Skip to content
cccskills
FreePublished on GitHub

alibaba-supplier-outreach

Codex-native supplier sourcing and outreach workflow for Alibaba using LaunchFast research. Use when the user wants supplier shortlists, outreach messages, reply triage, or negotiation support. Requires `supplier_research`. Browser automation is optional but useful when the user wants Codex to interact with Alibaba directly.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md3.8 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Alibaba Supplier Outreach

This skill has three modes: outreach, reply review, and follow-up drafting.

Mode detection

  • Product keyword or “find suppliers” -> OUTREACH
  • “check replies”, “any responses” -> REPLY REVIEW
  • “follow up”, “reply to supplier” -> FOLLOW-UP

Shared defaults

Use these defaults when the user does not care:

  • first order quantity: 500 units
  • shortlist size: top 5 suppliers
  • conversation notes path: ./artifacts/launchfast/supplier-conversations/

OUTREACH

1. Gather context

Ask once for:

  • product keyword
  • target price or landed-cost goal
  • target first order quantity
  • sign-off name or company
  • optional Amazon selling experience

2. Research suppliers

Run:

supplier_research(keyword="<keyword>", goldSupplierOnly=true, tradeAssuranceOnly=true, maxResults=10)

Present a compact shortlist with:

  • supplier name
  • quality score
  • price
  • MOQ
  • years in business
  • trust signals

3. Draft the outreach

Use this structure:

  1. Mention the supplier by name and one concrete credibility signal.
  2. Establish buyer credibility briefly.
  3. State quantity and target pricing clearly.
  4. Ask exactly 3 questions:
    • best price at target quantity
    • lead time
    • private-label capability
  5. End with a warm but direct close.

Always show the message to the user before sending it anywhere.

4. Browser automation, if requested

If the user wants Codex to send messages and browser automation tools are available, use this concrete flow:

  1. Open Alibaba in the browser automation session.
  2. Confirm the user is already logged in before proceeding.
  3. Navigate to the supplier page or Alibaba messaging UI.
  4. Use page inspection or accessibility snapshot tooling to find the Contact Supplier or reply form.
  5. Click into the message textarea and paste the approved message verbatim.
  6. Submit the form.
  7. Confirm success by checking for a sent-state confirmation or the new message appearing in the thread.
  8. Save the conversation summary to the local notes path.

If browser automation is unavailable, stop after drafting the approved message set.

5. Save notes

Store outreach notes under:

./artifacts/launchfast/supplier-conversations/[supplier-slug]/conversation.md

Keep a simple index file at:

./artifacts/launchfast/supplier-conversations/index.md

REPLY REVIEW

When the user asks to check replies:

  • use browser automation if available and authenticated
  • open Alibaba messages
  • inspect the conversation list for unread or recent threads
  • open each relevant thread
  • extract pricing, MOQ, lead time, sample terms, and direct supplier questions
  • summarize supplier-by-supplier
  • update the conversation note files

If browser automation is unavailable, ask the user to provide exported text or screenshots and continue from that material.

FOLLOW-UP

When drafting or sending a reply:

  • read the relevant conversation note file first if it exists
  • preserve negotiation context
  • answer supplier questions directly
  • push toward quote clarity, samples, lead time, packaging, and payment terms
  • ask for approval before sending any reply through the browser

If browser automation is used for the send:

  1. Open the supplier thread.
  2. Locate the reply textarea.
  3. Paste the approved response.
  4. Submit.
  5. Verify the message appears in the thread.
  6. Update the local notes file with the sent reply and timestamp.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Use AtomLane to compile and execute safe atomic parallel plans on macOS and native Windows Preview for worthwhile independent argv tasks, dependency DAGs, supported platform entrypoints, or Apple-silicon operators. Use at task start or an execution boundary when structured local work may contain two or more worthwhile units; skip plain answers, one quick command, and work whose effects cannot be safely bounded.

The English summary is being prepared. Showing the original description.

hashgraph-online/awesome-codex-plugins1.4KUpdated Oct 21, 2026

add

Free

Register a deferred decision in the debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you defer work, or when the user invokes $add. Over-register freely; the developer drops with "drop A", "drop A,C", or "drop all".

The English summary is being prepared. Showing the original description.

hashgraph-online/awesome-codex-plugins1.4KUpdated Oct 21, 2026

ADK 框架适配层。为 LangChain / EINO / AutoGen / AgentScope / CrewAI 提供框架特定的 代码模板、惯用模式、API 映射和项目结构,供 agent-dev-workshop Phase 5 代码生成使用。 每个框架 reference 文件标注 verified_date 用于版本锁定。

The English summary is being prepared. Showing the original description.

hashgraph-online/awesome-codex-plugins1.4KUpdated Oct 21, 2026

中文调试修复技能。用于报错、测试失败、页面异常、功能不符合预期、需要定位根因并做最小修复时。触发语包括"进入调试模式""帮我修问题""报错了""测试失败""页面坏了""找根因"。

The English summary is being prepared. Showing the original description.

hashgraph-online/awesome-codex-plugins1.4KUpdated Oct 21, 2026

交互式 AI Agent 开发工作坊:通过 6 阶段深度协作对话,引导用户完成 Agent 需求分析、架构设计、 工具定义、Prompt 与编排设计、代码生成、验证迭代,产出可直接运行的 Agent 项目。 框架无关设计优先,支持 LangChain / EINO / AutoGen / AgentScope / CrewAI 等 ADK 框架。

The English summary is being prepared. Showing the original description.

hashgraph-online/awesome-codex-plugins1.4KUpdated Oct 21, 2026

中文漂移审计技能。用于项目或学习过程变乱、上下文漂移、任务分叉、多个方案冲突、命名不一致、Codex 可能顺手改多了时。触发语包括"漂移检查""感觉跑偏了""项目变乱了""检查是否失控""分叉太多""上下文漂移"。

The English summary is being prepared. Showing the original description.

hashgraph-online/awesome-codex-plugins1.4KUpdated Oct 21, 2026

See all skills by hashgraph-online

Report a problem with this skill