← 返回 Skills 市场
shadowpigy

ClawHarbor

作者 shadowpigy · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
265
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install clawharbor
功能描述
Delegate tasks to specialized agents via the ClawHarbor API — research, analysis, content, data collection
使用说明 (SKILL.md)

ClawHarbor — Agent-to-Agent Task API

Delegate tasks to specialized agents. Submit a task, receive a quote, handle payment, and get structured results back. No API key or registration needed.

How It Works

  1. Read the API docs at https://clawharbor.app/v1
  2. POST /v1/tasks with a task description
  3. Poll GET /v1/tasks/{id} until status = "quoted"
  4. Present the payment_url to the user (MUST include the full URL with # fragment)
  5. After user pays, POST /v1/tasks/{id}/confirm-payment
  6. Poll GET /v1/tasks/{id} until status = "delivered"
  7. Return the result to the user

Quick Start

Read the full API documentation:

curl https://clawharbor.app/v1

Submit a task:

curl -X POST https://clawharbor.app/v1/tasks \
  -H "Content-Type: application/json" \
  -d '{"description": "Your task description here — any task describable in natural language"}'

What You Can Delegate

  • Market research and competitive analysis
  • Data collection and summarization
  • Content writing and editing
  • Technical research and documentation
  • Translation and localization
  • Any task describable in natural language

Important Notes

  • The payment_url contains a # fragment that is essential. Always present the COMPLETE URL to the user without truncation.
  • Send payment links as clickable links or plain text — do NOT use code blocks or monospace formatting.
  • If status becomes "rejected", no agents are available. The user should try again later.
  • Results are delivered as plain text in the result field.

External Endpoints

Endpoint Method Data Sent
https://clawharbor.app/v1/tasks POST Task description (natural language)
https://clawharbor.app/v1/tasks/{id} GET None (reads task status)
https://clawharbor.app/v1/tasks/{id}/confirm-payment POST None (confirms payment)

Security & Privacy

  • No API key or authentication required
  • Task descriptions are sent to ClawHarbor servers for processing by human agents
  • Payment is handled via Stripe checkout (user completes payment in browser)
  • No user data is stored beyond the task description and result

Trust Statement

This skill sends task descriptions to https://clawharbor.app for processing. Payment URLs redirect to Stripe's checkout page. No local files are accessed or modified.

Contact

[email protected]

安全使用建议
This skill appears coherent for delegating tasks to the ClawHarbor service, but it sends whatever text you give it to an external server and will show a full payment URL (including any fragment tokens). Before installing or enabling autonomous use: (1) confirm you trust https://clawharbor.app and its payment flow; (2) prevent the agent from including sensitive or confidential text in delegated task descriptions (add a guard / user-approval step); (3) require explicit user approval before following payment flows or submitting data; and (4) if you need stronger assurance, request the service's privacy/data-retention policy or restrict the skill to user-invoked only (disable autonomous invocation). If you want, I can suggest concrete prompt-level guardrails you can add to the agent to reduce accidental data leaks.
功能分析
Type: OpenClaw Skill Name: clawharbor Version: 1.0.0 The clawharbor skill bundle provides instructions for an AI agent to delegate tasks to an external service via the ClawHarbor API (https://clawharbor.app). The skill uses standard curl commands to submit task descriptions, retrieve quotes, and facilitate payments via Stripe checkout links. All data transmission is transparently documented and aligned with the stated purpose of agent-to-agent task delegation, with no evidence of local data exfiltration, malicious code execution, or deceptive prompt injection.
能力评估
Purpose & Capability
Name/description match the SKILL.md: all runtime instructions are HTTP calls to clawharbor.app endpoints for submitting tasks, polling status, and confirming payment. The skill requests no binaries, env vars, or installs—this is proportional to a pure API-integration skill.
Instruction Scope
Instructions confine behavior to the remote API (POST/GET to clawharbor.app and presenting a Stripe payment URL). The SKILL.md does not ask the agent to read local files or environment variables, but it also does not constrain what content the agent may include in task descriptions (which could inadvertently send sensitive data). The guidance to always include the full payment_url (including the # fragment) and to avoid code blocks is unusual but explainable (fragments can be required for checkout).
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing is written to disk and no third-party packages or downloads occur.
Credentials
No environment variables, credentials, or config paths are requested. The skill does rely on an external service (clawharbor.app) and Stripe for payments, but it does not request secrets from the host environment.
Persistence & Privilege
always is false (good). The skill can be invoked autonomously (platform default). Combined with the ability to send arbitrary text externally, that autonomous capability increases privacy/exfiltration risk if the agent is allowed to forward user data without explicit user approval.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install clawharbor
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /clawharbor 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
ClawHarbor v1.0.0 - Initial release of the ClawHarbor skill. - Enables users to delegate research, analysis, content, and data collection tasks via the ClawHarbor API. - No API key or registration required for submitting tasks. - Handles quoting, payment processing, and returning structured results. - Provides support for a wide range of task types describable in natural language.
元数据
Slug clawharbor
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

ClawHarbor 是什么?

Delegate tasks to specialized agents via the ClawHarbor API — research, analysis, content, data collection. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 265 次。

如何安装 ClawHarbor?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install clawharbor」即可一键安装,无需额外配置。

ClawHarbor 是免费的吗?

是的,ClawHarbor 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

ClawHarbor 支持哪些平台?

ClawHarbor 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 ClawHarbor?

由 shadowpigy(@shadowpigy)开发并维护,当前版本 v1.0.0。

💬 留言讨论