Best Claude Code Skills

These are the top 20 skills in our directory for Claude Code. The ranking is rule based, not a quality score.

How we rank

Skills with a license that lets us quote the description come first. Within that group, the skill whose repo was updated most recently ranks higher. Ties go in alphabetical order. We do not use install counts or stars, because we do not have that data yet. Our data has 1361 skills from 8 repos, checked 2026-10-13. We have not tested each skill in Claude Code.

The list

Claude Code reads skills from ~/.claude/skills/. Each skill page shows the full install command.

api-and-interface-design

addyosmani/agent-skills

Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, def...

Check: PassMITUpdated 2026-10-13

browser-testing-with-devtools

addyosmani/agent-skills

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture...

Check: PassMITUpdated 2026-10-13

ci-cd-and-automation

addyosmani/agent-skills

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test ...

Check: PassMITUpdated 2026-10-13

code-review-and-quality

addyosmani/agent-skills

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to ...

Check: PassMITUpdated 2026-10-13

code-simplification

addyosmani/agent-skills

Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend ...

Check: PassMITUpdated 2026-10-13

constraint-driven-development

addyosmani/agent-skills

Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane...

Check: PassMITUpdated 2026-10-13

context-engineering

addyosmani/agent-skills

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configu...

Check: PassMITUpdated 2026-10-13

debugging-and-error-recovery

addyosmani/agent-skills

Guides systematic root-cause debugging. Use when tests fail, builds break, something that worked yesterday broke, behavior doesn't match expectations, or you...

Check: PassMITUpdated 2026-10-13

deprecation-and-migration

addyosmani/agent-skills

Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when mi...

Check: PassMITUpdated 2026-10-13

documentation-and-adrs

addyosmani/agent-skills

Records decisions and documentation. Use when you need to document an architecture decision (ADR) or the reasoning behind a design choice, when changing publ...

Check: PassMITUpdated 2026-10-13

doubt-driven-development

addyosmani/agent-skills

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceedi...

Check: PassMITUpdated 2026-10-13

frontend-ui-engineering

addyosmani/agent-skills

Builds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing lay...

Check: PassMITUpdated 2026-10-13

git-workflow-and-versioning

addyosmani/agent-skills

Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, splitting uncommitted work in a mess...

Check: PassMITUpdated 2026-10-13

idea-refine

addyosmani/agent-skills

Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to str...

Check: PassMITUpdated 2026-10-13

incremental-implementation

addyosmani/agent-skills

Delivers changes incrementally in thin, verifiable slices. Use when implementing any feature or change that touches more than one file, or when picking up th...

Check: PassMITUpdated 2026-10-13

interview-me

addyosmani/agent-skills

Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confiden...

Check: PassMITUpdated 2026-10-13

observability-and-instrumentation

addyosmani/agent-skills

Instruments code so production behavior is visible and diagnosable. Use when adding logging, metrics, tracing, or alerting. Use when shipping any feature tha...

Check: PassMITUpdated 2026-10-13

performance-optimization

addyosmani/agent-skills

Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance reg...

Check: PassMITUpdated 2026-10-13

planning-and-task-breakdown

addyosmani/agent-skills

Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too lar...

Check: PassMITUpdated 2026-10-13

security-and-hardening

addyosmani/agent-skills

Hardens code against vulnerabilities. Use when auditing an input handler for vulnerabilities, when handling user input, authentication, data storage, or exte...

Check: NotesMITUpdated 2026-10-13

More: all Claude Code skills

The Daily 5 newsletter

Five good agent skills in one email. Unsubscribe any time.

Placeholder. The mailing list is not connected yet, so nothing is collected.

Questions

How are the best Claude Code skills picked?

By rule. Licensed, described skills come first, then the newest repo update. No paid placement.

Are these skills safe?

We run a basic automated check. It is not a full audit. Read a skill before you install it.

Ad Sponsor this spot. Reach developers who pick skills