A template repository for bootstrapping Claude Code configuration in any project. Includes 42 generic skills, 7 agents, and 4 rules.
# Option 1: Remote install — macOS / Linux
curl -fsSL https://raw.githubusercontent.com/eiei114/claude-code-template/main/install.sh | bash
# Option 1: Remote install — Windows (PowerShell, requires WSL or Git Bash)
Invoke-WebRequest -Uri "https://raw.githubusercontent.com/eiei114/claude-code-template/main/install.sh" -OutFile "install.sh"; bash install.sh
# Option 2: Clone and run locally
git clone https://github.com/eiei114/claude-code-template.git
cd /path/to/your/project
bash /path/to/claude-code-template/install.sh
# Option 3: Use as GitHub template
# Click "Use this template" on the repo page, then run install.sh| Skill | Description |
|---|---|
| ai-prompt-engineering-safety-review | AI prompt safety review and improvement |
| algorithmic-art | Generative art with p5.js |
| brainstorming | Creative exploration before implementation |
| brand-guidelines | Apply brand colors and typography |
| canvas-design | Visual art and poster creation |
| claude-api | Build apps with Claude API / Anthropic SDK |
| csharp-nunit | NUnit testing best practices |
| dispatching-parallel-agents | Parallel task execution with isolated contexts |
| doc-coauthoring | Structured documentation co-authoring |
| docx | Word document processing |
| executing-plans | Implementation plan execution |
| finishing-a-development-branch | Branch completion workflow |
| frontend-design | Production-grade frontend interfaces |
| grill-me | Interview-based design verification |
| internal-comms | Internal communication templates |
| java-junit | JUnit 5 testing best practices |
| mcp-builder | MCP server development guide |
| PDF processing | |
| playwright-explore-website | Website exploration for testing |
| playwright-generate-test | Playwright test generation |
| pptx | PowerPoint creation and editing |
| prd-to-issues | Break PRD into GitHub issues |
| prd-to-plan | Turn PRD into implementation plan |
| receiving-code-review | Handle code review feedback |
| requesting-code-review | Code review request workflow |
| skill-creator | Create and optimize skills |
| skill-forge | Skill improvement with evals |
| slack-gif-creator | Animated GIFs for Slack |
| subagent-driven-development | Execute plans with independent subagents |
| systematic-debugging | Systematic debugging methodology |
| template | Empty skill template |
| test-driven-development | TDD methodology |
| theme-factory | Styling with professional themes |
| using-git-worktrees | Git worktree workflows |
| using-superpowers | Skill discovery and usage guide |
| verification-before-completion | Verification before claiming done |
| web-artifacts-builder | Complex web artifacts (React/Tailwind) |
| webapp-testing | Local web app testing with Playwright |
| write-a-prd | Create PRDs through user interview |
| writing-plans | Multi-step implementation plans |
| writing-skills | Test-driven skill writing |
| xlsx | Spreadsheet processing |
| Agent | Description |
|---|---|
| tdd-red | Write failing tests first (TDD Red phase) |
| tdd-green | Minimal implementation to pass tests (TDD Green phase) |
| tdd-refactor | Improve quality while keeping tests green (TDD Refactor phase) |
| codex-debugger | Error analysis via Codex CLI |
| codex-analyst | Deep analysis via Codex CLI |
| playwright-tester | Playwright test automation |
| gemini-researcher | External research via Gemini CLI |
| Rule | Description |
|---|---|
| language.md | Bilingual (Japanese/English) language rules |
| session-bug-tracking.md | Session file and bug tracking conventions |
| todo-tracking.md | TODO.md tracking rules |
| branch-strategy.md | Git branch strategy (feature/fix/develop/main) |
| Template | Description |
|---|---|
| CLAUDE.md.template | Project CLAUDE.md skeleton with placeholders |
| settings.json.template | Basic settings.json skeleton |
| Flag | Description |
|---|---|
--force |
Overwrite existing files |
--skip-skills |
Skip skill installation |
--skip-agents |
Skip agent installation |
--skip-rules |
Skip rule installation |
--takt |
Run npx create-takt-sdd --lang ja after install |
--takt-skills |
Install TAKT skills via npx skills add j5ik2o/ai-tools |
- Edit
CLAUDE.mdto describe your project - Customize
.claude/rules/for your conventions - Add project-specific rules (tech conventions, delegation patterns, etc.)
TAKT and Spec-Driven Development workflows are installed separately:
# SDD workflows (pieces + facets)
npx create-takt-sdd --lang ja
# TAKT skills for Claude Code
npx -y skills add j5ik2o/ai-tools --skill takt-analyzer
npx -y skills add j5ik2o/ai-tools --skill takt-task-builder
# ... or use --takt-skills flag during installSee j5ik2o/takt-sdd for details.
Re-run install.sh to update. Existing files are skipped by default.
Use --force to overwrite with the latest versions.
Some skills and agents depend on external CLI tools:
| Tool | Used by | Install |
|---|---|---|
| Codex CLI | codex-debugger, codex-analyst | codex CLI |
| Gemini CLI | gemini-researcher | gemini CLI |
| Playwright MCP | playwright-tester | Playwright MCP server |
These are optional — the template works without them, but relevant skills/agents won't function.
MIT