Claude Code by use case
Hand-picked selections from the technical library, one per real task.
The technical library has thousands of components, and that is exactly the problem: when you need to solve a specific task, you do not want a list of everything, you want to know what is worth installing.
Each page below is a hand-picked selection. We chose a handful of agents, skills, commands and connectors that actually do the job and explain why each one made the list. If a use case does not have components of high enough quality, we do not create the page.
Choose a use case
- 21 hand-picked components
Agents and skills for code review
Review diffs, catch bugs before the merge and reduce technical debt.
- 21 hand-picked components
Agents, skills and commands for automated testing
Components to write, run and evaluate tests with Claude Code.
- 21 hand-picked components
Agents and skills for code security and auditing
Audit code, find vulnerabilities and stop secrets before the commit.
- 20 hand-picked components
Databases with Claude Code: schema, queries and migrations
MCP connectors, agents and skills for schema, SQL queries, migrations and performance.
- 21 hand-picked components
Agents and skills for technical documentation
READMEs, API docs, ADRs, diagrams and changelogs that do not go stale
- 21 hand-picked components
Agents and skills for frontend and interfaces
React, Vue, Angular, design systems, accessibility and performance in the browser.
- 22 hand-picked components
Agents and skills for DevOps, CI/CD and infrastructure
Components to package, ship and keep software running in production.
- 21 hand-picked components
Agents and skills for debugging and error diagnosis
Find the root cause: stack traces, logs, incidents and memory leaks.
Need help with Claude Code?
Ask Dr AI - it explains things simply.
How we choose what goes on each page
We start from the full library and filter by hand: we keep the ones that actually solve the task, not the ones that share a keyword. When two components do the same thing, the better documented one stays. Each pick has a line explaining when it makes sense, written from the component's own description. We do not mass-generate pages by combining tags: if there is no real inventory for a use case, the page does not exist.
Frequently asked questions
No. They are a starting point for each task. The library still has every component at /en/claude-code, with search and category filters, and each pick on these pages links to the full component page.
Sources
Prompts and resources curated from international sources, normalized and categorized: over 11 thousand. A Doutor AI bot checks the sources every day and brings in what is new.
- Daily updates
- Over 11 thousand resources
- Normalized and categorized
Need a tailor-made solution?
Not sure where to start with AI in your business? Get a free assessment and a tailored plan - no commitment.
Save hours every week with AI, no hassle
Doutor AI gives you 1,859 ready-to-copy AI prompts, by industry and in plain English - plus a complete technical library for those who want to go further.