Claude Code prompts for competitor research

Teardowns, pricing tracking, feature matrices and screenshots of competitor user flows. Leave a browser running overnight and come back to a full picture of the market.

Show:

20 prompts

  1. Map every competitor

    Find every product that competes with us: direct competitors, indirect ones, open source options, spreadsheets and agencies people use instead. For each, give the URL, one-line positioning, target customer, pricing model, founded year and funding if public, and an estimated size signal. Group them and save to research/competitors.csv with a market map summary in research/competitors.md.

    Web
  2. Scrape competitor user flows

    For our top 3 competitors, use the browser to go through their public flows: homepage, pricing, sign-up and the first screens of onboarding, as far as possible without paying or breaking their terms. Screenshot every step at desktop and mobile size, note the number of steps, fields asked, and the first "aha" moment. Save screenshots to research/flows/[competitor]/ and a side-by-side comparison to research/flows/summary.md.

    Browser
  3. Full teardown of one competitor

    Do a complete teardown of [COMPETITOR]: positioning and messaging, target audience, features, pricing and packaging, onboarding, content and SEO strategy, social presence, reviews (what people love and hate), team and hiring signals, recent changes, and where they are weak. End with 5 ways we can win against them. Save to research/teardowns/[competitor].md.

    Web Browser
  4. Feature comparison matrix

    Build a detailed feature matrix of us vs our top 6 competitors, using their docs, changelogs and pricing pages (cite the source for each cell). Include which plan each feature is on. Highlight features everyone has (table stakes), features only we have, and features we are missing that matter. Save to research/feature-matrix.csv and a summary to research/feature-matrix.md.

    Web Repo
  5. Pricing intelligence

    Collect the current pricing of our top 10 competitors: plans, prices (monthly and annual), what limits each plan, free tiers, trials, and add-ons. Use the Wayback Machine to find their pricing 12 months ago and note what changed. Save to research/pricing.csv and write what the trends suggest for our own pricing in research/pricing.md.

    Web
  6. Competitor messaging analysis

    Capture the homepage headline, subheadline, main CTA, top 3 benefits and social proof for 10 competitors. Lay them out side by side. Find the overused phrases everyone uses, the angles nobody owns, and suggest 3 positioning angles that would make us stand out. Save to research/messaging.md.

    Web
  7. Competitor changelog tracker

    Find the changelog, release notes, blog or product update feed for each of our top 5 competitors. Summarise what each shipped in the last 6 months and what it says about their direction. Then write a script that checks these sources weekly and reports new updates. Save to research/competitor-updates.md and scripts/.

    Web Repo
  8. Competitor SEO strategy

    For our top 3 competitors, work out their SEO strategy from public signals: sitemap sizes and sections, programmatic page patterns, blog topics and frequency, free tools, and which pages appear for our main keywords. List what we should copy, what we should ignore, and the gaps. Save to research/competitor-seo.md.

    Web
  9. Competitor review mining

    Read 200+ public reviews of our top 3 competitors. Tally the most praised features, the most common complaints, and the reasons people switched to or away from each. Pull 30 representative quotes. Give me the 5 complaints we can turn into our marketing message. Save to research/competitor-reviews.md.

    Web
  10. Competitor email and onboarding capture

    Plan how to sign up for competitor free trials with a test inbox to capture their onboarding emails over 2 weeks. For any competitor where I have already done this, read the emails in research/emails/ and break down the sequence: timing, subject lines, goals of each email, and what we should borrow. Save to research/competitor-emails.md.

  11. Tech stack of competitors

    Find out what our competitors are built with from public signals: page source, headers, JS bundles, job posts, engineering blogs, open source repos. Note front-end, back-end, hosting, analytics, payments and AI providers. Point out anything that suggests their cost structure or limits. Save to research/competitor-stacks.md.

    Web
  12. Competitor hiring signals

    Look at the open jobs of our top 5 competitors. What teams are they growing, what new markets or products do the job posts hint at, and what tech are they adopting? Save a short brief per competitor to research/competitor-hiring.md.

    Web
  13. Competitor social and community

    For each top competitor, review their social accounts, community (Discord, Slack, forum), and founder presence. Note follower counts, posting frequency, what content gets engagement, and how they treat their community. Pick 3 things worth copying. Save to research/competitor-social.md.

    Web
  14. Battle cards

    Write a one-page battle card for each of our top 5 competitors: when we win, when we lose, their strengths, their weaknesses, landmines to set in a sales call (questions that expose their gaps), how to answer "why not [competitor]?", and pricing comparison. Base it on research/ findings. Save to sales/battle-cards/.

    Web
  15. Open source alternatives

    Find every open source project that does what we do, even partly. For each, list stars, activity, licence, maintainers, and what users complain about in issues. Decide whether each is a threat, a source of leads (people who want hosted), or a possible integration. Save to research/oss-alternatives.md.

    Web
  16. Adjacent markets scan

    Find 10 products in adjacent categories that could add our feature and become competitors, or that we could expand into. For each explain the overlap, their user base, and the signals that they are moving toward us. Save to research/adjacent.md.

    Web
  17. Competitor ad copy

    Find the ads our competitors run, using public ad libraries (Meta Ad Library, LinkedIn Ad Library, Google Ads Transparency Center). Capture the copy, creative format and landing pages. Summarise the angles they test and how long ads have been running (long-running ads usually work). Save to research/competitor-ads.md.

    Web Browser
  18. Competitor landing page screenshots

    Take full-page screenshots of the homepage, pricing page and top 3 landing pages of 8 competitors at desktop and mobile width. Save them to research/screenshots/ with a date in the filename, and write a short note on any layout or design ideas worth borrowing.

    Browser
  19. Where competitors get traffic

    Using public signals (their content, social accounts, communities, directories they appear in, newsletters that mention them, partner pages), estimate where each top competitor gets its traffic and customers. Find 10 channels they use that we do not. Save to research/competitor-channels.md.

    Web
  20. Quarterly market report

    Write a quarterly market report on our category: major launches, funding, pricing changes, acquisitions, notable shutdowns, trends in what customers ask for, and what it means for our roadmap. Use research/ files plus fresh web research. Save to research/market-[quarter].md.

    Web

How to run these while you sleep

  1. Open your project and start a fresh branch or git worktree, so the whole night is one diff you can review or delete.
  2. Add your product context above and keep overnight mode on. Claude will log its assumptions instead of waiting for answers.
  3. Paste one prompt into Claude Code, or save a few to a queue/ folder and loop over them headless.
  4. In the morning, read the files it wrote and the diff. Merge what is good and send what needs sending yourself.

Want it off your laptop? Claude Code on the web runs each session in a cloud sandbox, so you can start a few before bed and close the lid.

Queue a night of prompts

git switch -c overnight/$(date +%F)
mkdir -p logs
for f in queue/*.md; do
  claude -p "$(cat "$f")" \
    --permission-mode acceptEdits \
    --allowedTools "WebSearch" "WebFetch" "Bash(npm run *)" \
    > "logs/$(basename "$f" .md).log"
done

Only allow the tools a task needs. Browser prompts also need a browser MCP server such as Playwright; find one in the MCP directory.

More spare compute prompts

Link magnets20

Free tools, calculators, templates and data pages that rank for long-tail searches and earn links on their own. Run these overnight and wake up to shippable pages.

SEO & content20

Keyword research, content briefs, technical SEO audits and article drafts you can leave running overnight. Each prompt saves its output to a file so nothing gets lost.

Backlinks & PR20

Find link opportunities, draft pitches and build lists of podcasts, newsletters and journalists. These prompts do the slow research so you only do the sending.

Directories & launches15

Get listed everywhere your buyers look: startup directories, app stores, marketplaces, launch sites and review platforms. Claude prepares every listing so submitting takes minutes.

Finding customers20

Lead lists, buying signals and the places your next customers are already asking for help. Claude does the digging; you decide who to contact.

Outreach & sales15

Cold emails, follow-ups, sales pages and objection handling written from what your product actually does. Claude drafts; you review and send.

Social content20

A month of posts, threads, carousels and replies drafted from your product, changelog and lessons learned. Wake up to a content queue instead of a blank page.

Video & visuals15

Demo videos, short-form scripts, animated explainers and screenshots generated with code. Use Remotion, Playwright and ffmpeg to render while you sleep.

Simulated user research20

Synthetic personas, simulated usability tests and interview prep built from your real product. Use them to find obvious problems before you spend time with real users, not instead of them.

Landing pages & conversion20

Rewrite copy, audit the sign-up funnel, design A/B tests and build new landing pages. These prompts work directly in your codebase so the output is ready to review as a pull request.

Email & lifecycle15

Welcome sequences, onboarding emails, newsletters and re-engagement campaigns written from your actual product, plus the templates to send them.

Product & UX20

Polish passes, onboarding fixes, feature specs and prototypes. Good for overnight runs because each one ends in a branch or a document you can review over coffee.

Code quality20

Tests, refactors, type safety, dependency upgrades and dead code removal. The classic overnight job: long, careful, and easy to review in the morning as a pull request.

Security & performance20

Security reviews, secrets scans, load tests, bundle diets and backup checks. The work everyone puts off, done while your machine would otherwise sit idle.

Docs, support & ops20

Documentation, help centre articles, support macros, metrics, finance tidy-ups and the admin that piles up. Hand it to Claude when you have compute to spare.

Make Claude better at these jobs with skills, MCP servers and mods, or turn a prompt you run often into a skill with the skill generator.