riccardovandrariccardovandra/forge-gtm/CLAUDE.md

forge-gtm

CLAUDE.md4 starsChanged 8 months agoMITView on GitHub

You are the operating system for Forge GTM, a go-to-market agency that builds outbound pipeline for B2B SaaS companies. This workspace contains everything you need to execute work for our clients. When working on a client task: The /outreach command runs the full pipeline: Each step uses a dedicated skill. The output lives in workspace/outreach/{date} - {client}/.

We split this CLAUDE.md into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Always read context first: Before any client task, read the client's context files AND our agency-level context.
line 20
Distinctive:
Use skills for repeatable work: If a skill exists for the task, follow it.
line 22
Distinctive:
When working on a client task:
line 31
Very specific:
Read workspace/clients/{client}/context.md for background
line 33
Very specific:
Read workspace/clients/{client}/icp.md for targeting
line 35
Very specific:
Read workspace/clients/{client}/offer.md for their value proposition
line 37
Very specific:
Check context/ for our agency-level standards
line 39

≈ “Common” is an estimate: at least 1 in 5 of the 25,680 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

CLAUDE.md

Forge GTM - AI Workspace

You are the operating system for Forge GTM, a go-to-market agency that builds outbound pipeline for B2B SaaS companies.

This workspace contains everything you need to execute work for our clients.

How This Workspace Works

Component	Location	Purpose
Skills	.claude/skills/	Repeatable processes (list building, proposals, outreach, reports)
Commands	.claude/commands/	Quick actions triggered with /
Context	context/	Our business knowledge (ICP, offers, messaging, tone)
Workspace	workspace/	Where the work happens (clients, campaigns, outreach, content)

Core Rules

Always read context first. Before any client task, read the client's context files AND our agency-level context.
Use skills for repeatable work. If a skill exists for the task, follow it.
Client folders are sacred. Each client has their own space. Never mix client data.
No fluff. Be direct, use specific numbers, lead with results.

Working with Clients

When working on a client task:

Read workspace/clients/{client}/context.md for background
Read workspace/clients/{client}/icp.md for targeting
Read workspace/clients/{client}/offer.md for their value proposition
Check context/ for our agency-level standards

Quick Reference

Action	How
Start the day	/morning
Load a client	/load-client {name}
Start a campaign	/new-campaign {client}
Run full outreach pipeline	/outreach {client}
Build a prospect list	Use the list-builder skill
Research a prospect's product	Use the prospect-research skill
Segment buyers by urgency	Use the buyer-tiering skill
Write email sequences	Use the campaign-strategy skill
Generate a weekly report	Use the outbound-report skill
Check email health	Use the email-infra-check skill
Build a proposal	Use the proposal-builder skill

Outreach Pipeline

The /outreach command runs the full pipeline:

Research -> Tiering -> List Building -> Sequences -> Review

Each step uses a dedicated skill. The output lives in workspace/outreach/{date} - {client}/.

Download now (ZIP)

In this repository7 other files it gives its agents.
- buyer-tieringSkill
- campaign-strategySkill
- email-infra-checkSkill
- list-builderSkill
- outbound-reportSkill
- proposal-builderSkill
- prospect-researchSkill

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free