Skip to content
Agentmart
Submit a tool

boilerplate

Use when starting a new project from scratch.

Skill by tsergeytovarov

IndexedMIT★ 15
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/tsergeytovarov-boilerplate

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when starting a new project from scratch. Scaffolds project structure from public template repo, creates GitHub repo, copies AI settings snapshot, and generates a ready-to-execute deployment runbook for the Yandex Cloud VM. Trigger: user calls /popovs:boilerplate or says "создать новый проект / развернуть проект". SKIP: if the project is already initialized (git repo exists, files present).

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/boilerplate

What's inside

Skill name
boilerplate
Description
Use when starting a new project from scratch. Scaffolds project structure from public template repo, creates GitHub repo, copies AI settings snapshot, and generates a ready-to-execute deployment runbook for the Yandex Cloud VM. Trigger: user calls /popovs:boilerplate or says "создать новый проект / развернуть проект". SKIP: if the project is already initialized (git repo exists, files present).
License
MIT
Instructions
304 lines in SKILL.md · view on GitHub

Files (3)

  • CHANGELOG.md
  • README.md
  • SKILL.md

SKILL.md (first lines)

# Purpose

Bootstrap a new project in one command: scaffold template, create GitHub repo,
copy AI rules snapshot, generate deployment runbook.

# Template Repository

`https://github.com/tsergeytovarov/popovs-boilerplate`

Each stack directory contains a `meta.yaml` with name, description, tags.
New stacks can be added to the repo — they appear in the list automatically.

# Process

## Step 1: Clone template repo

```bash
git clone --depth=1 https://github.com/tsergeytovarov/popovs-boilerplate /tmp/popovs-boilerplate-template
```

## Step 2: Show available stacks

Read `meta.yaml` from each subdirectory (skip `shared/` and any hidden dirs), present numbered list:

```
Доступные стеки:
1. Next.js + FastAPI — Full-stack: Next.js 15 frontend + FastAPI backend + PostgreSQL 16 + Docker Compose
2. FastAPI Backend — Backend only: FastAPI + PostgreSQL 16 + Docker Compose. Без фронтенда.
3. Landing Page — Статический сайт: HTML/CSS/JS.
4. Docs / Research — Документация и ресёрч: MkDocs Material.
```

## Step 3: Ask questions ONE AT A TIME

Ask each question separately, wait for answer before asking the next:

1. **Имя проекта?** (будет использовано как имя GitHub репо и плейсхолдер `{{PROJECT_NAME}}` в файлах)
2. **Стек?** (показать список из meta.yaml, пронумерованный)
3. **Видимость GitHub?** `public` / `private` (default: `private`)
4. **Домен?** (пример: `my-project.popovs.tech`)

After answers, compute:
- `{{SUBDOMAIN}}` = part of domain before first dot (e.g. `my-project` from `my-project.popovs.tech`)
- `{{YEAR}}` = current year

## Step 4: Copy template files

```bash
# Copy shared/ files (base structure for all stacks)
cp -r /tmp/popovs-boilerplate-template/shared/. ./

# Copy chosen stack files (overrides shared if same filename)
cp -r /tmp/popovs-boilerplate-template/<chosen-stack>/. ./

# Substitute all placeholders in all text files
find . -type f \( -name "*.py" -o -name "*.tsx" -o -name "*.ts" -o -name "*.js" \
  -o -name "*.json" -o -name "*.yml" -o -name "*.yaml" -o -name "*.conf" \
  -o -name "*.md" -o -name "*.html" -o -name "*.css" -o -name "*.txt" \
  -o -name "*.xml" -o -name ".env.example" -o -name "Makefile" \) \
  -not -path "*/node_modules/*" \
  -exec sed -i '' \
    "s/{{PROJECT_NAME}}/$PROJECT_NAME/g; \
     s/{{DOMAIN}}/$DOMAIN/g; \
     s/{{SUBDOMAIN}}/$SUBDOMAIN/g; \
     s/{{YEAR}}/$YEAR/g" {} \;
```

## Step 5: Copy AI settings snapshot

```bash
AI_SETTINGS=~/Desktop/projects/ai-settings

# docs/ai/ — all AI rules
mkdir -p docs/ai
cp -r $AI_SETTINGS/docs/ai/. docs/ai/

# Agent config files
cp $AI_SETTINGS/AGENTS.md ./AGENTS.md
cp $AI_SETTINGS/CLAUDE.md ./CLAUDE.md

# Claude Code settings
mkdir -p .claude
cp $AI_SETTINGS/.claude/settings.local.json ./.claude/settings.json

# Generate .claude/CLAUDE.md with model hints and MCP guard
cat > .claude/CLAUDE.md << 'EOF'
## Подсказки по модели и усилию

В конце каждого ответа, где предлагается следующий шаг или запускается задача, добавляй подсказку формата:

> 💡 *Для этого подойдёт **[модель]** + **[effort]***

Маппинг:
- **Haiku** — поиск по кодовой базе, explore-агенты, bash-команды, саммари, простые правки. Effort: не нужен.
- **Sonnet** — большинство задач: коммиты, PR, объяснения, скилы, планирование, рефакторинг. Effort: medium (по умолчанию).
- **Opus** — архитектурные решения, глубокий code review, дизайн-ревью, сложный дебаг, длинный контекст, ресёрч. Effort: high или xhigh.

Effort уровни: `low` / `medium` / `high` / `xhigh` — переключаются командой `/effort`.
Модель — командой `/model`.

Подсказку давай кратко, одной строкой, только когда уместно.

## MCP-серверы

Не вызывай инструменты MCP-серверов (Notion, Confluence, Claude_in_Chrome, scheduled-tasks) без явной просьбы пользователя.
EOF
```

## Step 6: Generate docs/DEPLOY.md

Read `~/Desktop/projects/infra/runbook.md` for exact commands.

Generate `docs/DEPLOY.md` using the stack-specific template from the **Deploy Instructions** section below.

Substitute `{{PROJECT_NAME}}`, `{{DOMAIN}}`, `{{SUBDOMAIN}}` with actual values collected in Step 3.

## Step 7: Create GitHub repo and push

```bash

From tsergeytovarov/ai-settings, MIT.

More from tsergeytovarov/ai-settings

Signals

Stars
15
Forks
4
Open issues
2
Last commit (this folder)
Apr 20, 2026 (6 months ago)
Last release
Oct 12, 2026 (16 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from tsergeytovarov

Cite this page

boilerplate skill. Agent Mart. https://agentmart.dev/skills/tsergeytovarov-boilerplate (last updated 2026-10-24)