Skip to content
Skills Library
AI & agents · Building & coding

Init

/Init

Bootstrap the checked-in AI layer on a brownfield repo. Delegates the project foundation to buddy, then generates a lean CLAUDE.md (under 300 lines, every rule cited to real code), on-demand .claude/context/ modules, and an .mcp.json scaffold for Jira/Confluence/GitHub. USE WHEN sdlc init, init ai layer, set up ai layer, generate CLAUDE.md, create rules, bootstrap project, onboard repo, brownfield setup.

Licence
MIT
Last repository change
21.08.2026

Assessment and security

95/ 100Class: good
Format20 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
4
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 21.08.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Bootstrap the checked-in AI layer on a brownfield repo. Delegates the project foundation to buddy, then generates a lean CLAUDE.md (under 300 lines, every rule cited to real code), on-demand .claude/context/ modules, and an .mcp.json scaffold for Jira/Confluence/GitHub. USE WHEN sdlc init, init ai layer, set up ai layer, generate CLAUDE.md, create rules, bootstrap project, onboard repo, brownfield setup.

Original author description

Bootstrap the checked-in AI layer on a brownfield repo. Delegates the project foundation to buddy, then generates a lean CLAUDE.md (under 300 lines, every rule cited to real code), on-demand .claude/context/ modules, and an .mcp.json scaffold for Jira/Confluence/GitHub. USE WHEN sdlc init, init ai layer, set up ai layer, generate CLAUDE.md, create rules, bootstrap project, onboard repo, brownfield setup.

How it works

  1. Customization
  2. Prerequisites
  3. Workflow Routing
  4. What it produces
  5. Core principle
  6. Examples
  7. Source
Original SKILL.md headings · 51 lines, 339 words
SKILL.md preview
---
name: Init
description: Bootstrap the checked-in AI layer on a brownfield repo. Delegates the project foundation to buddy, then generates a lean CLAUDE.md (under 300 lines, every rule cited to real code), on-demand .claude/context/ modules, and an .mcp.json scaffold for Jira/Confluence/GitHub. USE WHEN sdlc init, init ai layer, set up ai layer, generate CLAUDE.md, create rules, bootstrap project, onboard repo, brownfield setup.
---

# Init

Turn an existing (brownfield) repository into an AI-native one by checking the **AI layer** into source control: rules (`CLAUDE.md`), on-demand context modules (`.claude/context/`), and tool configuration (`.mcp.json`). Init does not reinvent codebase analysis — it **delegates the foundation to buddy** and layers the AI-native artifacts on top.

## Customization

Before executing, check `~/.claude/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/Init/PREFERENCES.md`. If present, load and apply it; otherwise use defaults.

## Prerequisites

1. **buddy** plugin installed (buddy requires **LifeOS**). LifeOS marker: `test -f ~/.claude/LIFEOS/VERSION`. If missing: "LifeOS is required. Run `/setup:lifeos`, then install the buddy plugin (`/plugin install buddy@claude-buddy-marketplace`)."
2. Run inside a git repository with real code (brownfield). For an empty repo, Init falls back to structured questions.
3. **MCP (recommended)**: Atlassian (Jira/Confluence) + GitHub servers. Optional at init time; `.mcp.json` is scaffolded for later.

## Workflow Routing

| Workflow | Trigger | File |
|----------|---------|------|
| **RunInit** | Any `/sdlc:init` invocation | `Workflows/RunInit.md` |

## What it produces

| Artifact | Path | Owner |
|----------|------|-------|
| Project foundation | `/directive/foundation.md` | buddy Foundation (delegated) |
| Global rules | `CLAUDE.md` (repo root, < 300 lines) | Init |
| Context modules | `.claude/context/*.md` | Init |
| MCP config scaffold | `.mcp.json` | Init (if absent) |

## Core principle

Every rule in `CLAUDE.md` must trace to something real in the codebase — cite it (`file:line`). Do not invent aspirational rules the code does not follow. Global rules are only for what applies to basically every task; anything task-specific belongs in a `.claude/context/` module, not the global file (context rot is real — keep `CLAUDE.md` lean).

## Examples

**Example 1: fresh brownfield init**
```
User: "/sdlc:init"
→ Confirms buddy + LifeOS present
→ Runs /buddy:foundation (detects domain, writes /directive/foundation.md)
→ Analyzes the code, derives a lean CLAUDE.md (< 300 lines, rules cited to file:line)
→ Writes .claude/context/{architecture,testing,...}.md for task-specific detail
→ Scaffolds .mcp.json (Atlassian + GitHub) if not present
→ Presents everything for human review before committing
```

## Source

Modeled on Cole Medin's `create-rules` from the ai-native-starter-pack, layered on buddy's Foundation.
Files in this package (4)
  • SKILL.md 3 KB
  • Templates/ClaudeMd.md 1 KB
  • Templates/ContextModule.md 1 KB
  • Workflows/RunInit.md 4 KB

Versions

RepositoryScoreLicence
This page · rsts-dev/claude-buddy-marketplace95MIT
CodaColaLight/nightmill100Apache-2.0
userKael/rastro100MIT
elalfner/relevo100MIT
abatyuk/okf100MIT
duronext/jig100MIT
sh5623/e2e-rail100MIT
Calvin-LLC/skills100MIT
arxdsilva/ai-loops100MIT

Database snapshot: 13.11.2026 · package version 9adfb28b7fc1 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100ctx-init
    Initialize AGENTS.md + CLAUDE.md + rules/ in a code repo (fresh mode). Triggers on "/ctx-init", "init context", "scaffold AGENTS.md", or when user asks to set up project context in a new repo.
  • 100init-claude
    Generate a production-grade CLAUDE.md for any project. Detects project type (Go CLI, Node API, full-stack monorepo, IaC, Python, etc.) and generates a comprehensive CLAUDE.md with architecture map, agent routing, dev commands, QA checklist, code standards, and workflow…
  • 100target-instructions-bootstrap
    Create the target repository's local AI instruction scaffold during first-use bootstrap. Use from repo-init-scan when `.github/instructions`, runtime adapters such as `AGENTS.md` / `CLAUDE.md`, or the neutral project facts scaffold are missing. Do not use to overwrite existing…
  • 100claude-md-init
    Use when a repo has no CLAUDE.md, or the user asks to create/refresh CLAUDE.md or project instructions for Claude Code. Generates a short, verified CLAUDE.md from the repo's real build/test/lint commands and layout, and never invents commands.
  • 90rules-create-global
    Set up your project's global rules, a lean and well-structured root CLAUDE.md (plus a starter .claude/), following the course methodology. Greenfield: pass your PRD and/or architecture-spec path and it derives rules from your engineering decisions (a PRD alone is product…
  • 100cc-stack-setup
    Deploy or audit the full 5-layer Claude Code stack (CLAUDE.md + skills + hooks + agents + memory) in a repository. Use this skill whenever the user runs /cc-setup, asks to "set up Claude Code on this repo", "configure a new repo for Claude", "audit my Claude Code setup",…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.