skillkit

Guides users through creating effective Claude Code skills with specialized knowledge, workflows, and tool integrations. Use when users want to create a new skill, update an existing skill, extract business logic into reusable packages, or ask about skill structure, frontmatter, or bundled resources.

Extracts text and tables from PDFs, creates new documents, merges/splits files, fills forms, and converts markdown to PDF. Use when working with PDF files, when the user mentions PDFs, document extraction, form filling, OCR, or markdown-to-PDF conversion.

Creates, edits, and analyses PowerPoint presentations with layouts, speaker notes, and design elements. Use when working with .pptx files, creating presentations from topics, modifying slides, or extracting content. Triggers: 'create presentation from topic', 'slide deck from document', 'powerpoint from scratch'.

Audits a codebase for production readiness across six dimensions: API completeness, frontend-backend sync, security, scalability, infrastructure, and dead code/architecture. Use when asked for a launch assessment, production readiness check, pre-deployment audit, or multi-agent patchwork cleanup.

Guides README creation and improvement with audience-matched templates. Use when writing READMEs for open source, personal, internal, or config projects, or when the user mentions documentation, README, or project setup.

Guides Remotion video development in React, including compositions, animations, timing, audio, captions, and rendering. Use when the user works with Remotion, writes <Composition>/<Sequence>/interpolate/spring, edits remotion.config.ts, renders or deploys Lambda videos, or asks about video creation in React.

Researches any topic by dispatching 6-10 parallel sub-agents across community discussions and official sources. Use when user wants to research something, asks 'what's new with X', needs recommendations, wants community opinions, or mentions analysing trends, news, or sentiment about any topic.

Reviews and automatically fixes Claude Code skills against official Anthropic best practices. Use when checking skill quality, refactoring bloated skills, improving discoverability, or contributing to open-source skills. Supports review, auto-fix, external review, and PR modes.

Installs, configures, and implements shadcn/ui accessible React components. Use when setting up shadcn/ui, adding components, building forms with React Hook Form and Zod, customising themes, or implementing UI patterns like buttons, dialogs, tables, and data displays.

Merges branches with comprehensive validation while preserving feature branches. Use when user wants to merge PR, sync with main, update feature branch, complete merge, or finalize work. Runs full validation (tests, lint, CI, review comments), merges without deleting branches, and always returns to the working branch.

Performs exhaustive multi-lens analysis through human, structural, inclusivity, and sustainability perspectives with domain-specific augmentation. Use when the user says "ULTRATHINK" (case-insensitive), uses /ultrathink, or faces complex decisions requiring maximum reasoning depth.

Creates, edits, and analyses spreadsheets with formulas, formatting, and data visualisation. Use when working with .xlsx, .xlsm, .csv, or .tsv files, creating spreadsheets from scratch, reading or analysing tabular data, modifying files while preserving formulas, building financial models, or recalculating formula values.

Generates changelogs and creates tagged releases. Use when updating changelogs, preparing releases, or tagging versions.

Creates production-ready GitHub Actions workflows for CI/CD, Docker builds, security scanning, and monorepo orchestration. Triggers on requests for CI/CD setup, workflow creation, pipeline automation, GitHub Actions help, deployment workflows, matrix builds, reusable workflows, or security scanning configuration.

Manages CLAUDE.md files. Audits, reviews, improves, refactors, updates, and generates subdirectory context. Discovers all CLAUDE.md files, evaluates quality against research-backed criteria, generates improvement reports, applies targeted updates, syncs CLAUDE.md with current codebase state, restructures using progressive disclosure, and creates contextual CLAUDE.md files for directories that benefit from instant context. Use when the user says "audit CLAUDE.md", "review my rules", "improve instructions", "organize Claude config", "update CLAUDE.md", "sync my rules", "init project", "generate subdirectory context", or "CLAUDE.md maintenance".

Invokes Codex CLI for code analysis, refactoring, or automated editing. Use when the user asks to run codex exec, codex resume, or references OpenAI Codex.

Guides systematic root-cause debugging through four phases. Use when encountering any bug, test failure, or unexpected behaviour, before proposing fixes.

Creates, edits, and analyzes Word documents with tracked changes, comments, and formatting preservation. Use when working with .docx files for document creation, modification, redlining, or text extraction.

Creates and improves distinctive, production-grade frontend interfaces that avoid generic AI aesthetics. Includes style/color/typography guides by industry, 30+ UX rules, 25+ chart types, and 10 tech stacks. Use when designing components, building pages, choosing palettes, implementing UI patterns, or improving existing interfaces.

Invokes Gemini CLI for code review, plan analysis, frontend development, or large-context (>200k token) processing. Use when the user asks to run Gemini CLI, references Google Gemini, or needs analysis that benefits from a 1M-token context window.

Reviews current git changes with a senior engineer lens. Detects SOLID violations, YAGNI/DRY/KISS breaches, security risks, performance issues, and proposes actionable improvements. Use when reviewing pull requests, checking code quality before merging, or auditing changes for security vulnerabilities.

Creates and improves event-driven hooks for Claude Code automation. Use when building, debugging, or refactoring PreToolUse guards, PostToolUse formatters, Stop hooks for testing, SessionStart environment setup, agent-based verification gates, or integrating Claude Code with CI/CD pipelines.

Discovers and installs agent skills from the open ecosystem and CCPM registries. Use when users ask 'how do I do X', 'find a skill for X', 'is there a skill that can...', 'ccpm', 'claude code skill', 'installed skills', or want to extend capabilities.

Creates professional software diagrams using Mermaid's text-based syntax. Use when users request diagrams, visualizations, or documentation of software architecture including class diagrams, sequence diagrams, flowcharts, ERDs, C4 architecture diagrams, state machines, git graphs, or gantt charts. Triggers: 'diagram', 'visualize', 'model', 'map out', 'show the flow', database design, code structure.