gtm-start
Skill2 starsChanged 2 months agoMITView on GitHub
Set up the GTM Architecture kit and guide a first ten-account pilot, using the offline demo, company brief, skills and hosted functions.
In this repository54 other files it gives its agents.
- AGENTS.mdAGENTS.md
- context/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- context/CLAUDE.mdCLAUDE.md
- brand-reviewSkill
- brand-systemSkill
- capture-contextSkill
- content-strategySkill
- crm-presync-checkSkill
- flowchartSkill
- graphics-designerSkill
- launch-videoSkill
- lead-magnet-creatorSkill
- lead-sourcingSkill
- linkedin-copywriterSkill
- long-formSkill
- manim-videoSkill
- newsletter-writerSkill
- outbound-copywriterSkill
- oxygen-dedupeSkill
- oxygen-deliverabilitySkill
- oxygen-diagnosticsSkill
- oxygen-email-infraSkill
- oxygen-gtmSkill
- oxygen-knowledgeSkill
- oxygen-linkedin-marketingSkill
- oxygen-quickstartSkill
- oxygen-recipesSkill
- oxygen-sequencer-enrollSkill
- oxygen-sequencerSkill
- oxygen-table-tidySkill
- oxygen-uniboxSkill
- oxygen-workflow-authoringSkill
- personalize-ai-columnSkill
- qmdSkill
- repurpose-contentSkill
- researcherSkill
- setup-workspaceSkill
- shorts-audioSkill
- shorts-cutSkill
- shorts-editSkill
- shorts-motionSkill
- shorts-qaSkill
- signals-sweepSkill
- spin-tagsSkill
- split-test-designerSkill
- video-useSkill
- voice-calibrationSkill
- week-postsSkill
- x-copywriterSkill
- youtube-descriptionSkill
- youtube-publisherSkill
- youtube-scriptSkill
- youtube-thumbnailSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Read the root README, the first-batch guide, the company brief and the selected function contracts.
- Very specific: line 11
Run npm run demo to inspect the synthetic pipeline.
- Very specific: line 13
Use lead-sourcing for ten known accounts and split-test-designer to freeze one test.
- Very specific: line 15
Use linkedin-copywriter to explain one supported learning or lead-magnet-creator to turn an actual deliverable into an asset.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill 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.
Files
Start a GTM pilot
Read the root README, the first-batch guide, the company brief and the selected function contracts. Work from this repository root.
- Establish one buyer, one problem, one offer and the next useful deliverable from the user's brief. Use existing answers; ask only for facts needed to proceed. Keep unknowns explicit.
- Run
npm run demoto inspect the synthetic pipeline. Explain the account gate, persona gate, capacity hold and unreviewed messages. Research, scores, verification and copy in this demo are fixtures. - Save real company inputs under ignored
company/private/, based on the examples. Fill audience, voice and public proof incontext/only from supplied sources. Treat a populated fork as private working material. - Use
lead-sourcingfor ten known accounts andsplit-test-designerto freeze one test. Useoutbound-copywriterfor one concrete message before generating a batch. - For hosted execution, use oxygen-quickstart and read the OXYGEN setup. Show the setup plan, apply within the user's requested scope, inspect one row and calibrate scoring before paid batch execution. Use the OXYGEN skill guide for context, composition, delivery and operation.
- Use
linkedin-copywriterto explain one supported learning orlead-magnet-creatorto turn an actual deliverable into an asset. A sample/demo result is never customer proof.
Deliver the brief, accepted/held account counts with reasons, one reviewed draft, test plan and next unresolved mapping. Distinguish a local simulation, hosted preview and live result. Installing this kit does not connect the full campaign.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.

