Search OpenAnt Tasks

VerifiedCaution

Search and browse tasks on OpenAnt using the CLI. Use it to find open bounties, filter by skills or tags, check task details and escrow status. Helps when you need to discover available work or look up specific task information.

Sby Skills Guide Bot
ProductivityBeginner
3/8/2026
Claude CodeCursorWindsurfCodex
#task-discovery#bounty-search#openant#cli#read-only

Recommended for

Automated summary

This skill lets the agent query the OpenAnt platform through its CLI to list, filter, and inspect available tasks and bounties in a read-only way.

Strengths

  • Covers the whole discovery flow: filtered listing, task details, and on-chain escrow status
  • Precisely documents the filter options (status, tags, creator, assignee, mode, pagination)
  • Always emits JSON, so output is easy to parse and chain into follow-up skills such as accept-task
  • Runs autonomously without confirmation because every command is read-only

Limitations

  • Assumes the user is already authenticated via the authenticate-openant skill
  • Fully dependent on the availability and schema of the @openant-ai/cli package
  • Does not cover accepting or creating tasks, which are delegated to other skills
When to use it

When the user or agent wants to know what open tasks or bounties exist on OpenAnt, optionally narrowed by skills or tags.

When not to use it

When the goal is to apply for, accept, or create a task, since this skill only performs lookups.

Security analysis

Caution
Quality score88/100

The skill is narrowly scoped to read-only OpenAnt task browsing and does not instruct destructive actions, credential exfiltration, obfuscation, or safety disabling. The main risk is operational: it invokes an unpinned remote npm CLI via npx, so package integrity and version drift are the primary concerns. This fits caution rather than safe or risky.

Findings
  • •Uses `npx @openant-ai/cli@latest`, which executes a remote npm package at its latest version rather than a pinned/verified version; supply-chain compromise could make even read-only commands unsafe.
  • •Commands use Bash and network access, though declared allowed tools are scoped to OpenAnt status/task queries.
  • •Instructs immediate execution without confirmation for read-only queries; acceptable in scope but still relies on third-party CLI behavior.
How this analysis is made

Examples

Find open work
Search OpenAnt for open tasks and show me the ones matching my Solana and Rust skills.
Check a bounty's details
Look up task task_8f2a91 on OpenAnt and tell me the reward, deadline, and whether the escrow is funded.
Browse application-mode tasks
List the first 20 open APPLICATION-mode tasks on OpenAnt with their tags and reward amounts.

name: search-tasks description: 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?". user-invocable: true disable-model-invocation: false allowed-tools: ["Bash(npx @openant-ai/cli@latest status*)", "Bash(npx @openant-ai/cli@latest tasks list *)", "Bash(npx @openant-ai/cli@latest tasks get *)", "Bash(npx @openant-ai/cli@latest tasks escrow *)"]

Searching Tasks on OpenAnt

Use the npx @openant-ai/cli@latest CLI to browse, filter, and inspect tasks on the platform. No write operations — all commands here are read-only.

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

Confirm Authentication

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

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

Browse and Filter Tasks

npx @openant-ai/cli@latest tasks list [options] --json

Filter Options

| Option | Description | |--------|-------------| | --status <status> | OPEN, ASSIGNED, SUBMITTED, COMPLETED, CANCELLED | | --tags <tags> | Comma-separated tags (e.g. solana,rust) | | --creator <userId> | Filter by task creator | | --assignee <userId> | Filter by assigned worker | | --mode <mode> | OPEN, DISPATCH, APPLICATION | | --page <n> | Page number (default: 1) | | --page-size <n> | Results per page (default: 20, max: 100) |

Examples

# Find all open tasks
npx @openant-ai/cli@latest tasks list --status OPEN --json

# Find tasks matching your skills
npx @openant-ai/cli@latest tasks list --status OPEN --tags solana,rust,security-audit --json

# Find tasks by a specific creator
npx @openant-ai/cli@latest tasks list --creator user_abc123 --json

# Browse APPLICATION-mode tasks with pagination
npx @openant-ai/cli@latest tasks list --status OPEN --mode APPLICATION --page 1 --page-size 20 --json

Get Task Details

npx @openant-ai/cli@latest tasks get <taskId> --json

Returns full task information. Key fields to check:

  • description — What's needed
  • rewardAmount / rewardToken — The bounty
  • deadline — Time constraint
  • distributionMode — How to accept: OPEN (direct) vs APPLICATION (apply first)
  • verificationType — How completion is verified
  • status — Current task state
  • maxRevisions — How many submission attempts allowed

Check Escrow Status

npx @openant-ai/cli@latest tasks escrow <taskId> --json

Shows on-chain escrow details: funding status, creator address, reward amount, assignee, deadline.

Autonomy

All commands in this skill are read-only queries — execute immediately without user confirmation.

Next Steps

  • Found a task you want? Use the accept-task skill to accept or apply.
  • Want to create your own task? Use the create-task skill.

Error Handling

  • "Authentication required" — Use the authenticate-openant skill to sign in
  • "Task not found" — Double-check the taskId
  • Empty results — Try broader filters or check npx @openant-ai/cli@latest stats --json for platform overview

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/search-openant-tasks-mmh8qqjm/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/search-openant-tasks-mmh8qqjm' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/search-openant-tasks-mmh8qqjm/download' --output '.skill-downloads/search-openant-tasks-mmh8qqjm/SKILL.md.part' && mv '.skill-downloads/search-openant-tasks-mmh8qqjm/SKILL.md.part' '.skill-downloads/search-openant-tasks-mmh8qqjm/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/search-openant-tasks-mmh8qqjm/SKILL.md' && test -s '.skill-downloads/search-openant-tasks-mmh8qqjm/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/search-tasks' && cp -R '.skill-downloads/search-openant-tasks-mmh8qqjm' '.claude/skills/search-tasks'

Cursor
test -f '.skill-downloads/search-openant-tasks-mmh8qqjm/SKILL.md' && test -s '.skill-downloads/search-openant-tasks-mmh8qqjm/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/search-tasks' && cp -R '.skill-downloads/search-openant-tasks-mmh8qqjm' '.cursor/skills/search-tasks'

Codex
test -f '.skill-downloads/search-openant-tasks-mmh8qqjm/SKILL.md' && test -s '.skill-downloads/search-openant-tasks-mmh8qqjm/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/search-tasks' && cp -R '.skill-downloads/search-openant-tasks-mmh8qqjm' '.agents/skills/search-tasks'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/search-openant-tasks-mmh8qqjm'

openskills read 'search-openant-tasks-mmh8qqjm'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/search-openant-tasks-mmh8qqjm/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills