Claude Code skillEdge Copilot
Edge Copilot
A Claude Code skill you call with /edge. It reads the session you're in and checks it against everything I've written.
- Why I built it
- Every /edge call was starting from scratch, with no sense of what I'd written or built. I wanted it to have memory.
- What it does
- Answers from the Corpus, sends a daily digest of takes on what you built and flags when I have a take on what you're doing now.
Claude Code skillFree
GTM engineer starter kit
The six Claude Code skills I run on every engagement, free on GitHub.
- Why I built it
- It's the starting point for go-to-market engineering the way I do it, from my Sculpt talk on October 8.
- What it does
- A shared knowledge folder, a data auditor, an account dossier builder, won/lost analysis and an evidence packet builder, with a worked example to run first.
Claude Code skillEdge Copilot
AutoClaygent
A Claude Code tool that builds production-ready Claygents for Clay, plus the course that teaches the method.
- Why I built it
- Building one by hand takes days of trial and error. Most Claygents fail from too many tasks, too little context and no testing loop.
- What it does
- Asks you questions, checks Clay's native integrations first, tests against real data and scores with a 7-criterion rubric until the output is right.
Claude Code skillEdge Copilot
Technology Finder
Finds confirmed customers of a technology, each with a URL you can click.
- Why I built it
- A client needed every company using a specific warehouse management system. BuiltWith, G2 and job posts only gave me a guess.
- What it does
- Fingerprints how a product shows up in DNS, certificates, headers and login pages, then scans for that fingerprint.
Claude Code skillEdge Copilot
Video List Extractor
Turns a screen recording of a list into clean rows.
- Why I built it
- A conference app had 597 attendees and no API, no export and no HTML. Just pixels.
- What it does
- Crops each row into its own image and reads them one at a time. Whole-frame reading got about 58% right; row by row got 99%.
Claude Code skillEdge Copilot
PDF Contact Finder
Pulls every contact row out of directory PDFs.
- Why I built it
- Government and industry PDFs, like a 798-page state fire department directory, are a TAM list nobody extracts.
- What it does
- Reads the text layer for free when it exists and crops rows only when it doesn't. Two directories gave 5,080 raw records at zero model cost.
Claude Code skillEdge Copilot
TAM Research
Builds a market list from public sources instead of a bought list.
- Why I built it
- A software company had bought lists for two years. Reps kept seeing the same companies, and their best customers were never on them.
- What it does
- Searches registries, licensing boards and trade associations for the vertical. One landscaping run surfaced 38 sources.
Claude Code skillEdge Copilot
Dossier Builder
One sorted timeline per account across CRM, calls, billing, product and support.
- Why I built it
- In one client's data, the field joining call recordings to accounts was wrong on 42.6% of records, and nobody noticed for weeks.
- What it does
- Stitches every system together and trusts what customers did first, what they said second and what the CRM says third.
Claude Code skillEdge Copilot
Win-Loss Rewind
Reads churned or lost accounts against clear hypotheses, using public evidence.
- Why I built it
- A CRO wanted to know before a board meeting whether any of their churn could have been seen coming.
- What it does
- Checks each account in parallel and writes structured findings. On 1,200 churned accounts, 19% were never the right kind of operator.
Claude Code skillEdge Copilot
Talent Sourcer
Searches every plausible company for candidates instead of sampling a few.
- Why I built it
- A Series B healthcare AI company needed its next SDR leader and wanted real candidates, not an agency shortlist.
- What it does
- Pulls every plausible person from every company in the filter, scores them and returns a ranked sheet with contact details.
Claude Code skillEdge Copilot
Triple Deep Research
Runs one research question through ChatGPT, Claude and Gemini at the same time.
- Why I built it
- Reading three deep research reports and checking every citation takes half a day by hand.
- What it does
- Checks every cited link, then leads with the claims only one engine found that survived the check.
Claude Code skillEdge Copilot
TAM Contact Harvester
Finds a named contact for every company website in a market.
- Why I built it
- Contact tools charge per domain, so the bill grows with the market, even though most of it sits in plain HTML.
- What it does
- Sorts sites into free and paid buckets before spending anything. Two markets, 650 sites, no paid lookups.
Claude Code skillEdge Copilot
Domain & LinkedIn Finder
Matches company names to their domains at scale.
- Why I built it
- Vendors charge by the row, so the bill grows with the list, for something the internet already knows.
- What it does
- Free sources first, a cheap search next, a model only on ambiguous names, and every domain checked against what the site says.
Claude Code skillEdge Copilot
Crawford
A Claude Code research skill built for right answers per dollar.
- Why I built it
- Three well-funded research tools all gave me a parked domain as a fire department's official website.
- What it does
- Uses free data first and verifies twice. Its proving run got 34 of 39 hand-checked rows right.
Claude Code skillEdge Copilot
Speaker Finder
Finds the best speaker for your event in any city.
- Why I built it
- GTMshift needed one more panelist for its Austin event after a speaker couldn't make the date.
- What it does
- Interviews you about the goal and audience, searches people data, stages, podcasts and your own network, then ranks finalists with a source behind every claim.
Claude Code skill
Rep Review
Turns five CRM exports into a Google Doc that grades every rep.
- Why I built it
- A real team's data disproved the number my first version led with: leads contacted the same day won at the same rate as leads first contacted a week later.
- What it does
- Follows each lead to its deal, compares reps inside one lead source and prices one coaching fix per rep in dollars.