Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tranfu-labs/tranfu-skills --skill ai-startup-feasibility-checkgit clone --depth 1 https://github.com/tranfu-labs/tranfu-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tranfu-labs/tranfu-skills/ai-startup-feasibility-check)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/ai-startup-feasibility-check"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/ai-startup-feasibility-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/ai-startup-feasibility-check"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/ai-startup-feasibility-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00428 | $0.02683 |
| Opus 5 | $0.00214 | $0.01341 |
| Sonnet 5 | $0.00086 | $0.00537 |
| Haiku 4.5 | $0.00043 | $0.00268 |
Grade A, and why
ai-startup-feasibility-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 创业方向可行性自检 · Feasibility Check Skill
为任何 AI 相关的创业方向 / 投资机会 / 项目判断，自动套用一套基于平台风险与护城河结构的强制评估框架。
本技能存在的目的：让"AI 风口"叙事下的项目立项决策，必须通过一道结构化的怀疑性筛查。
触发与配合
自动触发场景：
- 任何对 AI 创业方向、赛道、投资机会的研究任务
- 用户描述一个具体 AI 项目并问"怎么样 / 值不值得做 / 能不能成"
- 与
elite-market-researcher或market-analysis技能并用时
配合规则：
- 如果同时触发了
elite-market-researcher：本技能在其 Step 6 报告输出之后，追加一个独立章节## 附录 X · AI 创业可行性自检，强制完成 4 个评估模块。 - 如果单独触发：完整输出 4 个评估模块作为独立报告。
- 评估对象不限于"创业方向"——也可以是某个已存在项目（如分析 UUMit、Mercor、某 startup）。
执行流程
收到 AI 创业方向 / 项目评估任务
↓
Step 1：方向归类（属于 Tier 1 / 2 / 3 哪一类？）
↓
Step 2：三维评分（替代风险 / 杠杆方向 / 单位经济）
↓
Step 3：10 题自检表
↓
Step 4：输出可行性诊断（含建议动作）
Step 1：方向归类 —— 13 条禁止清单对照
读取 references/prohibition-list.md，将研究目标对照 13 条禁止方向，识别命中哪些。
输出格式：
| 编号 | 禁止方向 | 命中 | 命中证据 |
|---|---|---|---|
| 1.1 | 单功能 AI 工具 | ✅/❌ | [若命中，说明哪个特征命中] |
| 1.2 | 通用 Agent / OS | ✅/❌ | ... |
| ... | ... | ... | ... |
命中规则：
- 命中 1 条 Tier 1 = 🔴 红灯（结构性死亡概率 > 80%）
- 命中 2 条以上 Tier 2 = 🔴 红灯
- 命中 1 条 Tier 2 + 任意 Tier 3 = 🟡 黄灯
- 仅命中 Tier 3 = 🟡 黄灯
- 全部未命中 = 🟢 绿灯（进入下一步评估）
Step 2：三维评分
对研究目标从三个维度评估，每维评分 [+2, +1, 0, -1, -2]：
维度 A：替代风险 (Substitution Risk)
基础模型公司主动 / 被动覆盖该产品功能的概率。
- +2：基础模型公司明确不会做（如需要牌照、需要线下、需要专有数据）
- +1：基础模型公司可能做但不愿意做（脏活累活、低毛利）
- 0：基础模型公司可能做但需要 24+ 个月
- -1：基础模型公司可能在 12 个月内覆盖
- -2：基础模型公司 6 个月内或已经在 roadmap
维度 B：杠杆方向 (Leverage Direction)
模型变强对你的影响。
- +2：模型越强我越赚（推理成本下降直接转化为毛利）
- +1：中性偏正（模型升级让产品自动变好）
- 0：完全中性
- -1：模型变强会侵蚀部分价值
- -2：模型变强直接让产品变得不必要
维度 C：单位经济 (Unit Economics)
LTV / CAC 在规模化下的趋势。
- +2：边际成本随规模下降，毛利随时间扩张
- +1：单位经济健康，可线性扩张
- 0：当前盈利但增长受限
- -1：LTV 接近 CAC，规模化困难
- -2：LTV < CAC 且无明显改善路径
综合判定
| 三维总分 | 判定 | 建议 |
|---|---|---|
| +4 ~ +6 | 🟢 优质方向 | 加大投入 |
| +1 ~ +3 | 🟢 可做但需聚焦 | 选定最强单边突破 |
| 0 | 🟡 边界条件 | 重新评估定位 |
| -1 ~ -3 | 🟡 高风险 | 需要明确反例条件 |
| -4 ~ -6 | 🔴 结构性死亡 | 不应启动 |
Step 3：10 题自检表
逐题作答，每题给出（是 / 否 / 不确定）+ 1 句证据：
- 能力替代检验：模型 12 个月内提升 50%，产品变得更值钱还是更不值钱？
- 杠杆方向：模型升级时，客户对你的依赖是增强还是减弱？
- 单一 API 风险：72 小时内能切换主要模型供应商吗？
- 护城河层级：核心壁垒在哪一层？（模型能力 / UI / 工作流 / 分发 / 数据-社区）— 第三层以下扣分
- 客户身份：付费客户是企业还是"想做副业的个人"？
- 付费意愿验证：是否已有 3+ 个付费客户？（早期项目可放宽至"3+ 个明确付费意向"）
- 替代成本：客户离开你切换到下一个方案需要多少天？少于 7 天 = 没粘性
- 数据排他性：基础模型训练数据中能找到你的核心数据吗？能找到 = 没壁垒
- 责任承担：AI 错误时谁赔？能赔得起吗？有牌照 / 保险吗？
- 聚焦度：当前同时在做几个业务模型？> 1 = 红灯
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 216 lines · 428 tokens per session scan A cbcb85606d8c
ai-startup-feasibility-check is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 428 tokens to every session and 2,683 once invoked, about $0.0021 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…