Explore skills

Automate GitHub PR review workflows with configurable reviewers. This skill helps manage code reviews at scale, iterate through feedback cycles, address comments, and ensure tests and CI pass until all reviews are resolved, supporting multiple reviewers and a coder role.

Configure project-local Playwright browsers for Claude Code's Playwright MCP using PLAYWRIGHT_BROWSERS_PATH. This allows launching browsers from the current project instead of the global cache, addressing Chromium revision mismatches.

Empower non-developers to use agent tools like Codex, Antigravity, and Claude Code more clearly and safely. This skill is useful for clarifying requests, explaining bash commands, isolating risky work, creating backups, capturing preferences, reviewing for security, or improving the tool itself.

Synchronizes forked/cloned open source repositories with upstream changes by fetching and applying diffs directly to files. This is useful for integrating new commits from an original repository into a customized fork.

An AI that chats on KakaoTalk for you, mimicking your speaking style. It continuously replies to messages from registered contacts throughout the session.

Analyze and classify agent skills for safety using local evaluation with structured risk assessment and optional verifiable attestation.

context-density-optimizer is an AgentSkill for pruning bloated working context before implementation, review, debugging, or planning work.

This skill is triggered when the user expresses a desire to learn, understand, or master a topic. It is domain-agnostic, applicable to programming languages, mathematical concepts, design patterns, tools, frameworks, domain knowledge, and soft skills.

Safe, reliable file editing with validation and debugging, ideal for code, configs, or markup (HTML, JSON, Python, JS). It prevents common mistakes like wrong parameter names or unintended changes, incorporating validation, search verification, and rollback strategies.

JUnit 5 skill pack for creating, debugging, modernizing, documenting, and routing JVM test workflows.

Inspects a codebase, detects the test stack, and plans or writes isolated unit and component tests safely.

A 4-pass prompt optimization engine that combines 7 skills into a pipeline, guaranteeing 5/5 across all quality dimensions. It takes a user prompt and returns an optimized version with a full scoring report.