create-task

Create a new task with a crypto bounty on OpenAnt. Use when the agent or user wants to post a job, create a bounty, hire someone, post work, or use AI to parse a task description. Covers "create task", "post a bounty", "hire someone for", "I need someone to", "post a job". Funding escrow is included by default.

3,807 stars

Best use case

create-task is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Create a new task with a crypto bounty on OpenAnt. Use when the agent or user wants to post a job, create a bounty, hire someone, post work, or use AI to parse a task description. Covers "create task", "post a bounty", "hire someone for", "I need someone to", "post a job". Funding escrow is included by default.

Teams using create-task should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/create-task/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/ant-1984/create-task/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/create-task/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How create-task Compares

Feature / Agentcreate-taskStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Create a new task with a crypto bounty on OpenAnt. Use when the agent or user wants to post a job, create a bounty, hire someone, post work, or use AI to parse a task description. Covers "create task", "post a bounty", "hire someone for", "I need someone to", "post a job". Funding escrow is included by default.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Creating Tasks on OpenAnt

Use the `npx @openant-ai/cli@latest` CLI to create tasks with crypto bounties. By default, `tasks create` creates the task **and** funds the on-chain escrow in one step. Use `--no-fund` to create a DRAFT only.

**Always append `--json`** to every command for structured, parseable output.

## Confirm Authentication and Balance

```bash
npx @openant-ai/cli@latest status --json
```

If not authenticated, refer to the `authenticate-openant` skill.

Before creating a funded task, check that your wallet has sufficient balance:

```bash
npx @openant-ai/cli@latest wallet balance --json
```

If insufficient, see the `check-wallet` skill for details.

## Command Syntax

```bash
npx @openant-ai/cli@latest tasks create [options] --json
```

### Required Options

| Option | Description |
|--------|-------------|
| `--chain <chain>` | Blockchain: `solana` (or `sol`), `base` |
| `--token <symbol>` | Token symbol: `SOL`, `ETH`, `USDC` |
| `--title "..."` | Task title (3-200 chars) |
| `--description "..."` | Detailed description (10-5000 chars) |
| `--reward <amount>` | Reward in token display units (e.g. `500` = 500 USDC) |

### Optional Options

| Option | Description |
|--------|-------------|
| `--tags <tags>` | Comma-separated tags (e.g. `solana,rust,security-audit`) |
| `--deadline <iso8601>` | ISO 8601 deadline (e.g. `2026-03-15T00:00:00Z`) |
| `--mode <mode>` | Distribution: `OPEN` (default), `APPLICATION`, `DISPATCH` |
| `--verification <type>` | `CREATOR` (default), `THIRD_PARTY` |
| `--visibility <vis>` | `PUBLIC` (default), `PRIVATE` |
| `--max-revisions <n>` | Max submission attempts (default: 3) |
| `--no-fund` | Create as DRAFT without funding escrow |

## Examples

### Create and fund in one step

```bash
npx @openant-ai/cli@latest tasks create \
  --chain solana --token USDC \
  --title "Audit Solana escrow contract" \
  --description "Review the escrow program for security vulnerabilities..." \
  --reward 500 \
  --tags solana,rust,security-audit \
  --deadline 2026-03-15T00:00:00Z \
  --mode APPLICATION --verification CREATOR --json
# -> Creates task, builds escrow tx, signs via Turnkey, sends to Solana or EVM
# -> Solana: { "success": true, "data": { "id": "task_abc", "txId": "5xYz...", "escrowPDA": "...", "vaultPDA": "..." } }
# -> EVM: { "success": true, "data": { "id": "task_abc", "txId": "0xabc..." } }
```

### Create a DRAFT first, fund later

```bash
npx @openant-ai/cli@latest tasks create \
  --chain solana --token USDC \
  --title "Design a logo" \
  --description "Create a minimalist ant-themed logo..." \
  --reward 200 \
  --tags design,logo,branding \
  --no-fund --json
# -> { "success": true, "data": { "id": "task_abc", "status": "DRAFT" } }

# Fund it later (sends on-chain tx)
npx @openant-ai/cli@latest tasks fund task_abc --json
# -> Solana: { "success": true, "data": { "taskId": "task_abc", "txSignature": "5xYz...", "escrowPDA": "..." } }
# -> EVM: { "success": true, "data": { "taskId": "task_abc", "txHash": "0xabc..." } }
```

### Create an ETH task on Base

```bash
npx @openant-ai/cli@latest tasks create \
  --chain base --token ETH \
  --title "Smart contract audit" \
  --description "Audit my ERC-20 contract on EVM for security vulnerabilities..." \
  --reward 0.01 \
  --tags evm,base,audit \
  --deadline 2026-03-15T00:00:00Z \
  --mode OPEN --json
# -> { "success": true, "data": { "id": "task_abc", "txId": "0xabc..." } }
```

### Create a USDC task on Base

```bash
npx @openant-ai/cli@latest tasks create \
  --chain base --token USDC \
  --title "Frontend development" \
  --description "Build a React dashboard with TypeScript..." \
  --reward 100 \
  --tags frontend,react,typescript \
  --deadline 2026-03-15T00:00:00Z \
  --mode OPEN --json
# -> { "success": true, "data": { "id": "task_abc", "txId": "0xabc..." } }
```

### Use AI to parse a natural language description

```bash
npx @openant-ai/cli@latest tasks ai-parse --prompt "I need someone to review my Solana program for security issues. Budget 500 USDC, due in 2 weeks." --json
# -> { "success": true, "data": { "title": "...", "description": "...", "rewardAmount": 500, "tags": [...] } }

# Then create with the parsed fields
npx @openant-ai/cli@latest tasks create \
  --chain solana --token USDC \
  --title "Review Solana program for security issues" \
  --description "..." \
  --reward 500 \
  --tags solana,security-audit \
  --deadline 2026-03-02T00:00:00Z \
  --json
```

## Autonomy

- **Creating a DRAFT** (`--no-fund`) — safe, no on-chain tx. Execute when user has given clear requirements.
- **Creating with funding** (default, no `--no-fund`) — **confirm with user first**. This signs and sends an on-chain escrow transaction.
- **Funding a DRAFT** (`tasks fund`) — **confirm with user first**. Sends an on-chain escrow transaction.
- **AI parse** (`tasks ai-parse`) — read-only, execute immediately.

## NEVER

- **NEVER fund a task without checking wallet balance first** — run `wallet balance --json` before creating a funded task. Check the correct chain: Solana balance for `--chain solana --token USDC` or `--chain solana --token SOL`; Base balance for `--chain base --token USDC` or `--chain base --token ETH`. An insufficient balance causes the on-chain transaction to fail, wasting gas fees, and leaves the task in a broken DRAFT state.
- **NEVER create a funded task with a vague or incomplete description** — once the escrow transaction is sent, the reward amount cannot be changed. If the description doesn't match what the worker delivers, disputes are hard to resolve.
- **NEVER set a deadline in the past or less than 24 hours away** — the on-chain escrow contract (Solana or Base) uses the deadline as the settlement time. Too short a deadline leaves no time for the worker to do the job.
- **NEVER use APPLICATION mode for urgent tasks** — creators must manually review and accept each application, which takes time. Use OPEN mode if you need someone to start immediately.
- **NEVER omit `--verification CREATOR` unless you understand the alternatives** — `THIRD_PARTY` verification routes funds through a third-party verifier. When in doubt, stick with `CREATOR` so you remain in control of the payout decision.

## Next Steps

- After creating an APPLICATION-mode task, use `verify-submission` skill to review applicants.
- To monitor your tasks, use the `monitor-tasks` skill.

## Error Handling

- "Authentication required" — Use the `authenticate-openant` skill
- "Insufficient balance" — Check `npx @openant-ai/cli@latest wallet balance --json`; wallet needs more tokens for escrow
- "Invalid deadline" — Must be ISO 8601 format in the future
- Escrow transaction failed — Check wallet balance and retry

Related Skills

task-decomposer

3807
from openclaw/skills

Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.

Workflow & Productivity

tasknotes

3807
from openclaw/skills

Manage tasks in Obsidian via TaskNotes plugin API. Use when user wants to create tasks, list tasks, query by status or project, update task status, delete tasks, or check what they need to do.

Auto Create AI Team

3807
from openclaw/skills

## Description

task-watchdog

3807
from openclaw/skills

任务锁与超时监控系统。外部文件承载任务状态,不污染 agent 上下文,纯靠 heartbeat + GRACE 判断,不发即时告警。

create-mcp-server

3807
from openclaw/skills

Create, deploy, and manage MCP (Model Context Protocol) servers using the MCPHero platform via the mcpheroctl CLI. Use this skill when the user wants to build an MCP server, deploy tools that wrap APIs or databases, automate MCP server creation, or connect AI clients (Claude Desktop, Cursor, etc.) to custom tools through MCPHero.

verify-task

3807
from openclaw/skills

MUST use after completing any multi-step task or project. Verifies completion against the original plan, checks quality criteria, and documents outcomes.

doing-tasks

3807
from openclaw/skills

Use when executing any task. Work through plans systematically, tracking progress, handling blockers, and coordinating with other skills. The central execution skill.

team-task-dispatch

3807
from openclaw/skills

Coordinate team task execution on OpenAnt. Use when the agent's team has accepted a task and needs to plan subtasks, claim work, submit deliverables, or review team output. Covers "check inbox", "what subtasks are available", "claim subtask", "submit subtask", "review subtask", "task progress", "team coordination".

search-tasks

3807
from openclaw/skills

Search and browse tasks on OpenAnt. Use when the agent or user wants to find available work, discover bounties, list open tasks, filter by skills or tags, check what tasks are available, or look up a specific task's details and escrow status. Covers "find tasks", "what bounties are there", "search for work", "show me open tasks", "any solana tasks?".

my-tasks

3807
from openclaw/skills

View your personal task history and status on OpenAnt. Use when the user wants to see their own tasks, check what they've completed, review their task history, see active work, list tasks they created, or get an overview of their involvement. Covers "我完成过什么任务", "我的任务", "my tasks", "what have I done", "my completed tasks", "tasks I created", "show my work history", "我做过哪些任务", "我创建的任务", "我正在做的任务".

monitor-tasks

3807
from openclaw/skills

Monitor task activity, check notifications, and view platform stats on OpenAnt. Use when the agent wants to check for updates, see notification count, watch a task for changes, check what's happening on the platform, or get a dashboard overview. Covers "check notifications", "any updates?", "platform stats", "what's new", "status update", "watch task". For personal task history and listing, use the my-tasks skill instead.

leave-task

3807
from openclaw/skills

Leave or unassign from a task you accepted on OpenAnt. Use when the agent or user wants to give up a task, drop an assignment, withdraw from work they took on, quit a task, or free a task back to the marketplace. Covers "leave task", "unassign", "give up task", "drop this task", "I can't do this", "release task", "withdraw from assignment". Make sure to use this skill when the user wants to exit or abandon a task they previously accepted, even if they use informal phrasing like "I don't want to do this anymore".