TypingMindTypingMindThe best frontend for AI
Money Find logo

Money Find

Organization
XBuilderLAB
money-find

用「需求信号反推法」找 AI 时代兼职/副业机会——不搜"教你赚钱"的帖子（那是卖课钓粉的污染信源），而是看行业报告/招聘数据/采购数据等利益中立的需求信号，推理出个人能供给的机会，并用多个独立信号交叉验证，每个机会再过反诈+时效 rubric。触发词："帮我找机会"/"找AI兼职"/"有什么能搞钱的"/"money find"/"找副业"。前置：需要 .money-state.json（无则先路由到 money-init）。

Overview

PublisherXBuilderLAB
Repositorycheat-on-money
Skill namemoney-find
Stars
770
Forks
83
Bundled files
Instructions only
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by XBuilderLAB on GitHub. Read the source before you install it.

Installation

Install the Money Find AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/XBuilderLAB/cheat-on-money/tree/main/skills/money-find
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/XBuilderLAB/cheat-on-money.git /tmp/cheat-on-money
mkdir -p .claude/skills
cp -r /tmp/cheat-on-money/skills/money-find .claude/skills/money-find
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Money Find in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Money Find on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Money Find is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

/money-find — 需求信号反推 + 反诈筛选

跨平台说明（一次性，下文不再重复）

  • 资源路径：下文写的 ../../shared-references/、../../templates/、../../examples/、../../adapters/ 是 repo / Claude Code 的路径；Codex 安装下改读当前 skill 目录的 references/、templates/、examples/、adapters/（install-codex.sh 已软链进来）。
  • 网页检索/打开网页：Claude Code 用 WebSearch / WebFetch；Codex 用其内置等价能力。allowed-tools 是 Claude Code 权限声明，Codex 忽略。

核心方法（先读这条）

主方法是「需求信号反推法」，不是「搜怎么赚钱的帖子」。 没人会把真能赚钱的方法发到"教你赚钱"的帖里——那类内容是卖课/钓粉漏斗，利益不中立。 所以 money-find 看的是利益中立的需求信号（行业报告/招聘数据/采购数据/政策），再推理出个人能供给的机会。 完整方法见 ../../shared-references/demand-signal-method.md，本 skill 严格执行它。

铁律

  1. 主信源是一级信号（报告/招聘/采购/政策），"教你赚钱"类帖子不作依据，只用来了解方向。
  2. 每个机会要给"推理链 + 交叉验证"：从哪个信号推出来、另一个独立信号怎么印证它。单一来源 = 未验证。
  3. 绝不凭记忆。 信号一律实时网页检索获取。
  4. 核查发布日期（rubric C′）。 超 24 个月默认失效；12–24 个月标"可能过时"并交叉验证。检索词加年份。
  5. 每个机会先答"钱从哪来"，且过三连：谁有真需求 / 个人能否供给 / 买家个人够不够得着。
  6. 每个机会必须过 ../../shared-references/anti-scam-rubric.md（含 C′），标注判定后才呈现。
  7. 按画像收敛，不全量铺开。

流程

Step 0 — 读上下文

  • 读 .money-state.json 拿画像 + profile.tier 段位（无 → 路由 money-init）。
  • 读 ../../shared-references/user-tiers.md（按段位分流）。
  • 读 ../../shared-references/demand-signal-method.md（主方法）。
  • 读 ../../shared-references/opportunity-taxonomy.md（机会类型，仅辅助分类）。
  • 读 ../../shared-references/anti-scam-rubric.md（反诈 + 时效）。
  • 读 lessons.md（若存在）：用户过往复盘沉淀的经验，优先参考（哪类对他有效 / 哪些坑亲历过）。
  • 看 ../../examples/worked-examples.md 作为高质量推理范本参照。

Step 1 — 采集需求信号（demand-signal-method Step 1）

先按段位锁定方向范围（user-tiers）：T0→平台众包/接单；T1→技能服务/B端陪跑；T2→小工具/GEO/SaaS；T3→垂直专业服务。别给低段位推够不着的。

按方向实时网页检索 一级信源（都加年份）。除报告外，优先抓更一手的：

  • 真实招聘需求（BOSS/猎聘"在招什么、给多少、要哪些 AI 技能"——最诚实的需求温度计：岗位涨=有人花钱买这能力，降=红海）
  • 成交侧（闲鱼/1688/淘宝"正在卖什么服务、销量多少"——"有人真付钱"的直接证据）
    • ⚠️ 能力边界(诚实标注)：网页检索通常进不去登录墙，直接搜只能拿到二手转述，不是平台实时数据。
    • ✅ 要一手数据用 adapter（B 档半自动：用户自己登录+搜索，adapter 只读当前页公开列表；弹滑块用户手动过）：
      • 成交侧 → ../../adapters/xianyu（在卖什么/什么价/多少人想要）
      • 招聘侧 → ../../adapters/boss（在招什么/给多少/要哪些 AI 技能；只读搜索结果列表页，不进详情页、不碰 HR 个人信息，故不触反诈 A6）
  • <行业> AI 落地 需求 / 缺口 / 痛点 报告
  • <工具/服务> 市场规模 增长 采购 B端
  • 平台 官方 创作者 扶持 / 变现 政策 · 政策 / 监管 <领域> 新规

Step 2 — 推理 + 交叉验证（method Step 2-3）

对每个信号过三连（谁有真需求 / 个人能否供给 / 买家够得着），并找至少两个独立信号互相印证才往下推。 信号下降的方向，主动作为劝退呈现。

Step 3 — 形成方案 + 过反诈

每个方案套 anti-scam-rubric.md 的 D 节格式输出，并额外带「推理链」「交叉验证」两行： 推理链 / 交叉验证 / 机会 / 钱从哪来 / 硬红线 / 存疑信号 / 信息时效 / 判定 / 验证第一步 / 诚实收入预期。 验证第一步和收入预期都按用户段位写（user-tiers Step 3）；T0 的反诈讲得最重。

措辞基调：给的是"带证据链的推断/假设"，验证第一步就是去证伪它。未被市场验证前不说"这个能赚钱"。

Step 4 — 呈现 + 落盘

  • 按 可行 ✅ → 存疑 ⚠️ → 高危 ❌ 排序呈现，每个附"钱从哪来"和"验证第一步"。
  • 把候选写入 .money-state.json 的 opportunities[]（含 for_tier、verdict、freshness、found_at=今天）。
  • 结尾给期望管理一句话（rubric E），并提示：
    • "我想做 XX，帮我做计划" → money-plan
    • "再帮我查 XX 靠不靠谱" → money-verify

注意

  • 信息有时效性：在结果里注明"以下基于 <今天日期> 的检索，平台规则可能变化，开工前请复核"。
  • 找不到可信机会时，如实说没找到靠谱的，不要硬凑。这本身是有价值的反诈结论。

Frequently asked questions

What does the Money Find AI skill do?

用「需求信号反推法」找 AI 时代兼职/副业机会——不搜"教你赚钱"的帖子（那是卖课钓粉的污染信源），而是看行业报告/招聘数据/采购数据等利益中立的需求信号，推理出个人能供给的机会，并用多个独立信号交叉验证，每个机会再过反诈+时效 rubric。触发词："帮我找机会"/"找AI兼职"/"有什么能搞钱的"/"money find"/"找副业"。前置：需要 .money-state.json（无则先路由到 money-init）。

Why use Money Find on TypingMind?

Because you install it once and use it with any model. Money Find is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Money Find in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/XBuilderLAB/cheat-on-money/tree/main/skills/money-find. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Money Find?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Money Find?

As many as you like. As long as a model supports skills, you can use Money Find with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Money Find AI skill free?

It is published on GitHub by XBuilderLAB. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
CherryHQ logo

Faq Collector

CherryHQ
OrganizationPopular

将成功解决的用户问题收录到 FAQ 知识库。问题解决后自动判断是否收录。也可以在用户说"收录到 FAQ"、"记录这个问题"、"add to FAQ"时手动触发。

5.1K
52.5K
Instructions
View
CherryHQ logo

Issue Reporter

CherryHQ
OrganizationPopular

只在用户明确要求提交 GitHub Issue、GitHub Bug Report 或 GitHub Feature Request 时使用。用户只说“提交问题”“提交反馈”“上报 bug”“这是个 bug”或描述功能建议但未点名 GitHub 时不得触发，必须改用 cherry-studio-feedback 并默认提交飞书。

5.1K
52.5K
Instructions
View
CherryHQ logo

Skills Manager

CherryHQ
OrganizationPopular

搜索、安装和协调创建 Claude Code Agent Skills。当用户想要搜索技能、安装工具、创建自定义 Skill，或者说"find a skill"、"搜索技能"、"帮我做个 skill"、"create a skill"时触发。也适用于用户说"有没有做 X 的工具"、"我想扩展 Agent 能力"，或当前能力不足需要先查找可复用方案的场景。

5.1K
52.5K
Instructions
View
HKUDS logo

Cli Anything 3mf

HKUDS
OrganizationPopular

3MF mesh geometry editor — detect and resize cylindrical holes, repair meshes, compare 3D printing files. Works with BambuStudio and PrusaSlicer 3MF files.

4.6K
49.5K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇