← Explore all skills

CLAUDE CODE AUTOMATION / Anthropic

Claude automation recommender

Pins the Claude Code setup skill that recommends hooks, skills, and MCP servers and says this skill must not create or modify files.

“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.”

01 / THE REASONING

Why this made the selection.

  • The skill says it is read-only, does not create or modify files, and tells the user to implement recommendations separately.
  • Its hook table says to block .env edits and lock-file edits when those files are present, and it marks deploy, commit, and send skills as user-only.

02 / THE REVIEW RECORD

What we actually inspected.

Source review has boundaries.
A clear record is more useful than a “safe” badge.

Material inspected

  • plugins/claude-code-setup/skills/claude-automation-recommender/SKILL.md
  • plugins/claude-code-setup/README.md
  • plugins/claude-code-setup/LICENSE
  • README.md
  • LICENSE

Our findings

  • The skill says it is read-only and does not create or modify any files. Users implement the recommendations or ask separately.
  • Declared tools are Read, Glob, Grep, and Bash. Edit and Write are not in that list.
  • When .env files or lock files are present, the hook table recommends a PreToolUse block on those edits.
  • disable-model-invocation is described as user-only for side effects such as deploy, commit, and send.
  • The file tells the agent to search beyond the bundled reference lists. Those reference files were not part of this review.

Not established by this review

  • The resource was not executed and its tools were not called.
  • No codebase was scanned and no recommendation report was generated.
  • The references directory was not opened, and web search was not used.
  • Not executed: it was not installed or run.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

Add a skill to your workflow.

Upstream setup instructions ↗
  1. The root README says to run `/plugin install {plugin-name}@claude-plugins-official`. The braces are a placeholder, so install.command is null.
  2. The claude-code-setup README does not contain an install command. It says the skill is read-only.
  3. No fetched line installs only claude-automation-recommender.

Before you start

  • Claude Code

04 / FOLLOW THE EVIDENCE

The source trail.

Our notes are separate from the original resource.
Check upstream before adopting a new version.

  1. https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-code-setup/skills/claude-automation-recommender/SKILL.md

    Supports: read-only rule, tool list, and sensitive-file hook recommendations

  2. https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-code-setup/README.md

    Supports: the plugin README repeats that the skill does not modify files

  3. https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-code-setup/LICENSE

    Supports: Apache License, Version 2.0

  4. Repository README ↗Checked

    https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/README.md

    Supports: placeholder install line

  5. Repository LICENSE ↗Checked

    https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/LICENSE

    Supports: Apache License, Version 2.0

  6. https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-code-setup/skills/claude-automation-recommender/SKILL.md

    Supports: upstreamDescription, review.notTested, review.reviewedAt

Evidence & Ask