il-projectlisted

This skill should be used when the operator says "il project", "new project", "scaffold a project", "create infinite leverage project", "init new project", "start new client project", or "bootstrap project folder". Scaffolds a brand-new project directory from the canonical `templates/project-scaffold/` in `talentedgeai/infinite-leverage`, substitutes placeholders, wires the agent team into `.claude/`, seeds `docs/product/` (product.md, epics.md, epic-status.md) from any rich description the operator provides, seeds `docs/brand/` styling from a chosen or random getdesign.md reference, initializes git, and prints next steps. All operations are inline — no bundled scripts.
talentedgeai/infinite-leverage · ★ 0 · AI & Automation · score 65

Install: claude install-skill talentedgeai/infinite-leverage

# Infinite Leverage — New Project Scaffold ## Canonical Source — Read This First **Every file this skill writes comes from ONE repo:** > https://github.com/talentedgeai/infinite-leverage | What | Canonical path | |---|---| | Project folder scaffold + stub files | `templates/project-scaffold/` | | Folder structure spec | `templates/project-scaffold/FOLDER-STRUCTURE.md` | | 6 agent definitions | `.claude/agents/*.md` | | Project skills | `.claude/skills/*/SKILL.md` | | Engineering rules | `.claude/rules/global-engineering.md` | | AGENT-DELEGATION block content | embedded below in this SKILL.md — single source for the routing table | **Rules:** 1. Never modify the scaffold template locally. To change what new projects look like, edit `templates/project-scaffold/` in the canonical repo, commit, push — the next scaffold pulls it automatically. 2. All shell operations are inline in this SKILL.md. **This skill does NOT depend on any external `.sh` files** — every step is something Claude executes directly. That keeps each action visible and auditable. --- ## When to invoke The operator wants a fresh project folder that follows the canonical Infinite Leverage layout. Prerequisites: the Infinite Leverage v2 plugin installed (which is how this skill is running), plus `git`, an authenticated `gh`, `perl`, `node`/`npm`/`npx`, and `rsync` — Step 1 checks all of them. Agents are installed into the project itself; nothing is ever written to `~/.claude/`. --- ## Inputs to gather |