claude-automation-recommender_skill

This skill analyzes a codebase and suggests Claude Code automations across hooks, subagents, skills, plugins, and MCP servers to optimize setup.

Shell
Official

5.4k

GitHub Stars

1

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill anthropics/claude-plugins-official --skill claude-automation-recommender

SKILL.md10.6 KB

Overview

This skill analyzes a codebase and recommends tailored Claude Code automations across hooks, subagents, skills, plugins, and MCP servers. It surfaces the top 1–2 high-value automations per category and explains why they fit your project. Use it to prioritize which automations to build or install and to get concise implementation guidance.

How this skill works

The skill inspects project files, dependency manifests, folder structure, and config patterns to detect languages, frameworks, testing tools, CI, databases, and external APIs. It maps those signals to the most relevant automation types and returns a compact, prioritized report with 1–2 recommendations per category. If you ask for a specific automation type it will expand options to 3–5 focused suggestions.

When to use it

When you want to optimize Claude Code workflows for a new or existing project
When you need guidance on which external MCP servers to enable (databases, browsers, docs)
When you want safe, repeatable automations for formatting, linting, tests, or PR checks
When onboarding a team and standardizing common tasks or dev ergonomics
When you’re planning to add background reviewers or parallel analyzers (subagents)

Best practices

Recommend only the top 1–2 automations per category to avoid overload
Prefer non-destructive, read-only analysis; users implement or request implementation help
Match recommendations to explicit project signals (package files, imports, test configs)
Include clear install or create steps and the reason each automation adds value
If a user requests a type, return more focused options (3–5) and tradeoffs

Example use cases

Detect a Next.js + Prisma app and recommend a Playwright MCP for UI tests and a Database MCP for schema queries
Scan a Python FastAPI service and suggest a context documentation MCP and an api-document skill for OpenAPI generation
Analyze a repo with Jest and Prettier and recommend formatting and test-run hooks plus a test-writer subagent
Review a monorepo and propose a code-reviewer subagent for parallel reviews and a GitHub MCP to automate issues/PRs
Identify Stripe/AWS SDK usage and recommend corresponding MCP servers for secure operations and debugging

FAQ

No. The skill is read-only and only produces recommendations. Implementation is done by you or by asking for follow-up help.

How many recommendations will I get per category?

By default you get 1–2 top recommendations per category. If you request a specific type, you get 3–5 focused options.

Can the skill tailor recommendations to CI or team workflows?

Yes. It checks CI configs and team tools (GitHub, Linear, Slack) and will recommend MCP servers or hooks that integrate with those workflows.