Skill UI

A comprehensive guide to diagnosing and resolving performance bottlenecks in React applications. This skill teaches advanced techniques like state isolation, memoization (using `useMemo`, `useCallback`, and `React.memo`), and list virtualization. It guides users through profiling using React DevTools to identify render hotspots, ensuring components render efficiently and maintain high application responsiveness.

This skill enables the transcription, display, and animation of captions within Remotion projects. It requires captions to be processed in JSON format using the specific Caption type. Users can generate captions from video/audio, display them in the final video, or import existing .srt files. It is suitable for video production workflows requiring automated or structured subtitle integration.

This skill reviews git diffs or specific file scopes for code reuse, quality, efficiency, clarity, and standards compliance. It optionally applies safe, behavior-preserving fixes. It uses parallel read-only sub-agents to inspect code while the main agent applies changes. Suitable for auditing changes, simplifying code, or refactoring.

This skill enables parallel read-only multi-agent review of git diffs or specific file scopes. It identifies behavioral regressions, security risks, performance issues, and coverage gaps using four specialized sub-agents. The main agent synthesizes findings to filter and summarize critical issues without modifying code. Ideal for ensuring code quality and safety before merging changes.

This skill evaluates code diffs against a specific rubric to determine issue detection and resolution. It reads diff files, rubrics, and original fixtures, then answers detection and fix questions for specific problems. Results are appended to a CSV file. Ideal for automated testing and quality assurance workflows in software development.

Comprehensive guidance for configuring and using ShellCheck to improve shell script quality, catch common pitfalls, and enforce best practices through static code analysis. Covers installation, configuration files, common error codes, and integration patterns.

SkillCheck validates SKILL.md files against the agentskills specification and Anthropic best practices. It performs read-only checks on structure, semantics, naming, and quality to catch errors before publishing. The tool provides a score, grade, and detailed report with fix suggestions for critical issues to ensure high-quality skill authoring.

Comprehensive guide for creating and managing skills in Claude Code with auto-activation system. Covers two-hook architecture, skill types (guardrail/domain), configuration files, and enforcement levels following Anthropic best practices including 500-line rule and progressive disclosure pattern.

This skill provides comprehensive diagnosis and optimization for agent skill libraries. By analyzing historical session transcripts from platforms like Claude Code and Codex, alongside static skill file checks, it scores each skill across 8 dimensions. It identifies issues such as low trigger rates, poor post-invocation user reaction, and incomplete workflow execution, generating a prioritized report (P0/P1/P2) to significantly improve the agent's overall performance and reliability.

Turn a repository into a cited HTML slide deck and detect when it drifts from the code. Citations record file, lines, and hash; a stdlib check reports CURRENT, MOVED, CHANGED, or MISSING. Ideal for docs-as-code and maintaining accurate presentations.

This skill enables encryption of secrets within configuration files using Mozilla SOPS. It supports GitOps workflows, Kubernetes secret management, and secure configuration storage. Users can encrypt files with KMS or PGP keys, decrypt them for editing, and integrate with tools like ArgoCD. It ensures sensitive data remains protected while maintaining file structure visibility for version control.

Freezes PRD, technical design, and acceptance criteria before medium-to-large Codex work, then coordinates multiple agents with explicit file ownership and judges delivery from diffs, tests, and evidence-backed acceptance.