← 返回 Skills 市场
staybased

Upwork Hunting

作者 staybased · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
1013
总下载
2
收藏
3
当前安装
1
版本数
在 OpenClaw 中安装
/install upwork-hunting
功能描述
Systematically find and evaluate Upwork automation jobs, bid strategically using 2,000+ n8n templates to maximize win rate and delivery speed.
安全使用建议
What to check before installing: - Clarify where the skill will run and what it may access. The SKILL.md references ~/projects/n8n-workflows/, workspace/artifacts/, and a live n8n at localhost:5678 — confirm these paths/services exist and are intended to be read or contacted. - Ask the author to declare required credentials (Twilio, OpenAI/Ollama, Upwork API keys if used) and config paths in the skill metadata. Right now the skill assumes credentials are 'already configured' but does not request them explicitly. - If you allow autonomous invocation, restrict the agent's network and filesystem permissions (or run in an isolated environment) because the skill instructs the agent to contact local services and third-party APIs. - Verify how the skill searches Upwork (web search vs Upwork API). Scraping pages or automating bidding may violate Upwork terms; get that clarified. - Prefer a version of this skill that lists required env vars and config paths, and that includes explicit 'dry-run' / manual-approval steps before posting bids or sending messages (Twilio) to prevent accidental outbound actions. If you can't get those clarifications, treat the skill as untrusted and avoid giving it filesystem/network access or permission to submit bids/messages automatically.
功能分析
Type: OpenClaw Skill Name: upwork-hunting Version: 1.0.0 The skill bundle defines an AI agent's strategy for finding and winning Upwork jobs. The `SKILL.md` file provides detailed instructions, criteria, and a playbook for the agent. While it mentions the agent's access to local resources (`~/projects/n8n-workflows/`, `localhost:5678`) and external APIs (Twilio, OpenAI), these are presented as capabilities essential for the skill's stated purpose of automation and job hunting. There are no instructions for data exfiltration, malicious execution, persistence, or any form of prompt injection designed to subvert the agent's core directives or perform unauthorized actions. All content is aligned with the legitimate goal of an 'Upwork Hunting' skill.
能力评估
Purpose & Capability
The SKILL.md describes finding and bidding on Upwork jobs using an n8n template library and a local n8n instance, which is coherent with a 'Upwork Hunting' purpose. However, the skill claims capabilities (live n8n demos, Twilio integration, OpenAI/Ollama use, template library ~~/projects/n8n-workflows/) that require local resources and credentials that are not declared in the skill metadata.
Instruction Scope
The runtime instructions explicitly reference local files/paths (~/projects/n8n-workflows/, workspace/artifacts/), a local service (localhost:5678), and configured third-party services (Twilio, OpenAI, Ollama). The skill does not declare or justify access to these paths or services, nor does it explain how it will authenticate to Upwork (scrape vs API). Instructions therefore ask the agent to read local state and reach local/external endpoints without any declared boundaries.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so there is no installer risk. Nothing will be written to disk by an installer as part of skill installation.
Credentials
The skill presumes access to Twilio, OpenAI/Ollama, and a local n8n instance but declares no required environment variables or primary credential. That absence is disproportionate to the claimed capabilities: those integrations normally require API keys/credentials and/or local configuration paths.
Persistence & Privilege
The skill does not request always:true and has no install-time persistence. It can be invoked autonomously (platform default), which increases its practical reach — combine that with the other concerns (local services and undeclared creds) before enabling autonomous use.
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 upwork-hunting
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /upwork-hunting 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
Initial release — job targeting, template matching, 30-day playbook
元数据
Slug upwork-hunting
版本 1.0.0
许可证
累计安装 4
当前安装数 3
历史版本数 1
常见问题

Upwork Hunting 是什么?

Systematically find and evaluate Upwork automation jobs, bid strategically using 2,000+ n8n templates to maximize win rate and delivery speed. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1013 次。

如何安装 Upwork Hunting?

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

Upwork Hunting 是免费的吗?

是的,Upwork Hunting 完全免费(开源免费),可自由下载、安装和使用。

Upwork Hunting 支持哪些平台?

Upwork Hunting 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 Upwork Hunting?

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

💬 留言讨论