When should I use The Loop Ledger?

A loop keeps re-reporting something you already dismissed, or you cannot tell what a loop changed last week. That's the diagnostic trigger. Once installed, ask Claude for the outcome ("keep the state file every loop reads and appends to") and the skill kicks in automatically.

How does The Loop Ledger work under the hood?

The Loop Ledger is part of the Store Loops mechanism in Sid Chaudhary's gtm-skills repo. When invoked, Claude reads the SKILL.md, pulls your shared product-context (ICP, brand voice, scoring model), and produces a structured output. No prompt engineering on your side.

Do I need Claude Code to run The Loop Ledger?

Claude Code is the fastest path since it auto-loads local skill folders. The same SKILL.md also runs in Claude Desktop and claude.ai Projects - upload the zip in Capabilities. See the install options below for both paths.

How is The Loop Ledger different from just prompting Claude?

A skill is a folder with a SKILL.md file plus reference material - real methodology, frameworks, and benchmarks Claude loads on demand. A prompt is text you paste every time. With The Loop Ledger installed, you ask for what you need in plain language and Claude runs the right process without you re-explaining it.

All skills

Store Loops

The Loop Ledger

Q: Is The Loop Ledger really free?

Yes. The full gtm-skills repo is MIT licensed on GitHub. Clone it, fork it, modify it. Running the install command (npx skills add sidchaudhary/gtm-skills/skills/store-loops/the-loop-ledger) pulls it straight from GitHub into your project's .claude/skills/ folder. No signup, no build step, no gated tier.

Keep the state file every loop reads and appends to

terminal

$ npx skills add sidchaudhary/gtm-skills/skills/store-loops/the-loop-ledger

No signupMIT licensedView source

About

What it does

Keep the state file every loop reads and appends to

You'll know it's time when...

A loop keeps re-reporting something you already dismissed, or you cannot tell what a loop changed last week.

How it works

Run it in three steps

0110 sec

Install

Copy the install command above and run it in your project.

02instant

Ask Claude

Ask for what you need in plain English, no prompt tuning required.

03seconds

Get the output

Claude returns a structured artifact aligned to your ICP and voice.

When to reach for it

A loop keeps re-reporting something you already dismissed, or you cannot tell what a loop changed last week.

What it does

Full SKILL.md preview couldn't load right now. View source on GitHub.

Part of the Store Loops pack

This is one of 9 Store Loops skills. They chain - the order you run them in changes what you get, and running one in isolation usually means re-answering setup another skill already captured. Claude Skills for Shopify walks the whole pack in the order the skills actually chain.

Install

Two ways to run it.

Pick your Claude surface. Both paths take under a minute.

Prefer one command? npx skills add sidchaudhary/gtm-skills installs the whole set via the community skills CLI. If you'd rather not run a third-party CLI, use either path below to install the ZIP directly.

claude.ai or Claude Desktop

Upload as a zip in Capabilities

Paid plan

Open Settings, then Capabilities
Turn on code execution if it isn't already on
Upload the .zip you downloaded

Requires a Pro, Max, Team, or Enterprise plan. Not available on the Free plan.

Claude Code

Drop the folder, it auto-loads

Any plan

Unzip the download
Drop the folder into ~/.claude/skills/ (or .claude/skills/ in a project)
Claude Code finds it automatically

$ ls ~/.claude/skills/
your-new-skill/

Questions about The Loop Ledger

Everything you need before installing, plus how the skill actually behaves once Claude picks it up.

Creates and maintains `.agents/store-loop-ledger.md`: what each run checked, its input row count, what it flagged, what actually changed, and which patterns to stop flagging. Logs a zero-row run as failed rather than clean, and keeps suppressions dated with a review date. It's a Claude Agent Skill - a folder with a SKILL.md file and reference material - so Claude loads the methodology on demand when you ask for what you need in plain language, instead of you pasting a template.