Is the New Loop skill free?

Yes. The skill itself is free from AI-Builder-Club/skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the New Loop SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.

How do I install New Loop?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use New Loop with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

New Loop

Scaffold a recurring workstream as a knowledge-base loop and prove it with one live run

by AI-Builder-Club · AI-Builder-Club/skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · b813f40

Fetched SKILL.md and spot-checked all 4 body-referenced files (references/ARCHITECTURE.md, KNOWLEDGE_SETUP.md, CLAUDE.template.md, LOG.md) — all HTTP 200; no security smells (pure Markdown file ops, no curl|sh or secrets). Ran the skill end-to-end in a temp KB repo for a "weekly competitor-watch loop": bootstrapped the substrate per KNOWLEDGE_SETUP, scaffolded domains/competitor-watch/README.md from the domain template, and did the required Step-3 live run — actually pulled Linear's changelog (HTTP 200, real ships "Introducing Loops"/"Initiative properties") and recorded it in the loop Timeline plus a LOG.md entry. Baseline (no skill) produced one flat folder with an ad-hoc "# Competitor Watch" note, no frontmatter, no dated run record, and no proof it ran; the skill produced queryable frontmatter (cadence: weekly, status: active), a full substrate, and a Timeline line evidencing an executed run.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 5/5

What New Loop does

Stands up a new "loop" (a domain folder) in a file-based Markdown knowledge base: bootstraps the substrate (ARCHITECTURE.md, LOG.md, signals/docs/domains schemas) if missing, scaffolds domains/<name>/README.md from a domain template with structured frontmatter, then executes one real small-scale run and records it in the loop Timeline and global LOG.md. Triggers when the user asks to "set up a new loop", "create a domain", "start a new beat/workstream", or names a recurring job they want the agent to own.

How to install New Loop

git clone --depth 1 https://github.com/AI-Builder-Club/skills.git /tmp/new-loop-src
mkdir -p ~/.claude/skills
cp -R /tmp/new-loop-src/skills/new-loop ~/.claude/skills/new-loop
# No external deps, API keys, or tools — pure file operations in your KB repo.
# Bundles references/ (ARCHITECTURE.md, KNOWLEDGE_SETUP.md, CLAUDE.template.md, LOG.md) used at runtime.
# Run it from your knowledge-base repo root (where CLAUDE.md lives), not an app code repo.
# Part of a sibling harness set (crabbox-setup, verifier-setup) for loops that ship code.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger New Loop

/new-loop Scaffold a recurring workstream as a knowledge-base loop and prove it with one live run

It also activates on plain-language prompts like these:

Set up a new loop for tracking customer feedback
Create a domain for our weekly reporting workstream
Start a new beat and scaffold its README

Frequently asked questions

Is the New Loop skill free?: Yes. The skill itself is free from AI-Builder-Club/skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does New Loop work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md and spot-checked all 4 body-referenced files (references/ARCHITECTURE.md, KNOWLEDGE_SETUP.md, CLAUDE.template.md, LOG.md) — all HTTP 200; no security smells (pure Markdown file ops, no curl|sh or secrets). Ran the skill end-to-end in a temp KB repo for a "weekly competitor-watch loop": bootstrapped the substrate per KNOWLEDGE_SETUP, scaffolded domains/competitor-watch/README.md from the domain template, and did the required Step-3 live run — actually pulled Linear's changelog (HTTP 200, real ships "Introducing Loops"/"Initiative properties") and recorded it in the loop Timeline plus a LOG.md entry. Baseline (no skill) produced one flat folder with an ad-hoc "# Competitor Watch" note, no frontmatter, no dated run record, and no proof it ran; the skill produced queryable frontmatter (cadence: weekly, status: active), a full substrate, and a Timeline line evidencing an executed run.
What is the New Loop SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install New Loop?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use New Loop with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.