product-discovery
Expert product discovery guidance for user research and problem validation. Use when conducting user interviews, validating problems, applying jobs-to-be-done framework, sizing opportunities, customer segmentation, competitive analysis, prototype testing, usability testing, designing surveys, or synthesizing research insights. Covers discovery sprints, continuous discovery, and research operations.
- Installs
- 170
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/ncklrs/startup-os-skills --skill product-discovery- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads product-discovery automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Product Discovery
Strategic user research and problem validation expertise — from interview techniques and JTBD to opportunity sizing and insight synthesis.
Philosophy
Great products start with great problems. Discovery is how you find problems worth solving for people who will pay.
The best product discovery:
- Talk to users, not stakeholders — Customers know their problems, not solutions
- Validate problems before solutions — Build the right thing, then build it right
- Quantify and qualify — Numbers tell you what, conversations tell you why
- Continuous over batched — Weekly habits beat quarterly projects
How This Skill Works
When invoked, apply the guidelines in rules/ organized by:
research-*— User interview techniques, survey design, research opsdiscovery-*— Problem discovery, JTBD framework, validationanalysis-*— Synthesis, segmentation, competitive analysistesting-*— Prototype testing, usability testing
Core Frameworks
Discovery Process
| Phase | Activities | Outputs |
|---|---|---|
| Explore | Interviews, observation, data mining | Problem space map |
| Validate | Problem interviews, surveys, experiments | Validated problems |
| Prioritize | Opportunity scoring, segmentation | Prioritized roadmap |
| Test | Prototype testing, usability studies | Solution validation |
Jobs-to-be-Done Framework
┌─────────────────────┐
│ FUNCTIONAL JOB │
│ (What they do) │
└──────────┬──────────┘
│
┌────────────────┼────────────────┐
│ │ │
▼ ▼ ▼
┌──────────┐ ┌──────────┐ ┌──────────┐
│ EMOTIONAL│ │ SOCIAL │ │ CONTEXT │
│ JOB │ │ JOB │ │ (When/ │
│ (Feel) │ │ (Appear) │ │ Where) │
└──────────┘ └──────────┘ └──────────┘
Opportunity Scoring (OST)
| Factor | Weight | Description |
|---|---|---|
| Importance | 40% | How important is this job to the customer? |
| Satisfaction | 30% | How satisfied are they with current solutions? |
| Frequency | 20% | How often do they encounter this problem? |
| Willingness to Pay | 10% | Will they pay to solve this? |
Opportunity Score = Importance + max(Importance - Satisfaction, 0)
Research Method Selection
┌─────────────────────────────────────────────────────────────┐
│ GENERATIVE RESEARCH │
│ (Discover unknown unknowns) │
│ ┌───────────┐ ┌───────────┐ ┌───────────┐ │
│ │Contextual │ │ Discovery │ │ Diary │ │
│ │ Inquiry │ │ Interviews│ │ Studies │ │
│ └───────────┘ └───────────┘ └───────────┘ │
├─────────────────────────────────────────────────────────────┤
│ EVALUATIVE RESEARCH │
│ (Validate known hypotheses) │
│ ┌───────────┐ ┌───────────┐ ┌───────────┐ │
│ │ Usability │ │ A/B │ │ Prototype │ │
│ │ Testing │ │ Testing │ │ Testing │ │
│ └───────────┘ └───────────┘ └───────────┘ │
├─────────────────────────────────────────────────────────────┤
│ QUANTITATIVE RESEARCH │
│ (Measure and prioritize) │
│ ┌───────────┐ ┌───────────┐ ┌───────────┐ │
│ │ Surveys │ │ Analytics │ │ Card │ │
│ │ │ │ Review │ │ Sorting │ │
│ └───────────┘ └───────────┘ └───────────┘ │
└─────────────────────────────────────────────────────────────┘
Customer Segmentation Matrix
| Dimension | Consumer (B2C) | Business (B2B) |
|---|---|---|
| Demographics | Age, income, location | Company size, industry, revenue |
| Behavior | Usage patterns, purchase history | Buying process, tech stack |
| Psychographics | Values, lifestyle, attitudes | Company culture, risk tolerance |
| Needs | Problems, goals, aspirations | Business outcomes, KPIs |
Continuous Discovery Cadence
Weekly:
├── 2-3 customer interviews
├── Review analytics/feedback
└── Update opportunity backlog
Monthly:
├── Synthesis session
├── Prioritization review
└── Stakeholder alignment
Quarterly:
├── Deep-dive research sprint
├── Competitive analysis refresh
└── Segment review
Interview Quick Reference
| Interview Type | When to Use | Key Questions |
|---|---|---|
| Discovery | Exploring problem space | "Tell me about the last time..." |
| Problem | Validating specific pain | "How painful is this 1-10? Why?" |
| Solution | Testing concepts | "Would this solve your problem?" |
| JTBD | Understanding motivation | "What were you trying to accomplish?" |
| Usability | Testing interfaces | "What do you expect to happen?" |
Anti-Patterns
- Solution-first discovery — Falling in love with solutions before validating problems
- Leading the witness — Asking questions that suggest desired answers
- Confirmation bias — Only hearing what supports your hypothesis
- Sample of one — Making decisions from a single interview
- Proxy research — Asking salespeople instead of customers
- Feature requests as research — Users ask for features, not problems
- Analysis paralysis — Researching forever, never deciding
- HiPPO-driven — Highest Paid Person's Opinion overriding data
FAQ
What does the product-discovery skill do?
Expert product discovery guidance for user research and problem validation. Use when conducting user interviews, validating problems, applying jobs-to-be-done framework, sizing opportunities, customer segmentation, competitive analysis, prototype testing, usability testing, designing surveys, or synthesizing research insights. Covers discovery sprints, continuous discovery, and research operations.
How do I install product-discovery?
Run npx skills add https://github.com/ncklrs/startup-os-skills --skill product-discovery in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/product-discovery/ (personal) or .claude/skills/product-discovery/ (project).
Which AI agents can use product-discovery?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is product-discovery safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains product-discovery?
It is published by ncklrs in ncklrs/startup-os-skills. It has 170 recorded installs.
More from ncklrs/startup-os-skills
community-builder
ncklrs/startup-os-skills
Expert community-led growth and community management guidance. Use when building developer communities, Discord/Slack communities, online communities, managing community platforms, designing member onboarding, creating engagement programs, running ambassador programs, measuring community health, setting up moderation systems, or implementing DevRel strategies. Use for community-led growth, member activation, user-generated content programs, and community governance.
proposal-writer
ncklrs/startup-os-skills
Expert sales proposal and pricing presentation strategist. Use when writing proposals, executive summaries, ROI business cases, pricing presentations, SOWs (Statement of Work), RFP responses, or competitive positioning documents. Covers proposal structure, terms positioning, design formatting, follow-up strategy, and win-rate optimization.
motion-designer
ncklrs/startup-os-skills
Advanced motion designer with decades of After Effects and motion graphics experience, specialized in creating engaging video specifications for Remotion. Use when creating video specs, planning motion graphics, designing animations, or when asked to "create a video", "design motion graphics", "plan video content", or "spec out a video". Produces detailed scene-by-scene specifications with timing, audio, sound effects, and animation descriptions.
website-copy-specialist
ncklrs/startup-os-skills
Expert website copywriting for SaaS and B2B companies. Use when writing homepage copy, feature pages, about pages, pricing pages, comparison pages, product tours, integration pages, use case pages, demo/contact pages, or navigation microcopy. Use for website messaging hierarchy, value proposition development, and page-level conversion optimization.
vsl-storyboard-writer
ncklrs/startup-os-skills
Open the skill to read its SKILL.md instructions.
remotion-animation
ncklrs/startup-os-skills
Generates animation configurations for Remotion including spring configs, interpolations, easing functions, and timing logic. Focuses ONLY on animation parameters, NOT component implementation. Use when defining animation behavior or when asked to "configure animations", "setup spring configs", "define easing curves".
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；/page/ 是妙搭应用，非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。