ReddRadar
Agent skill
init-rules
Initialize or update CLAUDE.md coding standards for any project by auto-detecting tech stack and assembling rules from the claude-rules template library. Use when user says "init rules", "初始化规范", "生成 CLAUDE.md", or wants to set up coding standards.
Install this agent skill to your Project
npx add-skill https://github.com/lifedever/claude-rules/tree/main/.claude/skills/init-rules
SKILL.md
Init Claude Rules
IMPORTANT: You MUST read rule files from this skill's bundled files. Do NOT generate rules from your own knowledge.
Rule files are bundled in this skill's directory. Use ${CLAUDE_SKILL_DIR} to reference them.
Workflow
Step 1: Detect Tech Stack
Scan the current working directory to identify languages and frameworks:
| Signal | Rule File |
|---|---|
tsconfig.json or *.ts files |
languages/typescript.md |
package.json with "vue" dependency |
frameworks/vue.md |
package.json with "react" dependency |
frameworks/react.md |
src-tauri/ directory |
frameworks/tauri.md |
*.js files without tsconfig.json |
languages/javascript.md |
*.java files or pom.xml |
languages/java.md |
build.gradle.kts or *.kt files |
languages/kotlin.md |
pom.xml/build.gradle with spring-boot |
frameworks/springboot.md |
Package.swift or *.swift files |
languages/swift.md |
Swift files with import SwiftUI |
frameworks/swiftui.md |
pyproject.toml or requirements.txt |
languages/python.md |
*.html files |
languages/html.md |
*.css/*.scss files |
languages/css.md |
go.mod or *.go files |
languages/go.md |
Cargo.toml or *.rs files |
languages/rust.md |
Present detection results and ask user to confirm or adjust before proceeding.
Step 2: Read Rule Files
Read files from this skill's bundled directory using the Read tool.
Always read:
${CLAUDE_SKILL_DIR}/base/core.md${CLAUDE_SKILL_DIR}/base/git.md
Then read each detected language and framework file, e.g.:
${CLAUDE_SKILL_DIR}/languages/typescript.md${CLAUDE_SKILL_DIR}/frameworks/vue.md
Step 3: Assemble & Write CLAUDE.md
Concatenate ALL fetched content in this exact order:
<!-- Generated by init-claude-rules | https://github.com/lifedever/claude-rules -->- Empty line
- Content of
base/core.md - Content of
base/git.md - Each detected language file
- Each detected framework file
Write to CLAUDE.md in the current working directory.
If CLAUDE.md already exists, warn user and ask before overwriting.
Step 4: Report
- List included rule files
- Total line count
- Remind user to run
claude plugin marketplace update claude-rulesto get latest rules
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
davila7/claude-code-templates
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
davila7/claude-code-templates
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
davila7/claude-code-templates
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
davila7/claude-code-templates
Claude Code Guide
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
davila7/claude-code-templates
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
davila7/claude-code-templates
behavioral-modes
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
Didn't find tool you were looking for?