mcpbeat Sign in

Market Scan Agent Skill

Refresh the founder's competitive and market context. Re-scan named rivals and the category for what changed since the brief was written (rebrands, repositioning, new entrants, pricing shifts, renamed categories) and update docs/gtm-cofounder/founder-brief.md and the roadmap with anything that moves positioning. Use on a cadence, or whenever a competitor rebrands, a new tool appears, or the founder senses the market has shifted under them.

1k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
176
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/AIDevGTM/gtm-cofounder --skill market-scan

The instruction itself

7 sections, as written by the author

Market scan (keep your read current)

> Positioning rots. The competitor you sized up six months ago has since rebranded, raised, repriced, or renamed the category. This is the habit that keeps your brief honest about the world outside it.

Use this when: a rival just rebranded or repositioned, a new tool is getting attention in your space, your docs/gtm-cofounder/founder-brief.md competitor answers are more than a quarter old, or you just have the feeling the ground moved and your messaging is answering last year's market.

The core idea

Your docs/gtm-cofounder/founder-brief.md captured the market as it was the day you wrote it. Markets don't hold still. A scan re-checks the outside world against your brief and surfaces the deltas: what changed, and which changes actually threaten or help your positioning. Most don't matter. The scan's job is to find the two or three that do, not to produce a competitor spreadsheet.

Before you start: can your agent see the web?

  • If your agent can browse or search the web, it runs the scan for real: competitor homepages, changelogs, pricing pages, launch posts, and recent discussion.
  • If it can't, it runs the scan as an interview: it asks what you've noticed and where, and you paste in the pages. Same output, you're the browser. Say which mode you're in up front.

How to run this (for the agent)

  • Start from the brief. Read docs/gtm-cofounder/founder-brief.md: the rivals ("what do they use instead"), the "why you", the villain, and the current positioning line. That's your baseline to compare against.
  • Scan the named rivals first, then the category. For each competitor in the brief, check: homepage headline and positioning, pricing, any rebrand or renamed category, funding or acquisition, and new capabilities that erase the founder's wedge. Then scan for new entrants and category-level shifts (a term everyone suddenly uses, a platform move, an AI or agent shift).
  • Report deltas, not descriptions. Do not summarize each competitor. Say what *changed* since the brief, and for each change, whether it strengthens, threatens, or is irrelevant to the founder's positioning. Rank by "does this move our position."
  • Tie every real change to an action. A rival adopting the founder's language means the wedge is eroding: route to positioning-and-story. A new pricing norm means revisit market-to-devs-sell-to-buyers. A dead competitor means an opening. No action, no reason to flag it.
  • Update the brief and roadmap. Rewrite the affected lines in docs/gtm-cofounder/founder-brief.md (rivals, why-you, villain, positioning) with today's reality and the date, and add any positioning move it triggers to docs/gtm-cofounder/gtm-roadmap.md. Keep the tags honest: a competitor's public claim is [assumption] until you have checked it is real.

What actually matters (and what doesn't)

Changes worth acting on:

  • A rival repositions onto your wedge or adopts your vocabulary. Your differentiation is eroding. Highest priority.
  • A new entrant is getting real traction in your exact lane.
  • The category gets renamed (buyers now search a different term than your copy uses).
  • A pricing norm shifts (a free tier appears or disappears, seat pricing becomes standard).

Noise to ignore:

  • Cosmetic rebrands, new logos, homepage redesigns with the same substance.
  • Feature announcements that don't touch your wedge.
  • Funding rounds that don't change what the product is or who it is for.

Mistakes that look reasonable

  • Reacting to a competitor's launch by copying it. Their move fits their strategy, not yours. Ask what it means for your wedge, not how to match it.
  • Scanning everything, changing nothing. A scan that doesn't update the brief or the roadmap was just anxiety with extra steps.
  • Treating a rival's marketing claim as fact. "Now with X" on a homepage is a positioning bet, not proof it works. Tag it [assumption].
  • Doing it constantly. Monthly, or on a real trigger (a rebrand, a new entrant), is plenty. Daily competitor-watching is procrastination dressed as diligence.

Your next 30 minutes

  • [ ] Tell your agent which mode you're in (it browses, or you paste).
  • [ ] List the rivals from your docs/gtm-cofounder/founder-brief.md. Scan each for a rebrand, repricing, or repositioning since you wrote it.
  • [ ] Write down only the changes that touch your wedge. Ignore the cosmetic ones.
  • [ ] For each real change, mark it strengthens / threatens / irrelevant, and the one action it triggers.
  • [ ] Update the affected lines in docs/gtm-cofounder/founder-brief.md (with the date) and add any positioning move to docs/gtm-cofounder/gtm-roadmap.md.

Built from real dev-tool GTM experience, with frameworks from Adam Frankl (*The Developer-Facing Startup*) and Jakub Czakon (*markepear.dev*).

When a framework can't make the call, that's what a human is for: The DevTool GTM Company.

Other skills for the same job

different authors, same section of the catalogue
Internal Comms
by anthropics
vendor ×13

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

6k tokens
Competitive Ads Extractor
by frostant
×10

Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.

2k tokens
Lead Research Assistant
by frostant
×8

Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.

2k tokens
Developer Growth Analysis
by frostant
×6

Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.

4k tokens
App Store Optimization
by alirezarezvani
×3

Complete App Store Optimization (ASO) toolkit for researching, optimizing, and tracking mobile app performance on Apple App Store and Google Play Store

55k tokens scripts
Deeptools
by christophacham
×3

NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.

21k tokens scripts
Pymatgen
by christophacham
×3

Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science.

26k tokens scripts
Enhance Prompt
by google-labs-code
vendor ×2

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

3k tokens

How to use it

Copy the folder

Take aidevgtm/market-scan from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.