Not in the top 1,000 by GitHub stars

derrickgong87/product-idea-excavator

Open-source bilingual Claude Skill for product discovery interviews and high-quality PRDs.

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

product-idea-excavator/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

08aff4088d82 → 08aff4088d82

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 08aff4088d82

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 08aff4088d821096e1702930086c666d56110820

git clone --filter=blob:none --no-checkout https://github.com/derrickgong87/product-idea-excavator.git .hotskills/derrickgong87-product-idea-excavator && git -C .hotskills/derrickgong87-product-idea-excavator checkout --detach 08aff4088d821096e1702930086c666d56110820 # Copy each selected skill directory from .hotskills/derrickgong87-product-idea-excavator into .agents/skills/<skill-name>/
29GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days

Heat

0.3
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Oct 25, 202629

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

product-idea-excavator

When your agent uses it

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.

What it loads into context

Frontmatter

153 tokens

Always available to the agent

SKILL.md

4,486 tokens

When the skill is activated

Reference documents

13,366 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Language Mode
  2. English Role Summary
  3. 你的角色
  4. 和普通 Plan Mode 的区别
  5. 核心循环
  6. 主动提问规则
  7. 诊断强度
  8. 六个强制诊断问题
  9. 前提挑战
  10. 替代方案生成
  11. 用户想法不成熟时
  12. 不要卡在单点
  13. 访谈地图
  14. 必须覆盖的产品发现模块
  15. 质量闸门
  16. 何时生成 PRD
  17. PRD 输出合同
  18. 技术建议原则
  19. 参考资料使用
  20. 输出风格

Files

  • README.mddoc1,710 bytes
  • SKILL.mdcore17,808 bytes
  • demo/sample-run.mddoc7,712 bytes
  • evals/evals.jsonasset3,440 bytes
  • references/ai-product-playbook.mddoc2,504 bytes
  • references/discovery-question-bank.mddoc3,692 bytes
  • references/en/ai-product-playbook.mddoc2,003 bytes
  • references/en/discovery-question-bank.mddoc3,449 bytes
  • references/en/example-interviews.mddoc1,957 bytes
  • references/en/prd-template.mddoc5,320 bytes
  • references/en/product-sense-playbook.mddoc3,621 bytes
  • references/en/tech-stack-playbook.mddoc3,168 bytes
  • references/example-interviews.mddoc2,056 bytes
  • references/prd-template.mddoc5,408 bytes
  • references/product-sense-playbook.mddoc5,928 bytes
  • references/tech-stack-playbook.mddoc4,427 bytes
Read SKILL.md

# 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
View the complete source on GitHub

Skills included

  • product-idea-excavator

Repository facts

License
MIT
Created
Apr 28, 2026
Last pushed
Apr 28, 2026
Forks
3
Open issues
1
Project activity
Slowing

Before you install

Instructions only

Automated signals, not a guarantee

Checked Nov 7, 2026

  • No broad tool permissions
  • No dangerous shell commands
  • No network access
  • No hidden or obfuscated text
  • No instruction overrides
  • No executable scripts
  • No access to secrets
  • No requests to vote in Hot

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

No combined signals at this commit.

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md product-idea-excavator/SKILL.md.claude/skills/<skill-name>/
CodexNativeManifest AGENTS.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md product-idea-excavator/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md product-idea-excavator/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md product-idea-excavator/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md product-idea-excavator/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.