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-opportunity-evaluationgit 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-opportunity-evaluation)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/ai-opportunity-evaluation"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/ai-opportunity-evaluation/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-opportunity-evaluation"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/ai-opportunity-evaluation.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 | $0.00110 | $0.02016 |
| Opus 5 | $0.00055 | $0.01008 |
| Sonnet 5 | $0.00022 | $0.00403 |
| Haiku 4.5 | $0.00011 | $0.00202 |
Grade A, and why
ai-opportunity-evaluation 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI机会立项判断
项目能不能做,不看它能不能开发出来,而看它能不能解决真实问题,并沉淀 TranFu 的能力。
本 Skill 是 TranFu 第二阶段产品开发的立项门禁。它不是需求包装助手,而是在 PRD 和开发前,帮助团队判断一个想法是否值得继续投入。
When to use
当用户想判断一个产品想法、内部工具、Agent 想法、工作流产品或一句话项目是否值得立项时使用。典型触发短语:
- "判断这个项目怎么样"
- "帮我做个立项判断"
- "这个方向能不能做"
- "这个产品想法值不值得做"
- "用 AI机会立项判断 Skill,帮我分析"
也适用于用户只丢出一个产品名或一句话想法,并且上下文是在讨论产品机会、内部提效、能力沉淀、对外案例或是否进入 PRD。
不适用:用户已经明确要求直接开发、修 bug、部署、写代码,或某个方向已经完成立项并明确要求输出 PRD。
工作模式
CREATE A TODO LIST FOR THE TASKS BELOW: 1) 判断信息是否足够 2) 判断真实问题 3) 判断 TranFu 价值 4) 输出立项判断卡
Step 1: 判断信息是否足够
任务:先识别用户给的是完整立项信息,还是只有一句话想法。
输入:项目名、一句话描述、背景信息、团队上下文。
输出:如果信息不足,只问 2-3 个最关键问题,不输出完整判断卡。
优先追问:
- 谁会高频使用?
- 现在怎么解决,最麻烦的地方是什么?
- 这个项目想验证什么能力、流程、Skill、Agent 或 SOP?
MUST 在 3 轮追问内给出立项判断卡;NEVER 进入第 4 轮追问。
若 3 轮追问后 4 项关键事实(用户 / 现解决方式 / 频率与损失 / 内部使用意愿)仍缺 ≥2 项,MUST 输出立项判断卡,结论字段写"暂不建议做",核心理由第 1 条写"关键事实不足,待补充后重审",并退出。
Step 2: 判断真实问题
任务:判断它是不是解决真实、高频、具体的问题,而不是一个随手想到的功能。
重点检查:
- 是否说清楚目标用户。
- 是否说清楚当前解决方式。
- 是否说清楚痛点频率和损失。
- 是否有内部团队愿意反复使用。
输出:保留关键事实和缺口,不要写长篇分析。
Step 3: 判断 TranFu 价值
任务:判断这个项目是否符合 TranFu 第二阶段产品开发原则。
按顺序判断:
- 真实问题:是不是有人真的需要?
- 使用频率:是不是高频问题?
- 内部价值:TranFu 团队会不会反复用?
- 验证目标:能不能验证流程、Skill、Agent 或 SOP?
- 沉淀价值:能不能变成官网产品、模板、案例或交付能力?
- 品牌风险:做出来会不会像低质 Demo,反而影响 TranFu 形象?
结论 MUST 是三档之一:
- 建议做
- 优化后再做
- 暂不建议做
NEVER 使用"可以考虑" / "有一定价值" / "看情况" / "可能值得"这类模糊结论。
Step 4: 输出立项判断卡
任务:用短卡片输出判断,让团队成员一眼知道下一步。
每块 1-2 句话,核心理由最多 3 条,整体控制在一屏以内。
立项判断:建议做 / 优化后再做 / 暂不建议做
核心理由:
1. ...
2. ...
3. ...
真实问题:
...
验证目标:
...
首版范围:
...
风险提醒:
...
下一步:
...
What NOT to do
- ❌ NEVER 直接写 PRD;仅当用户在本 Skill 完成立项判断后另行明确要求写 PRD 时,结束本 Skill 并转入 PRD 任务。
- ❌ NEVER 把普通工具包装成战略产品,例如低配排版器、低配待办页。
- ❌ NEVER 因为"能开发出来"就建议立项,必须看到真实问题和 TranFu 能力沉淀。
- ❌ NEVER 输出长篇产品分析报告;除非用户显式要求详细复盘,否则默认一屏以内。
- ❌ NEVER 一次追问 8 个问题,信息不足时只问最关键的 2-3 个。
- ❌ NEVER 给出模糊结论,必须在三档结论中选择一个。
- ❌ NEVER 建议做会影响 TranFu 品牌形象的低质 Demo。
示例判断
VPN智能路由平台
立项判断:建议做
核心理由:
1. 团队确实有 VPN 资源管理、分发、权限回收的问题。
2. 能验证"资源池管理 -> 可用性监控 -> 订阅分发"的关键流程。
3. 后续可以沉淀为内部网络资源管理 SOP,甚至成为对外案例。
真实问题:
团队网络资源分散,稳定性、权限和设备限制都需要统一管理。
验证目标:
验证资源统一管理、智能分发和权限回收流程。
首版范围:
先做资源录入、成员分配、订阅生成和可用性检查,不做复杂企业后台。
风险提醒:
不要一开始做成大而全平台,先跑通稳定分发闭环。
下一步:
进入 PRD。
What ships with it
5 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 · 233 lines · 110 tokens per session scan A f907944342eb
ai-opportunity-evaluation is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 110 tokens to every session and 2,016 once invoked, about $0.0006 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…