By medscout-gtm
Build qualification frameworks for B2B sales through guided interviews, extracting tacit judgment from contact profiles and distilling voice-to-text brain dumps into precise documentation for account targeting
Build a contact qualification framework through guided profile review — extract tacit judgment about which contacts are worth pursuing, then organize it into documented criteria with persona classification and fit assessment.
Enables thought partnership for sharpening thinking and articulation. Invoked when user needs help distilling fuzzy concepts, brain dumps, or voice-to-text into sharp, documented clarity.
Interview someone to clarify fuzzy thinking — sharpens voice-to-text brain dumps into precise articulation through synthesis and friction. Used by facilitation workflows.
Build a target account playbook through staged interviews — company context, fit analysis against real customers, optional rep walkthrough, and framework generation. Produces a qualification framework the team can use to decide which accounts are worth pursuing.
Your team already knows what good looks like — which accounts to pursue, which contacts matter, what signals mean someone's ready to buy. The problem is that knowledge lives in your best people's heads: never written down, never pressure-tested, never turned into something the rest of the team can use.
These skills pull that knowledge out through conversation, organize it into documented frameworks, and give you something you can actually hand to a rep, load into an agent, or build a workflow around.
Built by the MedScout team. Part of the Stage 2 Capital GTM AI How To series.
claude plugin marketplace add medscout-gtm/gtm-skills
claude plugin install gtm-skills
Codex support coming soon.
Each of these walks you through building a specific piece of your GTM playbook. They run as guided conversations — you talk through what you know, react to real examples, and end up with a documented framework.
| Skill | What it does | Time |
|---|---|---|
| Target Account Playbook | Build a qualification framework for which accounts to pursue. Walk through good-fit and poor-fit customers, surface the attributes and signals that actually predict success, organize them by when they become assessable. | 90–120 min |
| Contact Qualification Framework | Build qualification criteria for which people at target accounts are worth pursuing. Review real LinkedIn profiles, extract your judgment about what makes someone a fit, produce documented persona classification and fit assessment. | 60–90 min |
The domain skills are built on two general-purpose tools that you can also use directly.
| Skill | What it does |
|---|---|
| Interview Me | Guided conversation that turns fuzzy thinking into sharp articulation. Handles voice-to-text brain dumps, half-formed ideas, implicit knowledge that hasn't been written down. |
| Crystallization | Takes rough material and sharpens it through iterative rounds — reflect back what you heard, push on what's vague, tighten until it's precise. The methodology underneath Interview Me, also useful on its own for tightening a draft or plan. |
Every domain skill follows the same pattern: an interview that extracts what you know, then a generation step that organizes it into a framework you react to and refine. At the end, a validation pass pressure-tests the result — where would this give you the wrong answer? Which criteria are you least confident in? What would trip up someone using this without your judgment behind it?
You end up with one document you can share with your team, plus a record of how your thinking evolved during the session — useful context when you revisit the framework later.
Voice-to-text works best. The interview mechanics are built for brain-dump-style input. Typing works, but dictation (Wispr Flow, Monologue, or the built-in mic) is faster and usually produces richer material.
The tools you use to qualify accounts, find contacts, and prioritize outreach will change. The models will change. The specific workflow — whether it's Clay or Apollo or something that doesn't exist yet — will change.
What doesn't change is your judgment about what matters for your business. Which accounts are actually a fit. Which people at those accounts would drive an evaluation. What signals tell you someone is ready to buy versus just browsing.
That judgment is the input that makes everything else work. Without it, AI tools generate noise at scale. With it, they apply your best thinking consistently across every account and every contact.
These skills exist to help you get that judgment out of your head and into a form you can use.
Open Claude Code and describe what you want to do:
Claude picks the right skill based on the description.
The skills adapt to whatever you bring, but having a few things ready avoids interruptions:
Issues and improvements welcome — open a PR or issue on this repo.
MIT.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub medscout-gtm/gtm-skills --plugin gtm-skillsA growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.