Skip to content
Agentmart
Submit a tool

ecopartner-match-recommend

中南片区生态伙伴智能匹配 — 输入客户AI需求,匹配中南片区240家生态伙伴,输出推荐方案+追问澄清+HTML报告。触发词:供需匹配、伙伴匹配、中南片区匹配、服务商匹配、智能匹配、AI匹配、推荐方案、匹配伙伴、找服务商、伙伴推荐、AI需求、生态伙伴、ecopartner、ecopartner-match-recomm…

Skill by AgenticAIPlan

IndexedMIT★ 12
Write a review

Chalk Labs

Need help deploying ecopartner-match-recommend?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/agenticaiplan-ecopartner-match-recommend

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

中南片区生态伙伴智能匹配 — 输入客户AI需求,匹配中南片区240家生态伙伴,输出推荐方案+追问澄清+HTML报告。触发词:供需匹配、伙伴匹配、中南片区匹配、服务商匹配、智能匹配、AI匹配、推荐方案、匹配伙伴、找服务商、伙伴推荐、AI需求、生态伙伴、ecopartner、ecopartner-match-recommend

Use cases: frontend

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/ecopartner-match-recommend

What's inside

Skill name
ecopartner-match-recommend
Description
中南片区生态伙伴智能匹配 — 输入客户AI需求,匹配中南片区240家生态伙伴,输出推荐方案+追问澄清+HTML报告。触发词:供需匹配、伙伴匹配、中南片区匹配、服务商匹配、智能匹配、AI匹配、推荐方案、匹配伙伴、找服务商、伙伴推荐、AI需求、生态伙伴、ecopartner、ecopartner-match-recommend
License
MIT
Instructions
128 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (12)

  • .gitignore
  • README.md
  • SKILL.md
  • design-guide.md · references/
  • match-report-example.html · references/
  • partner-data-schema.md · references/
  • partner-data.json · references/
  • report-template.html · references/
  • screenshot-followup.png · references/
  • screenshot-overview.png · references/
  • screenshot-partners.png · references/
  • match.py · scripts/

SKILL.md (first lines)

# ecopartner-match-recommend

## 适用场景

当用户需要将一个模糊的 AI 落地需求快速匹配至中南片区的生态伙伴时,使用本 Skill。

典型触发场景:
- 客户提出 AI 项目需求,但未明确指定供应商
- 需要快速了解某类 AI 能力有哪些合作伙伴可承接
- 需要生成一份可汇报的伙伴匹配方案
- 区域生态运营中的供需对接

**关键约束**:本 Skill 仅覆盖中南片区生态伙伴,包括华南(广东、广西、海南、福建、香港、澳门)、华中(湖南、湖北)、西南(重庆、四川)。

---

## 输入要求

- **业务目标**:客户想解决的 AI 落地问题(描述性文本)
- **背景上下文**:客户的行业、规模等基本信息(如有)
- **关键约束**:是否指定技术路线(飞桨/文心)、预算范围等
- **期望输出**:推荐伙伴列表 + 可视化报告

---

## 执行步骤

### Step 1:读取伙伴数据

读取 `references/partner-data.json`,获取完整伙伴列表。

### Step 2:智能需求解析

仔细理解客户需求,拆解出所需 AI 能力组合:
- 需要 OCR 文字识别吗?
- 需要计算机视觉(图像检测/分类/分割)吗?
- 需要自然语言处理(文本分析/抽取)吗?
- 需要大模型/智能体吗?
- 需要语音识别吗?
- 还需要什么其他能力?

### Step 3:技术选型建议

根据场景推荐飞桨或文心技术路线:

| 场景 | 推荐技术 | 原因 |
|------|----------|------|
| 软硬一体/边缘部署 | 飞桨 | PaddleX、PP-OCR 原生支持端侧 |
| OCR + 视觉组合 | 飞桨 | PP-OCRv5 + PaddleX 视觉生态完整 |
| 工业视觉/质检 | 飞桨 | 工业相机 + 边缘推理生态成熟 |
| 快速接入/大模型对话 | 文心 | ERNIE API 调用简单,上线快 |
| 知识库 + RAG | 文心 | ERNIE + 千帆平台集成更好 |
| 数字人/创意生成 | 文心 | ERNIE 数字人能力更强 |

### Step 4:多标签组合匹配

带着 Step 2 分析出的 AI 能力,逐一审视伙伴数据:

| 优先级 | 规则 |
|--------|------|
| 第一优先 | ai_tags 同时包含多个需求能力 |
| 第二优先 | ai_tags 包含核心能力 + industry 匹配 |
| 第三优先 | ai_tags 包含核心能力(备选) |

### Step 5:分级推荐输出

按匹配度输出推荐结果:

| 等级 | 标准 |
|------|------|
| ⭐⭐⭐⭐ 强烈推荐 | AI能力全匹配 + 行业/场景匹配 |
| ⭐⭐⭐ 推荐 | AI能力匹配,或能力+行业部分匹配 |
| ⭐⭐ 备选 | 仅AI能力匹配 |

### Step 6:智能追问

每次选最相关的 1-2 个维度追问,每次 ≤ 3 个问题:

| 维度 | 作用 | 适用场景 |
|------|------|----------|
| 项目阶段 | 判断 POC 还是已立项 | 几乎所有场景 |
| 数据情况 | 影响方案设计 | 需要模型训练的 |
| 预算/时间 | 筛选供应商档位 | 有档位差异时 |

### Step 7:生成 HTML 可视化报告

完成匹配后,生成独立 HTML 报告,包含:
- 需求分析(客户场景、所需 AI 能力、推荐技术)
- 伙伴推荐(按分级展示)
- 匹配理由(每家伙伴的核心优势)
- 注意事项(选型和实施关键提示)
- 追问清单(引导深入了解项目)

---

## 输出要求

- **结构清晰**:按 ⭐⭐⭐⭐强烈推荐 / ⭐⭐⭐推荐 / ⭐⭐备选 分级展示
- **结论与过程一致**:匹配理由需对应 Step 2 分析出的 AI 能力
- **明确风险与假设**:
  - 定价信息不完整,需单独询价
  - 星级评分基于 ai_tags 匹配度,实际效果以 POC 为准
  - 区域限制:仅中南片区

---

## 参考资料

| 文件 | 用途 |
|------|------|
| `references/partner-data.json` | 核心数据:240+ 生态伙伴信息 |
| `references/partner-data-schema.md` | 数据字段说明 |
| `references/report-template.html` | HTML 报告模板 |
| `references/match-report-example.html` | 报告示例 |
| `references/screenshot-*.png` | 报告效果截图 |

---

## 踩坑经验

From AgenticAIPlan/AgenticAISkills, MIT.

More from AgenticAIPlan/AgenticAISkills

Signals

Stars
12
Forks
55
Open issues
4
Last commit (this folder)
Apr 21, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from AgenticAIPlan

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get ecopartner-match-recommend running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying ecopartner-match-recommend?

CallGet help
Cite this page

ecopartner-match-recommend skill. Agent Mart. https://agentmart.dev/skills/agenticaiplan-ecopartner-match-recommend (last updated 2026-10-24)