Install
$ agentstack add skill-yu19991110-womenswear-ecommerce-skills-mine-market-demand-signals ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
市场需求信号挖掘
核心目标
先发现需求,再寻找产品。寻找“消费者真实需要、愿意付钱,但现有市场满足不足”的问题,不因销量、搜索量、平台热度、同行销售或达人推荐直接下选品结论。
执行流程
- 明确品类、地域、目标人群、价格带和时间窗口;缺失时采用合理默认并写明。
- 必须联网检索近期公开讨论。默认同时观察最近 7 天、30 天、90 天和 12 个月,以区分突发、近期、持续、季节性和长期信号。
- 按品类选择综合平台、电商评价和垂直社区,重点搜索“抱怨、求推荐、替代、DIY、妥协购买、重复问题、跨品牌共性差评”等行为信号。
- 保存可核验来源、发布时间、原始语义、行为类型和证据强度。事实标为“公开证据”;无法验证的数量、趋势或市场判断标为“推测”。禁止虚构用户、帖子、销量、搜索趋势、市场规模或平台数据。
- 将近义问题聚为底层任务,不把商品名当作需求。例如“猫砂粘脚、带出、满屋散落”聚为“减少猫砂带出与清洁负担”。
- 将需求归为 A 强交易、B 强痛点、C 替代、D 情绪、E 伪需求;E 类必须降权。
- 按参考文件的 100 分模型逐项评分,保留每项证据与不确定性,生成需求机会榜。
- 只在需求成立后提出候选解决方向;不得把模拟结果倒灌为真实需求证据。
组合调用
- 用户只问市场最近有哪些真实需求、痛点或机会:仅执行本技能。
- 用户已给出候选商品,只需要测试购买与价格:跳过本技能,转交
$simulate-synthetic-consumer-market;若缺少真实需求证据,明确标记缺口。 - 用户要求完整选品、开发判断或“一起调用”:先输出
Demand Handoff,再依次调用$simulate-synthetic-consumer-market与$validate-product-opportunity。
Demand Handoff
每个候选机会至少交付:
demand_id、需求陈述、目标人群、使用场景、需求等级 A-E- 证据来源与时间范围、公开证据/推测标签、跨平台重复情况
- 当前方案、未满足点、付费信号、替代或 DIY 行为
- Demand Opportunity Score 九项分数、总分、置信度
- 候选产品概念、可验证差异、建议价格带、关键未知项
输出要求
先给结论,再给证据。至少包含市场扫描、近期问题、需求聚类、机会 TOP 榜、候选方向、证据局限和下一步。涉及精确数量时说明口径;没有可靠样本数时使用定性强弱,不伪造百分比。
完整的信号分类、评分锚点、淘汰条件和报告结构见 [references/demand-research-framework.md](references/demand-research-framework.md)。执行任务前按需读取该文件。
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: yu19991110
- Source: yu19991110/womenswear-ecommerce-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.