Individual skill
product-idea-excavator
Use this Skill whenever the user wants to explore, sharpen, validate, or turn a product idea, startup idea, AI tool, SaaS, app, platform, internal tool, or feature concept into a high-quality PRD. 必须用于用户想挖掘产品想法、定义 MVP、梳理需求、判断技术落地、做产品经理式访谈或生成 PRD 的场景。It leads a multi-turn product discovery interview, asks the questions first, probes users, demand evidence, current workarounds, wedge, MVP, business model, technical stack, AI/model feasibility, risks, and automatically produces a PRD after the user confirms discovery is complete.
product-idea-excavator/SKILL.md
Source commit 08aff4088d821096e1702930086c666d56110820
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- Yes
- Skill scan complete
- Yes
- Observed behavior
- Not checked yet
- Last checked
- Nov 11, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 29
- Repository last updated
- Apr 28, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai Repository topic
- ai-agents Repository topic
- bilingual Repository topic
- commercial-use Repository topic
- mvp Repository topic
- open-source Repository topic
- prd Repository topic
- product-discovery Repository topic
- product-management Repository topic
- saas Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
README.mddoc · 1,710 bytesSKILL.mdcore · 17,808 bytesdemo/sample-run.mddoc · 7,712 bytesevals/evals.jsonasset · 3,440 bytesreferences/ai-product-playbook.mddoc · 2,504 bytesreferences/discovery-question-bank.mddoc · 3,692 bytesreferences/en/ai-product-playbook.mddoc · 2,003 bytesreferences/en/discovery-question-bank.mddoc · 3,449 bytesreferences/en/example-interviews.mddoc · 1,957 bytesreferences/en/prd-template.mddoc · 5,320 bytesreferences/en/product-sense-playbook.mddoc · 3,621 bytesreferences/en/tech-stack-playbook.mddoc · 3,168 bytesreferences/example-interviews.mddoc · 2,056 bytesreferences/prd-template.mddoc · 5,408 bytesreferences/product-sense-playbook.mddoc · 5,928 bytesreferences/tech-stack-playbook.mddoc · 4,427 bytes
Read excerpt
# Product Idea Excavator
## Language Mode
Mirror the user's language.
- If the user writes in Chinese, respond in Chinese and use the Chinese reference files under `references/`.
- If the user writes in English, respond in English and use the English reference files under `references/en/`.
- If the user mixes languages, use the language they use for the product idea itself.
- Do not mix Chinese and English in user-facing output unless the user asks for bilingual output.
- Keep product terms such as MVP, PRD, SaaS, RAG, API, GTM, and Agent as-is when they are common in the user's language context.
## English Role Summary
