claude-automation-recommender

Claude Automation Recommender

Analyze codebase patterns to recommend tailored Claude Code automations across all extensibility options.

This skill is read-only. It analyzes the codebase and outputs recommendations. It does NOT create or modify any files. Users implement the recommendations themselves or ask Claude separately to help build them.

Output Guidelines

• Recommend 1-2 of each type: Don't overwhelm - surface the top 1-2 most valuable automations per category
• If user asks for a specific type: Focus only on that type and provide more options (3-5 recommendations)
• Go beyond the reference lists: The reference files contain common patterns, but use web search to find recommendations specific to the codebase's tools, frameworks, and libraries
• Tell users they can ask for more: End by noting they can request more recommendations for any specific category

Automation Types Overview

Workflow

Phase 0: Confirm Before Scanning（Cherry Studio addition）

This scan reads many files (package.json, source structure, .claude/, framework configs, dependencies) and produces detailed analysis. It is token-intensive — a typical run on a medium-sized repo consumes 20–40K tokens of model context, plus model output for the recommendations themselves.

Before doing any filesystem reads or Bash calls, you MUST:

1. Announce the scan plan in one short paragraph: what dirs/files you will read, why each is needed, and the token-budget estimate. Example phrasing:

   我准备扫描当前工作目录的 package.json/pyproject.toml/go.mod 等清单文件 + src/ tests/ 项目结构 + 已有的 .claude/ 配置 + CLAUDE.md，给出 hook / subagent / skill / MCP 推荐。预计消耗 ~30K tokens（实际取决于仓库大小）。

2. Ask explicit confirmation with a clear yes/no question — in Cherry Studio the chat UI surfaces this as a confirmation button:

   继续扫描吗？ / Proceed with scan?

3. Wait for explicit "yes" / "继续" / "go ahead" before proceeding to Phase 1. Treat anything ambiguous as a no.

4. If the user declines or hesitates, offer alternatives:

   • Narrower scope: scan only one directory the user names → smaller budget
   • Verbal-only: skip the scan, recommend based on what the user describes (project type, frameworks, pain points)
   • Defer: note the request to memory/FACT.md so a future session can pick it up without re-asking

5. Skip Phase 0 only if the user has already explicitly granted scan permission earlier in the same session (e.g. their first message was "scan my repo and recommend automations now").

Only after explicit confirmation, proceed with Phase 1 below.

Phase 1: Codebase Analysis

Gather project context:

# Detect project type and tools
ls -la package.json pyproject.toml Cargo.toml go.mod pom.xml 2>/dev/null
cat package.json 2>/dev/null | head -50

# Check dependencies for MCP server recommendations
cat package.json 2>/dev/null | grep -E '"(react|vue|angular|next|express|fastapi|django|prisma|supabase|stripe)"'

# Check for existing Claude Code config
ls -la .claude/ CLAUDE.md 2>/dev/null

# Analyze project structure
ls -la src/ app/ lib/ tests/ components/ pages/ api/ 2>/dev/null

Key Indicators to Capture:

Phase 2: Generate Recommendations

Based on analysis, generate recommendations across all categories:

A. MCP Server Recommendations

See references/mcp-servers.md for detailed patterns.

B. Skills Recommendations

See references/skills-reference.md for details.

Create skills in .claude/skills/<name>/SKILL.md. Some are also available via plugins:

Custom skills to create (with templates, scripts, examples):

C. Hooks Recommendations

See references/hooks-patterns.md for configurations.

D. Subagent Recommendations

See references/subagent-templates.md for templates.

E. Plugin Recommendations

See references/plugins-reference.md for available plugins.

Phase 3: Output Recommendations Report

Format recommendations clearly. Only include 1-2 recommendations per category - the most valuable ones for this specific codebase. Skip categories that aren't relevant.

## Claude Code Automation Recommendations

I've analyzed your codebase and identified the top automations for each category. Here are my top 1-2 recommendations per type:

### Codebase Profile
- **Type**: [detected language/runtime]
- **Framework**: [detected framework]
- **Key Libraries**: [relevant libraries detected]

---

### 🔌 MCP Servers

#### context7
**Why**: [specific reason based on detected libraries]
**Install**: `claude mcp add context7`

---

### 🎯 Skills

#### [skill name]
**Why**: [specific reason]
**Create**: `.claude/skills/[name]/SKILL.md`
**Invocation**: User-only / Both / Claude-only
**Also available in**: [plugin-name] plugin (if applicable)
```yaml
---
name: [skill-name]
description: [what it does]
disable-model-invocation: true  # for user-only
---

⚡ Hooks

[hook name]

Why: [specific reason based on detected config] Where: .claude/settings.json

🤖 Subagents

[agent name]

Why: [specific reason based on codebase patterns] Where: .claude/agents/[name].md

Want more? Ask for additional recommendations for any specific category (e.g., "show me more MCP server options" or "what other hooks would help?").

Want help implementing any of these? Just ask and I can help you set up any of the recommendations above.

## Decision Framework

### When to Recommend MCP Servers
- External service integration needed (databases, APIs)
- Documentation lookup for libraries/SDKs
- Browser automation or testing
- Team tool integration (GitHub, Linear, Slack)
- Cloud infrastructure management

### When to Recommend Skills

- Frequently repeated prompts or workflows
- Project-specific tasks with arguments
- Applying templates or scripts to tasks (skills can bundle supporting files)
- Quick actions invoked with `/skill-name`
- Workflows that should run in isolation (`context: fork`)

**Invocation control:**
- `disable-model-invocation: true` — User-only (for side effects: deploy, commit, send)
- `user-invocable: false` — Claude-only (for background knowledge)
- Default (omit both) — Both can invoke

### When to Recommend Hooks
- Repetitive post-edit actions (formatting, linting)
- Protection rules (block sensitive file edits)
- Validation checks (tests, type checks)

### When to Recommend Subagents
- Specialized expertise needed (security, performance)
- Parallel review workflows
- Background quality checks

### When to Recommend Plugins
- Need multiple related skills
- Want pre-packaged automation bundles
- Team-wide standardization

---

## Configuration Tips

### MCP Server Setup

**Team sharing**: Check `.mcp.json` into repo so entire team gets same MCP servers

**Debugging**: Use `--mcp-debug` flag to identify configuration issues

**Prerequisites to recommend:**
- GitHub CLI (`gh`) - enables native GitHub operations
- Puppeteer/Playwright CLI - for browser MCP servers

### Headless Mode (for CI/Automation)

Recommend headless Claude for automated pipelines:

```bash
# Pre-commit hook example
claude -p "fix lint errors in src/" --allowedTools Edit,Write

# CI pipeline with structured output
claude -p "<prompt>" --output-format stream-json | your_command

Permissions for Hooks

Configure allowed tools in .claude/settings.json:

{
  "permissions": {
    "allow": ["Edit", "Write", "Bash(npm test:*)", "Bash(git commit:*)"]
  }
}