.build/claude/skills/repo-onboarding-flow/SKILL.md
Onboard new repositories into a managed ecosystem with seed.yaml contracts, CI/CD setup, documentation standards, and governance integration. Covers the full lifecycle from repo creation through promotion readiness. Triggers on new repository setup, repo onboarding, or ecosystem integration requests.
npx skillsauth add organvm-iv-taxis/a-i--skills repo-onboarding-flowInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Bring new repositories into a managed ecosystem with consistent structure and governance.
Phase 1: Scaffold ──→ Phase 2: Configure ──→ Phase 3: Document ──→ Phase 4: Integrate ──→ Phase 5: Validate
│ │ │ │ │
├─ Create repo ├─ seed.yaml ├─ README.md ├─ Register in system ├─ Stranger test
├─ Set structure ├─ CI/CD ├─ CLAUDE.md ├─ Add to registry ├─ CI passes
└─ License ├─ Linting ├─ CONTRIBUTING.md ├─ Wire dependencies └─ Promotion ready
└─ Testing └─ Architecture docs └─ Event subscriptions
#!/usr/bin/env bash
set -euo pipefail
REPO_NAME="${1:?Usage: scaffold.sh <repo-name>}"
ORGAN="${2:?Usage: scaffold.sh <repo-name> <organ>}"
mkdir -p "${REPO_NAME}"
cd "${REPO_NAME}"
git init
# Core files
touch README.md LICENSE .gitignore
# Standard directories
mkdir -p src tests docs .github/workflows
# Python project defaults
cat > pyproject.toml << 'PYPROJECT'
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[project]
name = "${REPO_NAME}"
version = "0.1.0"
requires-python = ">=3.11"
[project.optional-dependencies]
dev = ["pytest>=8.0", "ruff>=0.5"]
[tool.ruff]
line-length = 100
target-version = "py311"
[tool.pytest.ini_options]
testpaths = ["tests"]
PYPROJECT
echo "Repository scaffolded: ${REPO_NAME}"
# Python
__pycache__/
*.pyc
.venv/
*.egg-info/
dist/
build/
# Environment
.env
.env.local
*.secret
# IDE
.vscode/
.idea/
# OS
.DS_Store
Thumbs.db
# Build artifacts
.build/
schema_version: "1.0"
repo: my-new-repo
organ: IV
tier: standard
promotion_status: LOCAL
produces:
- event: repo.created
schema: v1
consumes:
- from: orchestration-start-here
event: governance.updated
ci:
- name: lint-test
trigger: push
agent: github-actions
# .github/workflows/ci.yml
name: CI
on: [push, pull_request]
jobs:
lint-test:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ["3.11", "3.12"]
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- run: pip install -e ".[dev]"
- run: ruff check .
- run: pytest tests/ -v
# .pre-commit-config.yaml
repos:
- repo: https://github.com/astral-sh/ruff-pre-commit
rev: v0.5.0
hooks:
- id: ruff
args: [--fix]
- id: ruff-format
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v4.6.0
hooks:
- id: trailing-whitespace
- id: end-of-file-fixer
- id: check-yaml
- id: check-json
- id: detect-private-key
# {Repo Name}
{One-sentence description of what this does and why it exists.}
## Quick Start
### Prerequisites
- Python 3.11+
- {other prerequisites}
### Installation
\`\`\`bash
git clone {url}
cd {repo}
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
\`\`\`
### Usage
\`\`\`bash
{first command to run}
\`\`\`
## Architecture
{Brief description or diagram of how it works.}
## Development
\`\`\`bash
pytest tests/ -v # Run tests
ruff check . # Lint
\`\`\`
## System Context
**Organ:** {organ} | **Tier:** {tier} | **Status:** {status}
# CLAUDE.md
## Repository Overview
{What this repo does, in context of the larger system.}
## Development Commands
\`\`\`bash
{specific commands for this repo}
\`\`\`
## Architecture
{Key patterns and decisions.}
## Key Constraints
{Things Claude needs to know to work safely in this repo.}
def register_repo(registry_path: str, repo: dict):
registry = json.loads(Path(registry_path).read_text())
# Validate minimum fields
assert repo["name"], "Name required"
assert repo["organ"] in VALID_ORGANS, f"Invalid organ: {repo['organ']}"
assert repo["tier"] in VALID_TIERS, f"Invalid tier: {repo['tier']}"
registry["repos"].append(repo)
Path(registry_path).write_text(json.dumps(registry, indent=2))
# In seed.yaml, declare edges
consumes:
- from: orchestration-start-here
event: governance.updated
- from: meta/organvm-engine
event: registry.refreshed
produces:
- event: my-repo.deployed
schema: v1
def validate_onboarding(repo_path: str) -> list[str]:
issues = []
p = Path(repo_path)
# Core files
for f in ["README.md", "LICENSE", ".gitignore", "seed.yaml"]:
if not (p / f).exists():
issues.append(f"Missing: {f}")
# seed.yaml valid
if (p / "seed.yaml").exists():
seed = yaml.safe_load((p / "seed.yaml").read_text())
for field in ["schema_version", "repo", "organ", "tier", "promotion_status"]:
if field not in seed:
issues.append(f"seed.yaml missing: {field}")
# CI exists
if not list((p / ".github/workflows").glob("*.yml")):
issues.append("No CI workflow found")
# README quality
readme = (p / "README.md").read_text() if (p / "README.md").exists() else ""
if len(readme.split()) < 50:
issues.append("README too short (< 50 words)")
return issues
After onboarding, run the stranger-test-protocol against the README and documentation to verify a newcomer can understand the repository.
| Status | Requirements | |--------|-------------| | LOCAL | seed.yaml + README + .gitignore | | CANDIDATE | + CI passing + tests + CLAUDE.md | | PUBLIC_PROCESS | + Stranger test passed + full docs | | GRADUATED | + Production usage + monitoring |
development
Optimize resumes and CVs for impact, ATS compatibility, and audience targeting. Supports multiple formats (chronological, functional, hybrid), accomplishment framing (STAR/XYZ), and tailoring for specific roles. Triggers on resume review, CV update, job application prep, or career document requests.
testing
Transfer context between AI agent sessions with structured handoff protocols, state serialization, and decision log preservation. Covers multi-agent coordination, context compression, and continuity patterns. Triggers on agent handoff, session transfer, or multi-agent continuity requests.
tools
Craft compelling fiction and creative nonfiction with attention to structure, voice, prose style, and revision. Supports short stories, novel chapters, essays, and hybrid forms. Triggers on creative writing, fiction writing, story craft, prose style, or literary technique requests.
devops
Transform AI conversations and chat transcripts into publishable content including blog posts, documentation, tutorials, and knowledge base entries. Covers extraction, restructuring, and editorial refinement. Triggers on conversation-to-content, transcript processing, or chat-to-doc requests.