界面已本地化;技能介绍与说明文档按所选语言由 AI 自动翻译,代码、命令、路径和专业术语保留原文,以原作者文档为准。
探索技能
效率与协作 · SKILL.md

Upwork

Upwork

【效率与协作】Win freelance projects on Upwork with profile optimization, proposal writing, client communication, and scam detection.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准

技能说明

GitHub

name: Upwork slug: upwork version: 1.0.0 description: Win freelance projects on Upwork with profile optimization, proposal writing, client communication, and scam detection. homepage: https://clawic.com/skills/upwork metadata: clawdbot: emoji: 💼 displayName: Upwork

Quick Reference

AreaWhat the Agent Does
ProfileOptimize title, bio, portfolio, hourly rate
ProposalsWrite personalized, non-templated proposals
Red FlagsDetect scams, problematic clients, bad contracts
CommunicationDraft professional responses, handle negotiations
StrategyJSS optimization, pricing, client retention

Critical Rules

  1. Human-in-the-loop MANDATORY — Agent prepares drafts, human reviews and sends manually. Never auto-send proposals or messages.
  2. No credential access — Agent never logs into Upwork or accesses account directly. User copy-pastes info as needed.
  3. No automation scripts — Never provide code to automate Upwork actions, bypass detection, or scrape data.
  4. Honest timelines — Never promise delivery faster than realistically achievable.
  5. No off-platform payments — Always warn against payments outside Upwork (ToS violation = ban).

Red Flags to Always Flag

  • Budget <$100 for complex work
  • "Need ASAP" + low budget
  • Client with no payment history or <4.5 stars
  • Requests for free "test" work
  • Wants to move to WhatsApp/email immediately
  • Vague scope ("build me an app")
  • Payment outside platform

Workflow

For proposals: See proposals.md For profile optimization: See profile.md For client communication: See communication.md For platform mechanics: See platform.md For legal context: See legal.md

Disclaimer

This skill helps freelancers work more effectively on Upwork. The user is solely responsible for complying with Upwork's Terms of Service. All agent outputs must be reviewed before use. This is productivity assistance, not automation.

我的收藏