What makes Unitask Agent notable?

550 downloads. Trust evidence available

How should Unitask Agent be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Unitask Agent

Start finishing tasks instead of just organizing them: connect your OpenClaw agent to Unitask (unitask.app) to manage and do your tasks with secure prioritiz...

OpenClaw

View on ClawHub

Rank

Safety

Downloads

550

Updated

Apr 15, 2026

Version

0.18.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 550 downloads reported by the source. Last updated 4/15/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Apr 15, 2026
Protocol compatibility: OpenClawcompatibility · observed Apr 15, 2026
Adoption signal: 550 downloadsadoption · observed Apr 15, 2026
Latest release: 0.18.0release · observed Feb 23, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install kn7fq6yxd4a5q0r3dnfkz1bqy18041ew:unitask-agent

Install using `clawhub skill install kn7fq6yxd4a5q0r3dnfkz1bqy18041ew:unitask-agent` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/mfaiz-007/unitask-agent before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-mfaiz-007-unitask-agent/snapshot"

Documentation

CLAWHUB

22,890 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: "unitask-agent"
description: "Start finishing tasks instead of just organizing them: connect your OpenClaw agent to Unitask (unitask.app) to manage and do your tasks with secure prioritization, tags, time blocks and more."
homepage: https://unitask.app
read_when:
  - User wants to manage Unitask tasks from an AI agent
  - User wants to time-block today using Unitask scheduled_start + duration_minutes
metadata: {"clawdbot":{"emoji":"✅","requires":{"env":["UNITASK_API_KEY"]},"primaryEnv":"UNITASK_API_KEY"}}
---

# Unitask Agent

## Purpose

This skill lets an AI agent safely manage a user's Unitask account using **scoped API tokens**.
Unitask is in **public beta**. Anyone can sign up at `https://unitask.app`.

Supported operations:
- List tasks
- Get one task
- Create task
- Update task fields (`update_task`)
- Update status (`update_task_status`)
- Move subtask to a different parent (`move_subtask`)
- Merge parent tasks (`merge_parent_tasks`)
- List/create/update/delete tags
- Add/remove tags on tasks
- Delete task (soft delete)
- Read/update settings (optional one-time setup)
- Plan day time blocks (preview/apply)

Subtasks:
- Subtasks are tasks with a `parent_id`.
- Create a subtask via `create_task` with `parent_id=<parent id>`.

## Required setup

1. User signs up (public beta) at `https://unitask.app` if they do not already have an account.
2. User creates a Unitask API token from `Unitask -> Dashboard -> Settings -> API`.
3. User stores it in their agent/app secret store as: `UNITASK_API_KEY=<token>`.

Never ask users to paste full tokens in chat logs.

## Scope model

- `read`: required for read/list actions.
- `write`: required for create/update/move/merge actions.
- `delete`: required for delete actions.
- If `write` or `delete` is granted, `read` must also be granted.

## Hosted MCP (unitask.app, HTTPS)

Endpoint:
- `https://unitask.app/api/mcp`

Auth header (recommended):
- `Authorization: Bearer <UNITASK_API_KEY>`

## MCP tools

- `list_tasks` — filter by `status` (`todo|done`), `limit`, `offset`, `parent_id`, `tag_id`
  - advanced filters: `view` (`today|upcoming`), `tz`, `window_days`, `due_from`, `due_to`, `start_from`, `start_to`, `sort_by`, `sort_dir`
- `get_task` — fetch one task
- `create_task` — create task/subtask
- `update_task` — full mutable field update
- `update_task_status` — status-only helper
- `move_subtask` — move a subtask between parents (`dry_run` default true)
- `merge_parent_tasks` — merge parent trees (`dry_run` default true)
- `delete_task` — soft-delete task + descendants
- `list_tags` — list available tags
- `get_tag` — fetch one tag
- `create_tag` — create a tag
- `update_tag` — edit tag name/color/deleted
- `delete_tag` — soft-delete tag
- `add_task_tag` — attach tag to task
- `remove_task_tag` — detach tag from task
- `get_settings` — get user settings
- `update_settings` — update settings/quiz
- `plan_day_timeblocks` — preview/apply schedule

## Safety rules

- Use smallest required scope for t

README.md

# Unitask Agent

Start finishing tasks instead of just organizing them: connect any AI agent to Unitask (unitask.app) to manage and do your tasks with secure prioritization, tags, time blocks and more.

Unitask is now in **public beta**. Anyone can sign up at `https://unitask.app` and create a scoped API token.

## What it does

- Read tasks
- Create/update tasks (including subtasks via `parent_id`)
- Move subtasks between parent tasks
- Merge parent tasks (with preview first)
- Create/edit/delete tags
- Add/remove tags on tasks
- Soft-delete tasks
- Time-block your day (writes `scheduled_start` + `duration_minutes`)

## Setup

1. Sign up at `https://unitask.app` (public beta) if you do not already have an account.
2. In Unitask: `Dashboard -> Settings -> API` create an API token with scopes you need.
3. In your AI app / MCP client config, store token as `UNITASK_API_KEY` (never paste tokens in chat).

## Hosted MCP endpoint

- URL: `https://unitask.app/api/mcp`
- Header: `Authorization: Bearer <UNITASK_API_KEY>`

## Client configuration examples

### Claude Code (remote HTTP MCP)

Create/edit `~/.claude.json`:

```json
{
  "mcpServers": {
    "unitask": {
      "type": "http",
      "url": "https://unitask.app/api/mcp",
      "headers": {
        "Authorization": "Bearer ${UNITASK_API_KEY}"
      }
    }
  }
}
```

### VS Code (remote HTTP MCP)

Create `.vscode/mcp.json` in your workspace:

```json
{
  "inputs": [
    {
      "id": "unitask_api_key",
      "type": "promptString",
      "description": "Unitask API key",
      "password": true
    }
  ],
  "servers": {
    "unitask": {
      "type": "http",
      "url": "https://unitask.app/api/mcp",
      "headers": {
        "Authorization": "Bearer ${input:unitask_api_key}"
      }
    }
  }
}
```

## Safety

- Use the smallest scope needed.
- Scope guidance: `read` for retrieval, `write` for create/update, `delete` only when required.
- Keep `dry_run=true` first for compound actions (move/merge/timeblock apply).
- Confirm deletes unless user explicitly requested deletion.

_meta.json

{
  "ownerId": "kn7fq6yxd4a5q0r3dnfkz1bqy18041ew",
  "slug": "unitask-agent",
  "version": "0.18.0",
  "publishedAt": 1771837747053
}

ONBOARDING.md

# Unitask Agent Onboarding (Agent-Driven)

Use this question flow when helping a user set up `unitask-agent`.

## Goal
Get the user from zero to a working Unitask MCP connection safely, with the right scopes.

## Step 1: Confirm account status
Ask:
1. "Do you already have a Unitask account?"

If **No**:
- Direct user to sign up at `https://unitask.app/signup`.
- After signup, ask them to open `Dashboard -> Settings -> API`.

If **Yes**:
- Continue to token setup.

## Step 2: Choose intended capabilities
Ask which actions they want the agent to perform:
1. Read-only planning (`read`)
2. Create/update/move/merge (`read + write`)
3. Deletion operations (`read + write + delete`)

Recommend least privilege by default.

## Step 3: Create API token
Guide user:
1. Open `Unitask -> Dashboard -> Settings -> API`.
2. Create token with selected scopes.
3. Copy token once (never paste token in chat).

## Step 4: Store token securely
Ask where they run the agent:
1. OpenClaw
2. Claude Code
3. VS Code MCP
4. Other MCP client

Then guide to configure:
- Env var key: `UNITASK_API_KEY`
- Header: `Authorization: Bearer <UNITASK_API_KEY>`
- Endpoint: `https://unitask.app/api/mcp`

## Step 5: Connectivity verification
Run these checks in order:
1. `list_tasks` with `limit=5`
2. `list_tags`
3. Optional write test: `create_task` with a temporary title

If any step fails:
- Verify token format and scope.
- Verify header value is injected.
- Verify endpoint URL is exact.

## Step 6: First-value commands (guided)
Offer starter prompts:
- "What are my tasks for today?"
- "Create a task: ship MCP tag support"
- "Tag this task as urgent"
- "Move this subtask under parent X"

## Safety reminders
- Never ask users to paste full API tokens into chat.
- Use dry-run first for compound actions (`move_subtask`, `merge_parent_tasks`).
- Confirm destructive actions before apply.

USE_CASES.md

# Unitask Agent Use Cases (Public Beta)

Unitask is in **public beta**. Anyone can sign up at `https://unitask.app`, create a scoped token in `Dashboard -> Settings -> API`, and connect an AI agent.

## Day-to-Day Matrix (20)

| # | Use Case | Recommended Query/Tool | Support | Gap / Next Patch |
|---|---|---|---|---|
| 1 | What are my tasks for today including overdue? | `list_tasks(view=today,tz=<IANA>,status=todo,limit=100)` | Yes | None |
| 2 | What is coming up this week? | `list_tasks(view=upcoming,tz=<IANA>,window_days=7,status=todo)` | Yes | None |
| 3 | Tasks due in next 3 days | `list_tasks(due_from=<ISO>,due_to=<ISO>,status=todo)` | Yes | None |
| 4 | Tasks starting tomorrow | `list_tasks(start_from=<ISO>,start_to=<ISO>,status=todo)` | Yes | None |
| 5 | Today tasks sorted by priority | `list_tasks(view=today,sort_by=priority,sort_dir=desc)` | Yes | None |
| 6 | Parent tasks only | `list_tasks(parent_id=null,status=todo)` | Yes | None |
| 7 | Subtasks under a parent | `list_tasks(parent_id=<parent_id>,status=todo)` | Yes | None |
| 8 | Filter tasks by tag | `list_tasks(tag_id=<tag_id>,status=todo)` | Yes | None |
| 9 | Create a task | `create_task` | Yes | None |
| 10 | Create a subtask | `create_task(parent_id=<parent_id>)` | Yes | None |
| 11 | Update any task fields | `update_task` | Yes | None |
| 12 | Mark task done / reopen | `update_task_status` | Yes | None |
| 13 | Move subtask to another parent | `move_subtask(dry_run=true|false)` | Yes | None |
| 14 | Merge parent B into A | `merge_parent_tasks(dry_run=true|false)` | Yes | None |
| 15 | Create / rename / delete tags | `create_tag`, `update_tag`, `delete_tag` | Yes | None |
| 16 | Attach / remove tag on task | `add_task_tag`, `remove_task_tag` | Yes | None |
| 17 | Plan my day 9-5 with preview | `plan_day_timeblocks(apply=false)` | Yes | None |
| 18 | Apply approved timeblock plan | `plan_day_timeblocks(apply=true)` | Yes | None |
| 19 | Update onboarding/settings profile | `update_settings` | Yes | None |
| 20 | Mark many tasks done from one prompt | repeated `update_task_status` calls | Partial | Add `batch_update_task_status` tool |

## Quick Prompts

1. "What are my tasks for today including overdue?"
2. "Show what is upcoming in the next 7 days."
3. "List tasks tagged urgent and sort by priority."
4. "Move subtask <id> under parent <id>, preview first."
5. "Merge parent B into parent A, preview then apply."

## Safety Defaults

- Use least-privilege scopes (`read`, `write`, `delete`) for each workflow.
- Use dry-run first for `move_subtask` and `merge_parent_tasks`.
- Confirm destructive actions (`delete_task`, `delete_tag`) before apply.

Github ReposUpdated 5h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.