claude-automation-recommender
Analyze a codebase and recommend Claude Code automations
by anthropicsFree
Description
claude-automation-recommender is an agent skill from Anthropic's official plugins collection, listed on skills.sh. It analyses a codebase and recommends Claude Code automations across the extension types: hooks, subagents, skills, plugins and MCP servers. The skill is read-only. It analyses the project and writes recommendations, but it does not create or change any files, so the user implements the ideas or asks Claude separately to build them. By default it surfaces the one or two most valuable automations in each category, so the list stays short. If the user asks for one type, it focuses on that type and gives three to five options. The reference lists hold common patterns, and the skill is told to go beyond them with web searches for tools, frameworks and libraries the codebase actually uses. It ends by telling the user they can ask for more recommendations in any category. It is for developers who have a repository and want to know which Claude Code features would save them time.…
Highlights
- Covers hooks, subagents, skills, plugins and MCP servers
- Read-only: changes no files
- Top one or two per category by default
- Searches for tools the codebase uses
Ratings & Reviews
No ratings yet
Be the first to rate claude-automation-recommender.
People also visit
coding-agent
Delegate coding work to Codex, Claude Code, or OpenCode as background workers
loop-me
Grill me about specs for the workflows I want to build, within this workspace
continuous-learning
[DEPRECATED - use continuous-learning-v2] Legacy v1 stop-hook skill extractor
claude-automation-recommender FAQ
What does the claude-automation-recommender skill do?
It reviews a codebase and recommends Claude Code hooks, subagents, skills, plugins and MCP servers that would suit it.
How do I install it?
Run: npx skills add https://github.com/anthropics/claude-plugins-official --skill claude-automation-recommender
Will it change my project?
No. The skill is read-only and does not create or modify files. You implement the recommendations yourself or ask Claude to build them.
How many recommendations do I get?
By default one or two for each type. If you ask for a specific type, the skill gives three to five options for it.
Has it been checked for security?
skills.sh lists three audits: Gen Agent Trust Hub Pass, Socket Warn and Snyk Pass. A Warn or Fail is worth reading before you install.
What are the best claude-automation-recommender alternatives?
Popular alternatives to claude-automation-recommender include coding-agent, git-guardrails-claude-code and loop-me. See all claude-automation-recommender alternatives