competitor-scan — Claude Code skill: what it does, how to install
competitor-scan guides your agent to research market-leading interfaces using Browser MCP screenshots and web teardowns before coding.
MIT 1 installs ★ 353 updated 2026-10-28
npx skills add WellApp-ai/Well --skill competitor-scan -a claude-codeWhat competitor-scan does
The skill structures competitive product research into four clear phases. It begins by identifying benchmark products across domains, such as Notion and Linear for workspaces or Stripe and Plaid for user onboarding. Next, the agent uses Browser MCP commands to open product pages, record snapshots, capture screenshots, and step through interactive flows.
The research then switches to WebSearch queries targeting UI breakdowns and UX case studies. Everything converges into a structured Markdown summary detailing layout choices, navigation models, actions, feedback states, and UI copy.
Without an active Browser MCP setup and WebSearch access in your agent environment, the skill cannot navigate live sites or pull external teardowns.
What it helps with
- capture screenshots of key user flows and edge cases from top apps
- audit layout structures and navigation patterns across competitors
- pull UX case studies and feature teardowns before designing a new flow
- compile a structured design insights table during the DIVERGE loop phase
Example prompts for the agent
- use competitor-scan skill to audit billing and subscription flows in Stripe and Paddle
- Run competitor-scan to analyze team invitation flows across Slack and Linear
- Execute competitor-scan skill for chat interface patterns based on Claude and Perplexity
How to install competitor-scan
1Skills CLI (Vercel)
npx skills add WellApp-ai/Well --skill competitor-scan -a claude-code2Manually: put the files in place
~/.claude/skills/competitor-scan/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/competitor-scan/
1Skills CLI (Vercel)
npx skills add WellApp-ai/Well --skill competitor-scan -a codex2Manually: put the files in place
.agents/skills/competitor-scan/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add WellApp-ai/Well --skill competitor-scan -a cursor2Manually: put the files in place
.cursor/skills/competitor-scan/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install WellApp-ai/Well cursor-rules/skills/competitor-scan2Manually: put the files in place
.github/skills/competitor-scan/SKILL.md1Skills CLI (Vercel)
npx skills add WellApp-ai/Well --skill competitor-scan -a gemini-cli2Platform CLI
gemini skills install https://github.com/WellApp-ai/Well --path cursor-rules/skills/competitor-scanManually: put the files in place
.devin/skills/competitor-scan/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add WellApp-ai/Well --skill competitor-scan -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about competitor-scan
How to install competitor-scan in Claude Code?
Run npx skills add WellApp-ai/Well --skill competitor-scan -a claude-code. The skill file will be placed at ~/.claude/skills/competitor-scan/SKILL.md.
What does competitor-scan do?
It provides a step-by-step workflow for the agent to benchmark competing products, take screenshots via browser automation, search for UX teardowns, and generate an actionable design matrix.
Which agent tools are needed to use this skill?
The workflow relies on Browser MCP actions (browser_navigate, browser_snapshot, browser_take_screenshot, browser_click, browser_type) alongside a working WebSearch tool.
Source text
SKILL.md · MIT
--- name: competitor-scan description: Research best-in-class products using Browser MCP and WebSearch --- # Competitor Scan Skill Research how best-in-class products solve similar problems using Browser MCP for screenshots and WebSearch for teardowns. ## When to Use - At the start of DIVERGE Loop (L1) - When exploring new UI patterns - When benchmarking against industry standards ## Instructions ### Phase 1: Identify Competitors Use the domain competitor table: | Domain | Products to Study | |--------|-------------------| | Workspaces/Collaboration | Notion, Linear, Slack, Figma, Attio | | Data Tables | Airtable, Retool, Rows, Grist | | AI Chat | ChatGPT, Claude, Gemini, Perplexity | | Onboarding/Flows | Stripe, Plaid, Mercury, Ramp | | Settings/Admin | Vercel, Railway, PlanetScale | | Invitations/Team | Slack, Notion, Linear, Figma | | Billing/Subscriptions | Stripe, Paddle, Chargebee | ### Phase 2: Screenshot Key Flows (Browser MCP) For each relevant competitor: ``` 1. browser_navigate to the product URL or relevant page 2. browser_snapshot to understand the page structure 3. browser_take_screenshot to capture the UI 4. browser_click / browser_type to navigate through flows ``` **Capture:** - Entry points (how users start the flow) - Key screens (main interactions) - Edge cases (empty states, errors) - Micro-interactions (hover states, transitions) ### Phase 3: Research Teardowns (WebSearch) Search for existing analysis: ``` WebSearch "[Product] UI teardown [feature]" WebSearch "[Product] UX case study [feature]" WebSearch "[Feature] best practices design patterns" ``` ### Phase 4: Extract Patterns For each competitor, note: | Aspect | Pattern | |--------|---------| | **Layout** | How is content organized? | | **Navigation** | How do users move between states? | | **Actions** | How are primary/secondary actions presented? | | **Feedback** | How is success/error communicated? | | **Copy** | What language/tone is used? | ## Output Format After running this skill, output: ```markdown ## Competitor Scan ### Products Analyzed 1. [Product A] - [URL or feature] 2. [Product B] - [URL or feature] 3. [Product C] - [URL or feature] ### Key Patterns Observed | Pattern | Product | Description | |---------|---------|-------------| | [Pattern] | [Product] | [How they do it] | ### Insights for Our Design - [Insight 1]: [How to apply] - [Insight 2]: [How to apply] ### Screenshots Captured - [Description of screenshot 1] - [Description of screenshot 2] ``` ## Invocation Invoke manually with "use competitor-scan skill" or follow Ask mode DIVERGE loop which references this skill's phases. ## Related Skills - `problem-framing` - Define what problem to research - `design-context` - Compare external patterns with internal
© WellApp-ai · MIT · WellApp-ai/Well