api-key: $MANUS_TOKEN" --header "Content-Type: application/json" -d @/tmp/manus_task.json
```
### Get Task Detail
Replace `<task-id>` with the `task_id` from the create response:
```bash
curl -s "https://api.manus.ai/v2/task.detail?task_id=<task-id>" --header "x-manus-api-key: $MANUS_TOKEN"
```
Response includes `status`, `credit_usage`, and `task_url`. Poll this endpoint to track task completion.
**Task status values:** `pending`, `running`, `completed`, `failed`, `cancelled`
## Projects
### Create a Project
Write to `/tmp/manus_project.json`:
```json
{
"name": "<project name>",
"instruction": "<default instruction applied to all tasks in this project>"
}
```
Then run:
```bash
curl -s -X POST "https://api.manus.ai/v2/project.create" --header "x-manus-api-key: $MANUS_TOKEN" --header "Content-Type: application/json" -d @/tmp/manus_project.json
```
Response includes `project.id` — use this as `project_id` when creating tasks.
### List Projects
```bash
curl -s "https://api.manus.ai/v2/project.list" --header "x-manus-api-key: $MANUS_TOKEN"
```
## Files
Files are uploaded in two steps: first request a presigned upload URL, then PUT the file content to that URL. Files expire 48 hours after upload.
### Step 1 — Request Upload URL
Write to `/tmp/manus_file_upload.json`:
```json
{
"filename": "<your-filename.pdf>"
}
```
Then run:
```bash
curl -s -X POST "https://api.manus.ai/v2/file.upload" --header "x-manus-api-key: $MANUS_TOKEN" --header "Content-Type: application/json" -d @/tmp/manus_file_upload.json
```
The response contains `file.id` and `upload_url` (valid for 3 minutes).
### Step 2 — Upload File Content
Replace `<presigned-upload-url>` with the `upload_url` from Step 1:
```bash
curl -s -X PUT "<presigned-upload-url>" --header "Content-Type: application/octet-stream" --data-binary @/path/to/your/file.pdf
```
### Get File Detail
Check the file status before attaching it to a task. Only files with `status: uploaded` can be used:
```bash
curl -s "https://api.manus.ai/v2/file.detail?file_id=<file-id>" --header "x-manus-api-key: $MANUS_TOKEN"
```
## Webhooks
Webhooks deliver async task status updates to your HTTPS endpoint. Manus sends a POST request with the task result when the task completes or changes state.
### Create a Webhook
The endpoint URL must be publicly accessible and return a 2xx response:
Write to `/tmp/manus_webhook.json`:
```json
{
"url": "https://your-endpoint.example.com/webhook"
}
```
Then run:
```bash
curl -s -X POST "https://api.manus.ai/v2/webhook.create" --header "x-manus-api-key: $MANUS_TOKEN" --header "Content-Type: application/json" -d @/tmp/manus_webhook.json
```
Response includes `webhook.id` — save this to delete the webhook later.
### Delete a Webhook
Write to `/tmp/manus_webhook_delete.json`:
```json
{
"webhook_id": "<your-webhook-id>"
}
```
Then run:
```bash
curl -s -X POST "https://api.manus.ai/v2/webhook.delete" --header "x-manus-api-key: $MANUS_TOKEN" --header "Content-Type: application/json" -d @/tmp/manus_webhook_delete.json
```
## API Parameters Reference
### task.create Body
| Parameter | Type | Required | Description |
|---|---|---|---|
| `message` | object | Yes | Task prompt and configuration |
| `message.content` | array | Yes | Array of content parts (text, file, voice) |
| `message.connectors` | string[] | No | Connector UUIDs to enable |
| `message.enable_skills` | string[] | No | Skill IDs available to the agent |
| `message.force_skills` | string[] | No | Skill IDs the agent must invoke |
| `project_id` | string | No | Associates task with a project |
| `title` | string | No | Custom task title |
| `locale` | string | No | Output language (e.g. `en`, `zh-CN`) |
| `agent_profile` | enum | No | `manus-1.6`, `manus-1.6-lite`, `manus-1.6-max` |
| `interactive_mode` | boolean | No | Allow agent to ask follow-up questions |
| `share_visibility` | enum | No | `private`, `team`, or `public` |
| `hide_in_task_list` | boolean | No | Hide from webapp task list |
## Guidelines
1. **Polling**: Tasks are asynchronous. Poll `task.detail` until `status` is `completed` or `failed`. For production use, prefer webhooks.
2. **File expiry**: Uploaded files expire after 48 hours — upload just before task creation.
3. **Presigned URL expiry**: The `upload_url` from `file.upload` expires in 3 minutes — PUT the file immediately after receiving it.
4. **Rate limits**: 10 requests per second per API key.
5. **Credits**: Tasks consume credits based on complexity. Use `manus-1.6-lite` to reduce cost for simple tasks.
6. **Projects**: Use projects to apply shared instructions to groups of related tasks.
## API Reference
- API Reference: https://open.manus.im/docs/api-reference
- Manus Dashboard: https://manus.im
- Integration Settings: https://manus.im/settings/integrationRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.