跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
浏览器与自动化

claude-automation-recommender

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.

CherryHQ · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add CherryHQ/cherry-studio --skill claude-automation-recommender

技能说明


name: claude-automation-recommender description: Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use. allowed-tools: Read, Glob, Grep, Bash

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

TypeBest For
HooksAutomatic actions on tool events (format on save, lint, block edits)
SubagentsSpecialized reviewers/analyzers that run in parallel
SkillsPackaged expertise, workflows, and repeatable tasks (invoked by Claude or user via /skill-name)
PluginsCollections of skills that can be installed
MCP ServersExternal tool integrations (databases, APIs, browsers, docs)

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:

CategoryWhat to Look ForInforms Recommendations For
Language/Frameworkpackage.json, pyproject.toml, import patternsHooks, MCP servers
Frontend stackReact, Vue, Angular, Next.jsPlaywright MCP, frontend skills
Backend stackExpress, FastAPI, DjangoAPI documentation tools
DatabasePrisma, Supabase, raw SQLDatabase MCP servers
External APIsStripe, OpenAI, AWS SDKscontext7 MCP for docs
TestingJest, pytest, Playwright configsTesting hooks, subagents
CI/CDGitHub Actions, CircleCIGitHub MCP server
Issue trackingLinear, Jira referencesIssue tracker MCP
Docs patternsOpenAPI, JSDoc, docstringsDocumentation skills

Phase 2: Generate Recommendations

Based on analysis, generate recommendations across all categories:

A. MCP Server Recommendations

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

Codebase SignalRecommended MCP Server
Uses popular libraries (React, Express, etc.)context7 - Live documentation lookup
Frontend with UI testing needsPlaywright - Browser automation/testing
Uses SupabaseSupabase MCP - Direct database operations
PostgreSQL/MySQL databaseDatabase MCP - Query and schema tools
GitHub repositoryGitHub MCP - Issues, PRs, actions
Uses Linear for issuesLinear MCP - Issue management
AWS infrastructureAWS MCP - Cloud resource management
Slack workspaceSlack MCP - Team notifications
Memory/context persistenceMemory MCP - Cross-session memory
Sentry error trackingSentry MCP - Error investigation
Docker containersDocker MCP - Container manag
阅读完整来源 ↗