claude-plugins

This skill should be used when the user asks to "create an agent SDK app", "build a Claude Agent SDK project", "set up a new SDK application", "scaffold an agent app", "create a new agent", or needs guidance on initializing, configuring, and building applications with the Claude Agent SDK in TypeScript or Python.

Builds structured anime and manga prompts for Midjourney Niji mode, matching artist styles, SREF codes, and technical parameters to user requests. Activates when the user wants to create anime art, reference specific manga artists or studios, use Niji mode, or generate character reference sheets and animations.

Applies Anthropic's official brand colors, typography, and visual hierarchy to presentations, documents, slides, and other visual artifacts. Activates when the user requests Anthropic-branded styling or needs consistent brand identity across content.

This skill should be used when the user asks to "review a pull request", "code review this PR", "check this PR for bugs", "review PR

Guides collaborative creation of structured documents through a three-stage workflow of context gathering, iterative refinement, and reader testing. Activates when the user drafts documentation, proposals, technical specs, or decision documents that benefit from structured co-authoring.

Provides a reference template and structural guide for creating Claude Code plugin skills. Activates when the user asks about skill development patterns, requests a skill template, or wants to understand the SKILL.md format and frontmatter options.

This skill should be used when the user asks to "build a feature", "implement a feature", "add new functionality", "develop a feature", "create a new feature", or when embarking on a multi-phase feature development workflow that requires codebase understanding, architecture design, clarifying questions, implementation, and quality review.

Generates distinctive, production-grade frontend code with bold aesthetic direction and meticulous visual detail. Activates when the user requests web components, pages, or applications that need polished UI design beyond generic templates.

Guides creation of hookify rules in .claude/hookify.{name}.local.md files, including YAML frontmatter fields (name, enabled, event, pattern, action, conditions), event types (bash, file, stop, prompt, all), regex pattern writing, condition operators, and rule organization. Activates when the user asks to create a hookify rule, write a hook rule, configure hookify, or add pattern-based automation rules.

Reads, creates, edits, and formats Word documents (.docx files), including tracked changes, comments, and template-based generation. Activates when the user works with .docx files or requests document authoring, redlining, or text extraction from Word documents.

Reads, creates, merges, splits, and edits PDF files, including text and table extraction, form filling, OCR on scanned documents, and watermarking. Activates when the user works with .pdf files or requests any PDF manipulation task.

Creates, edits, and analyzes PowerPoint presentations (.pptx files), including slide design, chart and table insertion, HTML-to-PPTX conversion, and template-based generation. Activates when the user works with .pptx files or requests presentation authoring.

Creates, edits, and analyzes Excel spreadsheets (.xlsx, .xlsm, .csv), including formula-based calculations, cell formatting, financial modeling, and data analysis with pandas and openpyxl. Activates when the user works with spreadsheet files or requests Excel-related tasks.

Converts natural language descriptions into structured JSON schemas for Nano Banana Pro (Gemini 3 Pro Image) across five schema types covering marketing images, UI mockups, diagrams, data visualizations, and social media graphics. Activates when the user needs precise, reproducible control over image generation with defined specifications.

Guides development of Claude Code plugin agents, including agent file structure, YAML frontmatter fields, system prompt design, triggering conditions, and model/color/tool configuration. Activates when the user asks to create an agent, add a subagent, write agent frontmatter, configure agent triggering examples, choose agent tools or colors, or needs guidance on agent development best practices.

Guides development of Claude Code slash commands, including file format, YAML frontmatter fields, dynamic arguments ($ARGUMENTS, $1/$2), file references, bash execution, and command organization. Activates when the user asks to create a slash command, add a command, define command arguments, use command frontmatter, organize commands, create commands with file references, or needs guidance on command development best practices.

This skill should be used when the user asks to "create a plugin", "build a new plugin", "scaffold a plugin", "make a Claude Code plugin", "design a plugin", or needs guidance on the end-to-end plugin creation workflow including discovery, component planning, design, implementation, validation, and testing.

Guides development of Claude Code plugin hooks, including prompt-based and command hooks, hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification), matchers, output formats, and security practices. Activates when the user asks to create a hook, add event-driven automation, validate tool use, implement prompt-based hooks, block dangerous commands, or configure hooks.json.

Guides integration of Model Context Protocol (MCP) servers into Claude Code plugins, including server types (stdio, SSE, HTTP, WebSocket), .mcp.json configuration, authentication patterns (OAuth, tokens), environment variable expansion, and MCP tool naming. Activates when the user asks to add an MCP server, configure .mcp.json, connect an external service, or set up MCP in a plugin.

Guides implementation of user-configurable plugin settings using the .claude/plugin-name.local.md pattern, including YAML frontmatter parsing, per-project configuration, settings file creation, and reading settings from hooks, commands, and agents. Activates when the user asks about plugin settings, .local.md files, plugin state files, per-project configuration, or wants to make plugin behavior configurable.

Guides creation and organization of Claude Code plugin directory structure, including the plugin manifest (plugin.json), component directories (commands, agents, skills, hooks), MCP server configuration, auto-discovery mechanism, portable path references with ${CLAUDE_PLUGIN_ROOT}, and file naming conventions. Activates when the user asks to create a plugin, scaffold a plugin, organize plugin components, set up plugin.json, or needs guidance on plugin architecture.

Guides development of Claude Code plugin skills, including SKILL.md structure, YAML frontmatter, progressive disclosure design, bundled resources (scripts, references, assets), and the six-step skill creation process. Activates when the user asks to create a skill, add a skill to a plugin, improve a skill description, organize skill content, or needs guidance on skill development best practices.

This skill should be used when the user asks to "review my PR", "check my code before merging", "run a PR review", "analyze this pull request", "review my changes", or needs a comprehensive multi-agent pull request review covering code quality, test coverage, error handling, type design, comments, and code simplification.