Skill69 estrellas del repoactualizado 2mo ago

claude-md-template

Generate CLAUDE.md template for current project

Ver fuente Repositorio: director-mode-lite

Instalar en Claude Code

Copiar

git clone --depth 1 https://github.com/claude-world/director-mode-lite /tmp/claude-md-template && cp -r /tmp/claude-md-template/skills/claude-md-template ~/.claude/skills/claude-md-template

Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

Definición

SKILL.md

# CLAUDE.md Template Generator

Generate a customized CLAUDE.md template based on detected project type.

---

## Detection

1. **Language**: package.json, requirements.txt, Cargo.toml, go.mod
2. **Framework**: Parse dependencies
3. **Package Manager**: npm, pnpm, yarn, pip, cargo
4. **Test Framework**: jest, pytest, cargo test
5. **Existing Patterns**: .eslintrc, .prettierrc, tsconfig.json

---

## Template Structure

```markdown
# [Project Name] - Project Instructions

## Overview
[Auto-detected description]

## Tech Stack
| Category | Technology |
|----------|------------|
| Language | [detected] |
| Framework | [detected] |

## Development Commands
- Install: [detected]
- Dev: [detected]
- Test: [detected]
- Build: [detected]

## Project Structure
[Auto-generated tree]

## Coding Conventions
[Inferred from configs]

## Key Files
| File | Purpose |
|------|---------|
| [entry] | Main entry |

## Director Mode Commands
- /workflow - Start development
- /auto-loop - Autonomous TDD
```

---

## After Generation

1. Show generated CLAUDE.md
2. Highlight [TODO] sections
3. Offer to run `/claude-md-check`

Del mismo repositorio

changelog-observerSkill

Track development session events in a daily markdown changelog, including file changes, test results, and key decisions.

agents-expertSubagent

Expert on creating and configuring custom Claude Code agents. Helps design specialized agents for project-specific tasks.

claude-md-expertSubagent

Expert on CLAUDE.md design patterns, best practices, and project configuration. Essential for project initialization and customization.

code-reviewerSkill

Code review specialist for quality, security, and best practices

completion-judgeSubagent

Decision-making agent for Self-Evolving Loop. Evaluates validation results and decides next action (continue, evolve, or ship).

debuggerSkill

Debugging specialist for root cause analysis and problem resolution

doc-writerSkill

Documentation specialist for README, API docs, and code comments

evolving-orchestratorSubagent

Lightweight orchestrator for Self-Evolving Loop with Meta-Engineering integration. Coordinates phases, manages memory, and handles lifecycle. Only returns brief summaries.