Scale AI Gate

• Source: Built by Jonathan Kvarfordt. Standalone bundle v0.2.
• Frameworks applied: Step 3. Align

It covers a job one of the eight revenue seats has to finish, and it states its process, decision rules, and output format clearly enough for an agent to follow.

1. 1.Copy the SKILL.md text below, or download the raw file.
2. 2.Create a folder named exactly scale-ai-gate in your agent's skills directory.
3. 3.Save the file inside that folder as SKILL.md.
4. 4.Ask the agent one of the trigger requests below.
5. 5.Check the output against what you already know before it leaves your desk.

• do we need AI for this
• is this an AI problem
• should we automate this

---
name: scale-ai-gate
description: Decides whether a friction point needs AI, plain automation, an integration, or a human fix before any capability or vendor work begins. Use when the user says "do we need AI for this", "is this an AI problem", "should we automate this", "AI or automation", or as the first step of Module 3.
---

# scale-ai-gate

Write the Gate section of `artifacts/scale-capability-decision.md`. Not every problem needs AI. Saying so early saves a bad purchase.

## Preflight (every run)
1. Confirm `GTM-AI-OS/` is accessible. If not: "I need access to your GTM-AI-OS folder. Select it in Cowork's folder picker, or run `os-install` from the core plugin." Stop until it is.
2. Read `CLAUDE.md`, `INDEX.md`, and the last 20 lines of `signals/log.md`.
3. Check the prerequisites below. For anything missing, ask the cold-start questions and offer: (a) run the earlier skill now, or (b) fast path: answer the questions and this skill writes a minimal version of the missing artifact marked `status: draft (fast path)`.
4. On finish, update the artifact row in `INDEX.md` and append one line to `signals/log.md`: `<date> | <skill> | <produced> | <human changed> | <open question>`.

## Prerequisites
- `artifacts/scale-opportunity-matrix.md` with a top Plan item.
Cold-start: "Describe the one problem you want to solve, who does the work today, and what systems are involved." Write it as a fast-path friction entry and continue.

## Step 1: Classify the work
Ask these in order and stop at the first yes:
1. Is the rule fully known and the inputs structured? → Plain automation (workflow tool, native CRM automation). No AI.
2. Is the problem two systems not sharing a field? → Integration. No AI.
3. Is the problem that nobody documented how it's done, or that people don't follow the process? → Human/process fix first. AI later, maybe.
4. Does it require reading unstructured text, judging, summarizing, generating, or deciding under ambiguity? → AI candidate.

## Step 2: Cost check
For AI candidates: would an AI solution cost more than the friction costs (from the Module 2 dollar figure)? If yes, say so and recommend a cheaper path.

## Step 3: Write the verdict
One of: Automation · Integration · Process fix · AI candidate · AI candidate with prerequisites (list them). Write the reasoning in the Gate section and update `INDEX.md`.

## Hand off
If AI candidate: "Run `scale-capability-match`." Otherwise: "This doesn't need Module 3. Take the fix into Module 4 as a pilot without AI, or return to the matrix for the next item."

What does the Scale AI Gate skill do?

Decides whether a friction point needs AI, plain automation, an integration, or a human fix before any capability or vendor work begins.

Where does the Scale AI Gate skill come from?

Built by Jonathan Kvarfordt. Standalone bundle v0.2.. The source and included files are shown on this page and in the package download.

Why was the Scale AI Gate skill chosen for this library?

It covers a job one of the eight revenue seats has to finish, and it states its process, decision rules, and output format clearly enough for an agent to follow.

When should the Scale AI Gate skill not be used?

Use it only for the job named above. A skill applied outside its scope produces confident output on the wrong question.

How do I install the Scale AI Gate SKILL.md file?

Download the file, create a folder named exactly scale-ai-gate inside your agent's skills directory, and save the file inside it as SKILL.md. The agent loads it when a request matches the description.