Claude Automation Recommender
Scan your repository read-only and get prioritized Claude Code hooks, subagents, skills, plugins, and MCP recommendations tailored to your stack.
Overview
Claude Automation Recommender is an agent skill most often used in Build (also Operate iterate) that analyzes a codebase read-only and recommends tailored Claude Code hooks, subagents, skills, plugins, and MCP automation
Install
npx skills add https://github.com/anthropics/claude-plugins-official --skill claude-automation-recommenderWhat is this skill?
- Read-only analysis: recommends automations but does not create or modify project files
- Suggests 1–2 top picks per automation type by default, or 3–5 when user narrows to one type
- Covers hooks, subagents, skills, plugins, and MCP servers with a typed overview table
- Encourages web search beyond bundled reference lists for framework-specific patterns
- Uses Read, Glob, Grep, and Bash tooling to inspect the codebase before recommending
- Default cap: 1–2 recommendations per automation type
- Focused mode: 3–5 recommendations when user requests a single automation type
- Five automation types: hooks, subagents, skills, plugins, MCP servers
Adoption & trust: 4.2k installs on skills.sh; 29.6k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have a real codebase but no clear picture of which Claude Code hooks, skills, or MCP servers would actually pay off for your stack.
Who is it for?
Solo builders onboarding Claude Code to an existing monorepo or polyglot app who want a structured automation backlog before investing in hooks and MCP wiring.
Skip if: Teams expecting the skill to auto-install plugins or mutate configuration files, or greenfield projects with no code to analyze yet.
When should I use this skill?
User asks for automation recommendations, wants to optimize 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
What do I get? / Deliverables
You receive a prioritized, category-balanced recommendation list (typically 1–2 per automation type) you can implement yourself or delegate in a follow-up session.
- Prioritized automation recommendation list by type (hooks, subagents, skills, plugins, MCP)
- Short rationale tying each suggestion to observed repo patterns
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Build agent-tooling is the canonical shelf because first-time and ongoing Claude Code setup happens while the product codebase exists and needs tailored automations. Agent-tooling fits a recommender that maps repo patterns to hooks, subagents, skills, plugins, and MCP servers without writing application features.
Where it fits
Day-one Claude Code setup: scan the repo and pick the highest-value hook and skill pair before writing custom automations.
Identify which MCP servers match detected APIs and databases instead of installing a generic bundle.
Recommend lint-on-save hooks and review subagents after noticing inconsistent formatting in PRs.
Re-run recommendations when upgrading frameworks so skills and plugins stay aligned with new tooling.
How it compares
Use as a read-only discovery pass instead of blindly installing popular Claude plugins that do not match your repo.
Common Questions / FAQ
Who is claude-automation-recommender for?
Developers using Claude Code who want data-driven suggestions for hooks, subagents, skills, plugins, and MCP based on their actual repository layout and dependencies.
When should I use claude-automation-recommender?
Use it in Build agent-tooling when first wiring Claude Code for a project, in Operate iterate when workflows feel slow, and anytime you ask for automation or setup optimization recommendations.
Is claude-automation-recommender safe to install?
The skill is read-only regarding your repo but may invoke Read, Glob, Grep, and Bash; review the Security Audits panel on this page and restrict use to repositories you own.
SKILL.md
READMESKILL.md - 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 | Type | Best For | |------|----------| | **Hooks** | Automatic actions on tool events (format on save, lint, block edits) | | **Subagents** | Specialized reviewers/analyzers that run in parallel | | **Skills** | Packaged expertise, workflows, and repeatable tasks (invoked by Claude or user via `/skill-name`) | | **Plugins** | Collections of skills that can be installed | | **MCP Servers** | External tool integrations (databases, APIs, browsers, docs) | ## Workflow ### Phase 1: Codebase Analysis Gather project context: ```bash # 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:** | Category | What to Look For | Informs Recommendations For | |----------|------------------|----------------------------| | Language/Framework | package.json, pyproject.toml, import patterns | Hooks, MCP servers | | Frontend stack | React, Vue, Angular, Next.js | Playwright MCP, frontend skills | | Backend stack | Express, FastAPI, Django | API documentation tools | | Database | Prisma, Supabase, raw SQL | Database MCP servers | | External APIs | Stripe, OpenAI, AWS SDKs | context7 MCP for docs | | Testing | Jest, pytest, Playwright configs | Testing hooks, subagents | | CI/CD | GitHub Actions, CircleCI | GitHub MCP server | | Issue tracking | Linear, Jira references | Issue tracker MCP | | Docs patterns | OpenAPI, JSDoc, docstrings | Documentation skills | ### Phase 2: Generate Recommendations Based on analysis, generate recommendations across all categories: #### A. MCP Server Recommendations See [references/mcp-servers.md](references/mcp-servers.md) for detailed patterns. | Codebase Signal | Recommended MCP Server | |-----------------|------------------------| | Uses popular libraries (React, Express, etc.) | **context7** - Live documentation lookup | | Frontend with UI testing needs | **Playwright** - Browser automation/testing | | Uses Supabase | **Supabase MCP** - Direct database operations | | PostgreSQL/MySQL database | **Database MCP** - Query and schema tools | | GitHub repository | **GitHub MCP** - Issues, PRs, actions | | Uses Linear for issues | **Linear MCP** - Issue management | | AWS infrastructure | **AWS MCP** - Cl