Big Idea

The argument in one line.

Priming Claude Code with a pre-context folder of meeting transcripts, project scope documents, and stakeholder research before running the GSD framework cuts project execution time in half by giving the AI all necessary context on first run.

Who This Is For

Read if. Skip if.

READ IF YOU ARE…

A solopreneur or small team builder who uses Claude Code for projects and wants to ship 2-3x faster by structuring research before running GSD.
Someone who's tried GSD cold, felt it was slow or repetitive, and suspects better pre-context would unlock speed but doesn't know how to assemble it.
A developer or builder with scattered project intel (meeting notes, docs, requirements) who wants a systematic way to synthesize it into a single primer Claude can ingest on first run.

SKIP IF…

You're not using Claude Code or the GSD framework yet — this assumes you already run GSD and want to optimize it, not learn GSD from scratch.
You work in domains where pre-context is minimal or fast-moving (e.g., real-time bug fixes, ad-hoc consulting) — the priming payoff shrinks when project scope shifts mid-execution.
You're already shipping at the speed you want and don't have a backlog of half-finished Claude projects — this solves a specific pain point, not a universal one.

TL;DR

The full version, fast.

Running Claude Code's GSD (Get Shit Done) framework cold leaves speed on the table; priming it with a structured pre-context folder cuts project time roughly in half. Before invoking /GSD new project, build a project_research directory with three subfolders�discussions, project_scope, and stakeholders�and populate them using MCP servers: TLDV to pull meeting transcripts straight from your notetaker, and Apify to scrape stakeholder LinkedIn profiles, the client's site, and competitor pages. Drop proposals, pitch decks, and scope docs into project_scope manually. Then ask Claude to synthesize the whole folder into a single pre-context markdown file, and reference it when GSD starts asking onboarding questions. The shift is mindset: stop relying on the AI to discover the project and start acting as the architect who hands it a briefed workspace.

Free for members

Chat with this breakdown — free.

Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.

Create a free account →

Chapters

Where the time goes.

00:00 – 01:16

01 · Cold open — social proof + problem statement

GSD results are real but he went in cold; priming with research made projects go faster. Promise: build a pre-context file that turns your workspace into an execution machine.

01:17 – 04:51

02 · GSD overview — what it does and why cold-start is the gap

Shows the GSD GitHub repo, explains --dangerously-skip-permissions, walks through PRD + Technical State -> phases -> execute phase flow.

04:52 – 06:33

03 · The pre-context framework — three inputs, one primer

Whiteboard diagram: People, Project_Scope, and Discussions feed Context_Markup -> GSD. Visual proof the three folders directly prime the context window.

06:34 – 07:51

04 · Project folder setup — Claude Code + MCPs installed

Inside Cursor on WSL, /init generates CLAUDE.md, TLDV and Apify MCPs installed. Creates project_research/ with discussions/, project_scope/, stakeholders/ subfolders.

07:52 – 13:11

05 · Discussions — TLDV MCP live demo

Live: Claude uses TLDV MCP to pull a weekly call transcript and write it as a markdown file into discussions/. Manual fallback shown.

13:12 – 16:11

06 · Stakeholders — Apify LinkedIn scraper live demo

Apify MCP scrapes a LinkedIn public profile and saves it as a stakeholder markdown. Competitor research via Apify also shown.

16:12 – 17:28

07 · Project scope — website scraping + manual docs

Scrape client website via Apify, add to project folder. Move proposals, pitch decks, scope docs into project_scope/ regardless of format.

17:29 – 19:19

08 · Synthesis — Claude builds the pre-context markdown

Final prompt: summarize project_research/ into a comprehensive pre-context file. Claude assembles everything. Trevor recommends manually dialing it in after.

19:20 – 20:52

09 · Engage GSD + wrap

/gsd new project — use pre-context to answer GSD questions. Result: set up like a professional AI consultant. Recap + CTA.

Atomic Insights

Lines worth screenshotting.

Priming the GSD framework with a pre-context document assembled from meeting transcripts, project scope docs, and stakeholder LinkedIn profiles doubles the speed of the entire build.
Going into GSD cold and letting it guide you through questions is slower than feeding it a fully assembled primer on the first prompt — the primer front-loads all the context gathering.
The GSD framework creates two documents at project start: a phased roadmap (PRD) and a technical state document — these become the context window primer for every execution command.
The pre-context folder has three sub-categories: stakeholder information, project discussions (transcripts), and scope documents — one markdown file synthesizes all three for GSD.
TLDV and Apify MCPs handle the two hardest parts of pre-context assembly: downloading meeting transcripts automatically and scraping LinkedIn profiles of key stakeholders.
Running Claude Code with --dangerously-skip-permissions removes the approval prompts that would interrupt an automated pipeline — standard practice for GSD users.
A stakeholder profile in the pre-context file (decision maker vs. operator, seniority, power to approve scope) helps Claude calibrate its recommendations to the actual constraints of the project.
The slash GSD new-project command creates the roadmap and technical state, but only after the pre-context file tells it who the stakeholders are, what was discussed, and what the scope is.
Accessing transcripts via API (rather than copying them manually) is the hidden productivity multiplier — the MCP does the transcript retrieval automatically when you reference the meeting.
The pre-context workflow shifts the developer from relying on AI to guide the project toward being the architect who gives AI a complete brief before it starts working.
Version-controlling the pre-context folder inside the project means any team member can pick up the full project context by cloning the repository.
A project scope document fed into the context window before GSD starts eliminates the early rounds of clarifying questions that slow down every cold-start build session.

Takeaway

Build the primer before you run the framework.

context-first workflow

Structured context in equals structured output out — the pre-context assembly step is the unlock GSD users are missing.

Create project_research/ with three subfolders before touching /gsd: discussions/, project_scope/, stakeholders/.
Use TLDV MCP (or any notetaker with API access) to pull meeting transcripts directly into discussions/ as markdown.
Use Apify MCP to scrape LinkedIn profiles for stakeholders/ and client/competitor sites for project_scope/.
Run one synthesis prompt: Summarize everything in project_research/ into a comprehensive pre-context MD file.
Then go in and manually dial it in — the AI-generated synthesis is the draft, not the final.
Apply this pattern to LFB Line: make pre-context assembly the first deliverable in every client engagement.
The TLDV + Apify MCP combo is worth testing as a productizable onboarding workflow inside MCN+.

Glossary

Terms worth knowing.

GSD framework: A community-built workflow for Claude Code (short for Get Shit Done) that walks a user through scoping a new project, generating a roadmap and tech stack document, then executing the work in numbered phases.
Claude Code: Anthropic's command-line coding agent that runs in a terminal, reads and edits files in a project, and executes shell commands on the user's behalf.
Pre-context file: A single markdown document assembled before starting an AI build that summarizes stakeholders, prior discussions, and project scope so the coding agent has full background on its first run.
Context window: The amount of text a language model can hold in active memory at once. Anything outside it has to be re-fed, so curating what goes in determines how well the model performs.
Dangerously skip permissions: A Claude Code launch flag that disables the per-action approval prompts so the agent can read, write, and run commands without stopping to confirm each step.
PRD: Product Requirements Document. A written spec that lists what a project must do, who it serves, and how success is measured, used to align builders before code is written.
Phases / milestones: The chunks a roadmap is broken into so an agent can execute one bounded slice of work at a time instead of trying to build the whole project in one pass.
MCP server: Model Context Protocol server. A small adapter that lets an AI agent like Claude Code talk to an external service (a notetaker, a scraper, a database) through a standard interface.
WSL: Windows Subsystem for Linux. A built-in Windows feature that runs a real Linux environment alongside Windows, commonly used to run developer tools that expect a Unix shell.
Cursor: An AI-first code editor forked from VS Code that integrates LLM chat, inline edits, and agent workflows directly into the editing experience.
/init: A Claude Code slash command that scans the current repository and generates a CLAUDE.md file describing the project so the agent starts every future session with consistent baseline knowledge.
CLAUDE.md: A markdown file at the root of a project that Claude Code automatically loads at session start. It holds project-specific instructions, conventions, and commands the agent should follow.
TLDV: An AI meeting notetaker that records calls on Zoom, Google Meet, and Teams, then produces transcripts and summaries accessible by API or MCP for downstream automation.
Apify: A cloud platform of pre-built web scrapers (called Actors) for sites like LinkedIn, Google, and arbitrary websites, accessible by API or MCP so an agent can pull structured data on demand.
Slash command: A keyword starting with / that triggers a predefined workflow inside a tool like Claude Code, for example /init or /gsd new-project.
Webhook: A user-defined HTTP callback that a service fires when an event happens, letting another system react in real time, for example pulling a meeting transcript the moment a call ends.
Scraper: An automated program that extracts structured data from a webpage or platform, typically by simulating browser visits and parsing the returned HTML.
Stakeholder: Anyone with influence or decision authority over a project, such as a CEO, project manager, or operator, whose role determines what gets approved and how the work moves forward.
Pitch deck: A slide presentation used to win a client or investor, typically covering the problem, the proposed solution, scope, timeline, and price.

Resources

Things they pointed at.

01:17toolGSD (Get Shit Done) GitHub repo ↗

07:00toolTLDV ↗

07:50toolApify ↗

10:35linkTrevorpreneur AI Community (Skool) ↗

Quotables

Lines you could clip.

00:28

“I was going in cold, and I was letting GSD essentially just guide me through the project. But I discovered if I prime GSD with really good research information, my projects were going a lot faster.”

Clean pivot from setup to insight — no filler, no jargon→ TikTok hook↗ Tweet quote

00:55

“I think it's really, really important to shift our mindset from completely relying on AI tools and making ourselves more the architects.”

Quotable positioning line — stands alone→ Newsletter pull-quote↗ Tweet quote

02:00

“How can we 2x the 2x.”

Punchy, memeable, context-free→ IG reel cold open↗ Tweet quote

The Script

Word for word.

Read-along

Don't just watch it. Burn it in.

See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.

metaphor

00:00I've been running the GSD, get shit done framework on my last two projects. And honestly, the results have been unreal.

00:10I'm shipping in about half the time it usually takes me instead of just messing around with Claude or ChatGPT in a endless vacuum. One of the things I really want to start exploring is how can we two x the two x.

00:25GSD really enables us to work faster. But I noticed when I first started going on with GSD, I was going in cold, and I was letting GSD essentially just guide me through the project.

00:38But I discovered if I prime GSD with really good research information, my projects were going a lot faster in the long run.

00:48So I think it's really, really important to shift our mindset from completely relying on AI tools and making ourselves more the architects and really thinking about how our project structure should be going forward. So today, I'm gonna show you how to prep a pre context file that turns your workspace into an execution machine and that really primes the get shit done methodology to enable you to just work even faster.

01:17So this is the get shit done GSD git repository.

01:23And I would highly recommend, if you don't know about this repository, you go in and you just take a look at and understand everything that's going on in this repository because it's really interesting how it's all put together.

01:38But in order to get started, there's there's a few really high level things that you need to know. Um, the first of all is, uh, part of the GSD framework is you need to run claw dangerously and skip permissions.

01:52This seems really, really scary at first, but I promise you it's not once you get in and you start using it. If you've done AI projects before, you know how much Claude code needs to get permissions. And for a lot of those permissions, if Claude code crashes for any reason, then what happens is when you reload into Claude code, you have to give it that the all those permissions again.

02:13So it can it can be really annoying. So just starting Claude code by skipping these permissions is totally part of this. There are alternative if you do want to monitor that a little bit more effectively, but I would recommend that's the big thing.

02:27And then always, whenever you're starting GSD and the for the purposes of this video, uh, GSD new project is how you just get started, and it does a really good job of guiding you through how to execute on that project.

02:41So let's go into what actually GSD is doing on a high level. So this is what your typical a new project looks like.

02:50Right? So you're you're like, okay. I have a client requirement, and you know what?

02:54I gotta start my new project. So first thing I'm gonna do is I'm gonna dive right into GSD. I'm gonna do slash GSD new project.

03:02And what I'm saying is you actually don't wanna do this. And then for those who don't know, essentially what GSD is when you start a new project, it'll ask you a bunch of questions and it's gonna create two main documents at least.

03:14The first the first big document it's going to create is the project road map or like a a PRD. And essentially in this project road map, what it does is it lists out all the phases, just very high level of what needs to be accomplished.

03:31And then the other thing it's going to do is get a technical state of the types of tech you want to do. So when you start a new project to ask you, okay, what do you wanna accomplish? What do you want your back end to be?

03:42Um, how do you wanna develop your front end? Like, it's going to ask you a bunch of those questions. And essentially what it's starting to prep is your context window primer so when you start to execute in these phases okay I need to set up the front end for my client like I need to get a new website set up and maybe I want like an AI chat bot or something.

04:02It's going to break that up into phases or it's gonna break that up to milestones and then inside those milestones it's gonna break it up into phases. And then what you do is you say execute phase one and what it will do is it'll shoot all of this information into the context window, and it'll shoot the technical state into the context window, and then the instructions on how to execute phase one.

04:25Like, really, really high level. That's essentially what GSD does in a nutshell. But the problem that not really a problem, but where I've really noticed we can get a lot more efficient is starting to prep GSD before we actually engage into project.

04:45So what does that look like? So if you look at any AI project or any project you wanna complete in general, there's a few high level things that we need to dig into.

04:55First of all, who are the stakeholders in the project? What are we trying to accomplish? What are our timelines?

05:02Like, project scope is is a really big is a really big topic. And then secondly, what are the discussions that we've had around this project?

05:11And so what I found is if we can essentially mark up and summarize all of this information into a single document and then use this document to feed GSD when we initially create our project, it's two x ing your two x.

05:30So what does that look like when we actually create a new project? Well, firstly, all of us are using notetakers nowadays.

05:37So having access to an API or having access to webhooks on our notetakers where we can download the transcripts and add them into our project folders is a hidden superpower. Secondly, we've if we're doing client work, we've created a lot of documents explaining what we're doing.

05:56We've created a project scope document that should be getting fed into your context, your pre context window. So this should actually be like a pre context window.

06:05And then secondly, the stakeholders, like, that's really important. Like, are we working with a project manager?

06:10Are we working with the CEO? Are we working with a VP? What do they have the power to do in this project?

06:16Are they like a decision maker or are they like an operator of it? We need to know that information because as we pushed our project forward, we wanna achieve success.

06:27So let's dig in now to how we can actually get these three things and create this pre context file. Okay. So this is Claude code, and I have it installed on WSL, which is a Linux image on my Windows machine, and I'm inside a cursor right now.

06:44I've done a little bit of prep to expedite this process. And, essentially, I've come in and I've run a slash init since I'm starting a new Claude project in Claude code. I've also logged in to Claude.

06:58Additionally, there's two more things that we need to focus on here, which is I have installed two MCP servers, which MCP essentially just allows us to have our Claude code agent communicate with their technology or we can communicate with their services.

07:17So my notetaker is TLDV. And then what's also going to be very important is API phi or Apify.

07:25There's so many different things you can call this. But essentially, this is just like a scraper. It's a scraper mechanism for us that we can essentially use to get this information.

07:37So now that I have my project initially set up, the slash in it creates the Claude MD file for me. And then from there, we installed the MCPs and away we go.

07:48So in order to prep this on the original document that we had, there's three main folders. So I'm going to add these folders into my into my project.

07:59We can call it like client research or project research. Project research.

08:07And then we have three subfolders in here that we want to add which is going to be project scope. There's going to be discussions.

08:19So first things first is like for discussions, there's a couple of ways to do this.

08:25You can just go in and create markdown files yourself and paste the transcriptions in there depending on if you just have a few meetings or if you wanna be really if you wanna do it the cool way, which I'm doing it, you can do it through API or MCP servers. So if you wanna do that, you can just copy the transcript and you can just say, like, hey Claude create a md file of this discussion and then you can paste the transcript in there.

08:54The other thing you can do is if you're used to using MCP servers is you can essentially if you're used to using APIs or MCP servers, you can essentially just grab like a you can give the agent context on the meetings.

09:09Like, you can say, I want you to grab all the transcripts with client x y z and move them into the discussions folder. Um, and I can show you exactly how this works after I've installed the TLDV MCP.

09:22I can say use the TLDV MCP and then I just use TLDV as my notetaker.

09:30There's so many other notetakers that have API access and MCP access. So, um, you can install those. And if you're interested in learning more about installing MCP servers, I can show more on this.

09:42But use that TLDV MCP to grab to grab my discussion from yesterday from yesterday named Traverse Weekly Call which is one of my one of my businesses and create a MD file in the discussions folder with the transcript.

10:11And since I have the TLDV MCP installed and since I have the TLDV MCP installed and the skills installed and clogged code, you can see right here, it's essentially just connecting directly to TLDV, and it's going to create that transcript for me.

10:32So you can start to see the power of context at work here. And this is the coolest thing ever because now if we go into my discussions tab, obviously, Claude is still doing its thing.

10:44Once this is finished, I'm going to have my transcript in the discussions tab. While that's going now, let's talk about stakeholders and project scope. So project scope is good to move all of your project details into this folder.

11:00So if you've created any sort of documents when you've done your sale for AI consulting or your AI agency, move those into the project scope folder. If you've done any sort of proposal for the client, move that into the project scope folder.

11:16And then lastly here, we have the stakeholders folder. The stakeholders folder is essentially what I would really recommend you do is you essentially scrape your clients' LinkedIn profiles and do a little bit of a write up on each stakeholder.

11:36Additionally, another really good thing I do with the a the API fi MCP is I love to do competitor research.

11:46Um, I do a lot of high level AI consulting projects, and competitor research is really necessary. So we can use the APIify MCP to scrape LinkedIn profiles, and then we can also use it to scrape the websites and scrape the profiles of our of their competitors and add it into this project research folder.

12:09It's super powerful. So we'll do a little bit of that once this finishes. So I'm gonna let this finish now.

12:16Okay. So now we can see the TLDV MCP did its it connected to my TLDV account, grabbed that transcript, and it created a discussion markdown file that you can see right here, um, above that, um, is in our discussion.

12:32So you can obviously take this now and you can apply this to multiple discussions. Um, you can even search by email or name inside of the TLDV MCP or if your notetaker has a particular MCP or API, you can do that as well. All these notetakers are the same nowadays anyways and they all have the same kind of accessibility into them.

12:53Or again, you can just move the transcripts in. So next we wanna move on to project. We wanna move particularly into the, um, discussions tab and you can see here Claude just made another discussions folder.

13:05So I'll just move that in there and then I'll I will just, uh, delete that because I don't need that anymore. Um, you can see we have project scope and we have stakeholders right now.

13:16And really what I just wanna show off very quickly is how can we use the MCP servers to build this context. So first of all, I've connected APIify into I've connected into the APIify MCP server.

13:32And so I have all of the if if we if you don't know what APIify is, it's essentially a scraping service that has a variety of different scrapers where you can scrape LinkedIn, you can scrape websites, you name it.

13:45And it's MCP is extremely powerful. As an example, what I will do now is I will run I will grab my own LinkedIn profile and I will say let's say I'm one of the stakeholders for this project.

13:58I can say, please use the a API five MCP server to research a research a LinkedIn profile public profile scraper and scrape our client's profile which is my LinkedIn profile.

14:24So API Fi is going to now provide is going to do its thing and it's going to scrape that profile and I'm just gonna say add the scraped MD file into the stakeholders folder.

14:41K. And it's a you can always you can always just add a command into Cloud Code as you go on, um, and it'll take that additional context and it'll go. So you can see it's found an API scraper and now it's added it into the stakeholders.

14:55It looks like it's created another folder. That's okay. And it it'll add that at in a markdown into that folder.

15:02Additionally, what we can do with APIify is we can also scrape websites. We can scrape our client's website, and we can also scrape competitors' website.

15:12If you're a AI consultant or an AI agency, you should be doing this as part of setting up all your project. You know? And then we can say, like, we'll wait for this to finish, but we'll run a scrape of our website and we'll add that into the markup folder.

15:27And while this is running, we also have the project scope tab on the right here. And essentially what the project scope tab on the right is is what we should add in is any project folders that we've come up with up until this point.

15:43So I'm talking about if you've created any proposal documents for your clients, if you've done any pitch decks as part of signing the business, or if you have a project scope document. All of that should be added into the project scope regardless of what format they're in PDF or anything like that because what we're going to do is when we collect all of this information, you'll see that we now have we now have enough information to make that pre context.

16:12We're able to prime the primer essentially. So here you can see Claude code made a little bit of a mistake, not a big deal though. But you can see my LinkedIn profile here.

16:21Um, it's completely scraped and it's it's in the context of our project folder now. And then lastly, what we'll do is we will create a in the stakeholders tab, um, we will copy the path and then we can ask Claude code, hey, can you scrape our client's website for context and add it to this location in a md file.

17:07Okay. And now you can see that our our website scrape has been added into our project folder, our project research folder.

17:18So once we've identified and we've added in all our project research into the scope, we want to now prime our GSD.

17:29So very easily we can say we can say, Claude, please look over my project research folder and create a comprehensive markdown folder that summarizes all the information we have between project scope, oops, project scope, the discussions, and the stakeholders.

18:02Um, Additionally, if you've done another great thing you can do with the API Fi MCP is you can you can do competitor research in there and create a and stakeholders to create a pre context pre context MD file that we will use to get our GSD project launched with maximum efficiency.

18:36Then what I would just recommend you do is, like, I'm just trying to do this very quickly right now. But once we create that initial folder, you do wanna go in into this markdown file and you want to really, really dial in on it.

18:52That's the best way to really, really get the most out of this. Um, and then what's gonna happen after all of this takes place is we're then going to finally initiate GSD.

19:04So really exciting. Claude has collected all the context for a pre context folder. It's gonna be spitting that out any second now.

19:13And then from there, we're going to be able to engage GSD and get our project started. At which point, we would go slash GSD new project.

19:26And then once it starts inquiring about us or once it starts inquiring about the project, what we wanna do is we wanna reference this pre context folder and answer its questions so you'll just have a solid context for your for your new project and you have been set up in the best way possible like a professional AI consultant.

19:50So what we explored today was we got an understanding for how we wanna start setting up our AI projects. We wanna use frameworks like GSD, but what's really important is how we set those frameworks up.

20:04We utilized MCP servers to make the process of gathering all of our project context in the most efficient way, but we also understand there's manual backups if we're not that advanced yet or we don't have MCP or API access into the project context that we need.

20:24And we understand now how to make a pre project context file so when we start engaging our project frameworks like GSD, we can do so in the most efficient way possible, which in the long run will end up saving us a lot of time.

20:41So if you have any questions, leave a comment below. I'd be more than happy to answer. Please like and subscribe if you'd like to see more of this content.

20:49I'll catch you guys around.

The Hook

The bait, then the rug-pull.

Trevor opens mid-proof, not mid-pitch. Two projects shipped at half speed with GSD — now he wants to 2x the 2x. The insight: going into GSD cold is leaving efficiency on the table, and the fix is one folder and three data sources.

Frameworks

Named ideas worth stealing.

01:17model

GSD (Get Shit Done)

Claude Code framework: /gsd new project generates a PRD + Technical State doc, breaks work into phases, injects each phase into context window on execute.

Steal forAny multi-session Claude Code project — especially MCN feature builds and LFB Line client onboarding

04:52model

Pre-Context Assembly

Discussions (meeting transcripts via TLDV MCP)
Project Scope (proposals, pitch decks, scope docs)
Stakeholders (LinkedIn scrapes via Apify MCP)

Build three data folders before touching GSD. Synthesize into a single pre-context.md. Feed that to /gsd new project. This is the prime the primer step.

Steal forLFB Line onboarding, any AI consulting client project setup, CLAUDE.md generation for new projects

CTA Breakdown