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 konglong87/superPM --skill pm-business-modelgit clone --depth 1 https://github.com/konglong87/superPMWrote 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/konglong87/superpm/pm-business-model)<a href="https://agentmods.dev/skills/konglong87/superpm/pm-business-model"><img src="https://agentmods.dev/badge/skills/konglong87/superpm/pm-business-model/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/konglong87/superpm/pm-business-model"><img src="https://agentmods.dev/badge/skills/konglong87/superpm/pm-business-model.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.04414 |
| Opus 5 | $0.00026 | $0.02207 |
| Sonnet 5 | $0.00011 | $0.00883 |
| Haiku 4.5 | $0.00005 | $0.00441 |
Grade A, and why
pm-business-model scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 642 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble (run first)
bash "$(dirname "${BASH_SOURCE[0]}")/../../check-update.sh" 2>/dev/null || true
# 创建目录
mkdir -p docs/05-产品战略
# 检查是否有PRD作为输入
if [ -f "docs/02-方案设计/PRD产品需求文档.md" ]; then
echo "✅ 检测到PRD文档,将基于此设计商业模式"
fi
跨 Agent 交互规则
当流程要求与用户交互时:
- 如果当前环境支持 AskUserQuestion,使用 AskUserQuestion(最佳体验)。
- 如果当前环境不支持 AskUserQuestion,必须用普通聊天消息提出同样问题。
- 一次只问一个问题。
- 提问后必须停止当前回合,等待用户回答(STOP and WAIT)。
- 不得在用户回答前生成文档、写入 docs。
- 已有 docs 文件不能替代本轮用户回答。
执行流程
步骤 1: 商业模式画布(9要素)
使用 AskUserQuestion 逐个询问商业模式画布的9个要素:
要素 1: 客户细分(Customer Segments)
使用 AskUserQuestion 询问:
请问您的目标客户是谁?
A) 大众市场(面向所有用户) B) 利基市场(特定细分人群) C) 多边市场(连接多个用户群体) D) 分割市场(多个细分人群) E) 其他(请手动输入)
继续询问:
请详细描述您的核心客户群体(年龄、地域、行为特征等)
要素 2: 价值主张(Value Propositions)
询问:
您的产品为客户解决什么核心问题?提供什么独特价值?
引导用户输入:
- 解决的核心痛点
- 独特的价值点
- 与竞品的差异化
要素 3: 渠道通路(Channels)
询问:
您通过什么渠道触达客户?(可多选)
A) 线上渠道(官网、APP、小程序) B) 社交媒体(微信、抖音、小红书) C) 线下渠道(门店、地推) D) 合作伙伴渠道 E) 其他(请手动输入)
要素 4: 客户关系(Customer Relationships)
询问:
您与客户建立什么样的关系?
A) 自助服务(用户自助完成) B) 专用个人助理(一对一服务) C) 社区运营(用户社群) D) 共同创造(用户参与产品设计) E) 自动化服务(AI客服、智能推荐)
要素 5: 收入来源(Revenue Streams)
询问:
您的产品通过什么方式盈利?(可多选)
A) 销售商品收入 B) 订阅/会员收入 C) 广告收入 D) 交易佣金 E) 数据服务收入 F) 增值服务收入 G) 其他(请手动输入)
要素 6: 核心资源(Key Resources)
询问:
实现商业模式需要哪些核心资源?(可多选)
A) 实体资源(仓库、设备、门店) B) 知识产权(专利、技术、品牌) C) 人力资源(核心技术团队) D) 金融资源(资金、投资) E) 数据资源(用户数据、行为数据)
要素 7: 关键业务(Key Activities)
询问:
需要开展哪些关键业务?(可多选)
A) 产品研发 B) 用户运营 C) 市场营销 D) 供应链管理 E) 客户服务
要素 8: 重要伙伴(Key Partnerships)
询问:
需要哪些重要合作伙伴?(可多选)
A) 供应商 B) 分销渠道 C) 技术服务商 D) 物流合作伙伴 E) 战略投资方
要素 9: 成本结构(Cost Structure)
询问:
主要成本结构是什么?(可多选)
A) 固定成本(租金、人力、设备) B) 变动成本(原材料、物流、营销) C) 规模经济(规模越大成本越低) D) 范围经济(多元化降低成本)
步骤 2: 收入模型设计
根据步骤1的收入来源,设计详细的收入模型:
场景A: 订阅/会员收入
询问:
会员模式设计
A) 单一会员(免费/付费二元) B) 多级会员(基础/标准/高级) C) 分层会员(按功能/按时长) D) 其他(请手动设计)
继续询问会员定价:
会员定价策略
引导用户输入:
- 月费/年费价格
- 不同级别的功能差异
- 定价依据(成本加成/价值定价/竞争定价)
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.
- 10d ago First seen · 642 lines · 53 tokens per session scan A ff76236a76d1
pm-business-model is a skill published in the GitHub repository konglong87/superPM (64 stars, last pushed 6d ago), licensed MIT. It adds 53 tokens to every session and 4,414 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
multi-search
A web-search helper that chooses among DuckDuckGo, Tavily, Bing API, and Bing scraping based on the available network.
digital-avatar-shopping-video
A digital-avatar video maker for product recommendations and promotional sales videos. It creates a spoken presentation by coordinating the script, visuals, and audio-video assembly.
ecommerce-video-marketing
An e-commerce video script generator for platforms such as Douyin and Xiaohongshu. It creates a six-stage script covering a customer pain point, product presentation, and planned camera work.
dream-video-prompt-generator
A prompt generator for Jimeng video, producing prompts in Chinese and English for digital-avatar sales videos. It also creates storyboard scripts for five-second promotional scenes and aims to keep the character and emotion consistent.
ecommerce-copywriter
An e-commerce writing aid for creating or improving marketing text for product images across different product categories. It extracts key selling points and writes emoji-friendly titles and scenario-based descriptions.
infinitetalk-shopping-avatar
A prompt generator for five-scene vertical shopping videos made with InfiniteTalk. It specifies the scenes and helps keep the digital character consistent while matching speech and video.