agentleFS
SwastikPandey1024SwastikPandey1024/agentic-engineering-os/.agents/skills/project-bootstrap/SKILL.md

project-bootstrap

Skill1 starsChanged 3 months agoMITView on GitHub

Full 17-step lifecycle orchestrator for new and existing projects, environment initialization, stack selection, baseline documentation, and release readiness.

  • Reads credentials

40 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use delivery-planning, diagnose and 4 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • lzx-BillSkill

    delivery-planning

    Use when breaking work into tasks, planning milestones, mapping dependencies, sequencing implementation, or maintaining backlog and in-progress views. Trigger when user says "task breakdown", "milestone", "dependencies", "backlog", "sprint", "implementation plan", "delivery plan", or asks to "break this down into tasks". Coordinate with prompt-authoring for task-to-prompt mapping and with acceptance-design for task-to-acceptance mapping.

    Also in 3 projects that use this

  • MicrosoftSkill

    diagnose

    Use to systematically diagnose why scenarios fail — identifies root causes by analyzing agent traces, codebase, and behavioral patterns

    Also in 3 projects that use this

  • MicrosoftSkill

    api-design

    Guide for designing and documenting RESTful APIs. Use when asked to design an API, create endpoints, or document an API.

    Also in 3 projects that use this

  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 3 projects that use this

  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 3 projects that use this

  • +1 more from google

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 32 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when:

    line 10
  2. Distinctive:

    Workspace State: Ensure clean directory tree before initializing files.

    line 26
  3. Very specific:

    Create pyproject.toml with separate runtime and dev dependencies:

    line 123
  4. Very specific:

    Create directory tree and populate .gitignore:

    line 160
  5. Very specific:

    Create tests/conftest.py with FastAPI TestClient fixture.

    line 183
  6. Very specific:

    NEVER commit .venv/ or raw datasets without .gitkeep: Ensure .gitignore is populated immediately.

    line 202
  7. Very specific:

    NEVER omit .env.example: Always maintain sanitized configuration templates.

    line 204

“Common” is measured: kept by at least 6 in 10 of the 32 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Project Bootstrap Skill (V2 Lifecycle Orchestrator)

1. When Should I Use This?

Use this skill when:

  • Bootstrapping any brand-new software project, repository, microservice, or system from scratch.
  • Orchestrating the end-to-end initialization workflow across architecture, environment, tooling, documentation, and security.
  • Restructuring or standardizing an existing disorganized codebase into a production-grade system.

2. What Should I Inspect First?

  1. Target Domain & Archetype:
    • Python Backend API (FastAPI)
    • Fullstack Application (React 19 + TypeScript + FastAPI/Node)
    • Machine Learning / Deep Learning Research Platform
    • Time-Series / Data Engineering Platform
    • Small CLI / Automation Script
  2. Runtime & Hardware Constraints: Python version (>=3.11/3.12), Node.js (>=20), GPU availability (nvidia-smi), target hosting platform.
  3. Workspace State: Ensure clean directory tree before initializing files.

3. What Workflow Should I Follow?

┌─────────────────────────────────────────────────────────────┐
│ 1. CLASSIFY PROJECT (Utility vs ML vs Fullstack vs Prod)    │
└──────────────────────────────┬──────────────────────────────┘
                               │
┌──────────────────────────────▼──────────────────────────────┐
│ 2. SELECT TECH STACK (FastAPI, React, PostgreSQL, uv, etc.) │
└──────────────────────────────┬──────────────────────────────┘
                               │
┌──────────────────────────────▼──────────────────────────────┐
│ 3. ENVIRONMENT SETUP (Create .venv FIRST before packages)   │
└──────────────────────────────┬──────────────────────────────┘
                               │
┌──────────────────────────────▼──────────────────────────────┐
│ 4. DEPENDENCY SETUP (pyproject.toml, uv.lock, package.json) │
└──────────────────────────────┬──────────────────────────────┘
                               │
┌──────────────────────────────▼──────────────────────────────┐
│ 5. REPOSITORY STRUCTURE (Standard layered directories)      │
└──────────────────────────────┬──────────────────────────────┘
                               │
┌──────────────────────────────▼──────────────────────────────┐
│ 6. CONFIGURE AGENTS.md & RELEVANT SKILLS (.agents/skills/)  │
└──────────────────────────────┬──────────────────────────────┘
                               │
┌──────────────────────────────▼──────────────────────────────┐
│ 7. CHECK MCP AVAILABILITY (Memory, Database, DevTools)      │
└──────────────────────────────┬──────────────────────────────┘
                               │
┌──────────────────────────────▼──────────────────────────────┐
│ 8. DOCUMENTATION PLAN (Adaptive minimum documentation suite)│
└──────────────────────────────┬──────────────────────────────┘
                               │
┌──────────────────────────────▼──────────────────────────────┐
│ 9. TESTING PLAN (Pytest harness, conftest.py, test fixtures)│
└──────────────────────────────┬──────────────────────────────┘
                               │
┌──────────────────────────────▼──────────────────────────────┐
│ 10. SECURITY BASELINE (.env.example, SecretStr, .gitignore) │
└──────────────────────────────┬──────────────────────────────┘
                               │
┌──────────────────────────────▼──────────────────────────────┐
│ 11. OBSERVABILITY BASELINE (Structured JSON logs, req IDs)  │
└──────────────────────────────┬──────────────────────────────┘
                               │
┌──────────────────────────────▼──────────────────────────────┐
│ 12. IMPLEMENTATION (Domain logic, routes, schemas, models)  │
└──────────────────────────────┬──────────────────────────────┘
                               │
┌──────────────────────────────▼──────────────────────────────┐
│ 13. VERIFICATION (Unit, integration, and linting suites)    │
└──────────────────────────────┬──────────────────────────────┘
                               │
┌──────────────────────────────▼──────────────────────────────┐
│ 14. DOCUMENTATION EXECUTION (README, ARCHITECTURE, ADRs)    │
└──────────────────────────────┬──────────────────────────────┘
                               │
┌──────────────────────────────▼──────────────────────────────┐
│ 15. RELEASE READINESS (SemVer, Dockerfile, CI workflow)     │
└─────────────────────────────────────────────────────────────┘

4. Detailed Execution Steps

Step 1: Classify & Select Stack

Determine the project archetype and lock in the toolchain:

  • Python API: FastAPI + Pydantic v2 + SQLAlchemy/Prisma + uv
  • Frontend: React 19 + TypeScript + Vite + Tailwind CSS + TanStack Query
  • ML / Data: Scikit-Learn / XGBoost / PyTorch / Pandas / Parquet

Step 2: Environment Setup (CRITICAL: Before Dependencies)

# 1. Pin Python version
echo "3.12" > .python-version

# 2. Create isolated virtual environment
uv venv .venv --python 3.12

# 3. Configure IDE interpreter
mkdir -p .vscode
cat << 'EOF' > .vscode/settings.json
{
  "python.defaultInterpreterPath": "${workspaceFolder}/.venv/bin/python",
  "python.analysis.typeCheckingMode": "basic"
}
EOF

Step 3: Dependency Setup & Manifests

Create pyproject.toml with separate runtime and dev dependencies:

[project]
name = "my-service"
version = "0.1.0"
requires-python = ">=3.12"
dependencies = [
    "fastapi>=0.110.0,<1.0.0",
    "pydantic>=2.7.0,<3.0.0",
    "pydantic-settings>=2.2.0",
    "uvicorn>=0.28.0",
]

[project.optional-dependencies]
dev = [
    "pytest>=8.0.0",
    "pytest-cov>=5.0.0",
    "ruff>=0.3.0",
    "mypy>=1.9.0",
    "httpx>=0.27.0",
]

[tool.ruff]
line-length = 88
target-version = "py312"

[tool.pytest.ini_options]
testpaths = ["tests"]
addopts = "-v --tb=short"
# Sync dependencies and generate lockfile
uv sync

Step 4: Repository Layout & Git Hygiene

Create directory tree and populate .gitignore:

mkdir -p app/{api/v1/{routes,schemas,dependencies},core,services,models,utils} tests/{unit,integration} docs/decisions
# .gitignore
.venv/
__pycache__/
*.pyc
.env
.env.local
.pytest_cache/
.coverage
dist/
build/
datasets/raw/*
!datasets/raw/.gitkeep

Step 5: Universal Governance & Quality Baselines

  1. Copy or symlink AGENTS.md and .agents/skills/.
  2. Generate .env.example with sanitized placeholder keys.
  3. Create tests/conftest.py with FastAPI TestClient fixture.
  4. Set up structured logging with correlation IDs in app/core/logging.py.
  5. Set up health probe /api/v1/health in app/main.py.

4. What Decisions Should I Make?

Decision PointStandard Recommendation
Virtual Environment CreationALWAYS create .venv/ BEFORE running any pip or uv add commands.
Documentation ScopeDetermine minimum document suite using documentation-orchestrator.
Package ManagerDefault to uv for new Python projects.

5. What Should I Avoid?

  • NEVER install dependencies before creating .venv/: Environment initialization must precede package installation.
  • NEVER commit .venv/ or raw datasets without .gitkeep: Ensure .gitignore is populated immediately.
  • NEVER create monolith god-files: Split endpoints, services, schemas, and models from day one.
  • NEVER omit .env.example: Always maintain sanitized configuration templates.

6. How Should I Verify Success?

# 1. Confirm environment isolation
python -c "import sys; assert '.venv' in sys.executable, 'CRITICAL: Global python detected!'"

# 2. Run initial test suite
uv run pytest -v

# 3. Check linting and formatting
uv run ruff check .
uv run ruff format --check .

# 4. Check git status
git status

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.