Expert for creating and managing Claude Code Agent Skills. Create skills with git submodule + sparse-checkout for source references, write SKILL.md with proper frontmatter, and follow best practices. Use when creating new skills, adding source references to skills, or managing skill configurations.
Break down PM story into organized tasks in a single file following UI DEVELOPMENT order: Setup → Static UI → Dynamic Logic → Interactions → Testing. UNIQUE VALUE: Creates single task file (story-{name}.md) containing all tasks for a story. Tasks are ordered by UI development layers. Use this skill when: - Running /frontend.tasks command - User asks to "break down story", "create frontend tasks", "split into tasks" - Have story at docs/reference/pm/stories/ and need organized task breakdown - Need tasks ordered by UI development layers (not random order) - Starting frontend work and want organized task list Task order is CRITICAL: Setup → Static UI → Dynamic → Interactions → Tests Output: Create single file docs/reference/frontend/tasks/story-{name}.md with all tasks
Resolve requirement ambiguities through STRUCTURED questioning: one question at a time, with recommended options and reasoning. UNIQUE VALUE: Prevents overwhelming users with multiple questions. Provides expert recommendations for each decision. Use this skill when: - Running /pm.clarify command - User says "unclear", "not sure what this means", "confused about" - User asks "what does X mean?", "how should X work?", "can you clarify?" - Requirements have conflicting or inconsistent details - Stories are missing acceptance criteria or have gaps - Need to fill information gaps BEFORE development can proceed Process: Ask ONE question at a time (max 5 per session), provide recommended option with reasoning. DO NOT ask multiple questions at once - this overwhelms users.
Generate new MCP tools for GitLab operations following the project's standardized pattern. Creates complete TypeScript files with imports, registration functions, Zod schemas, error handling, and format options. Supports simple CRUD operations, complex multi-action tools, and advanced patterns like discussion management. Use when "create mcp tool", "generate gitlab tool", "new tool for", "add tool to gitlab", or building new GitLab integration features.
Download and generate plots from Weights & Biases runs. Use when you need to: - List projects you have access to - List runs in a W&B project - Inspect available metrics for a run - Download existing plot images from a run - Generate line plots from metric history (loss, accuracy, etc.)
Provide a reusable pattern for memoizing deterministic function calls to reduce latency and repeated computation. Backed by the `python` diskcache package. Use skill when updating or editing everything.
This skill should be used when the user asks to "test for insecure direct object references," "find IDOR vulnerabilities," "exploit broken access control," "enumerate user IDs or object references," or "bypass authorization to access other users' data." It provides comprehensive guidance for detecting, exploiting, and remediating IDOR vulnerabilities in web applications.
Coordinate multiple agents working simultaneously. Use when splitting tasks across agents or when avoiding overlapping diffs with shared files.
Run dotnet test, capture failed test cases, and generate a rerun filter plus a markdown failure summary. Use when test runs fail and you need a focused rerun command or a compact failure report.
Discover existing shadcn components from registries before building custom. Use PROACTIVELY when about to build any UI component, page section, or layout. Use when user explicitly asks to find/search components. Searches 1,500+ components across official and community registries including @shadcn, @blocks, @reui, @animate-ui, @diceui, Magic UI, and 30+ specialty registries. Provides install commands and code examples. Works best with shadcn MCP configured, but provides manual guidance without it.
Add a review comment to a GitHub pull request.
```yaml
Design and implement the personality, conversational style, and emotional behavior of the Ethereal "Digital Spirit". Use this skill when updating system prompts, mood logic, or implementing new interactive behaviors. Ensures the spirit remains witty, concise, and mysteriously connected to the system's pulse.
Use `astro:assets` for all images. This enables automatic optimization (resizing, WebP/AVIF conversion, lazy loading).
AI image generation using Nano Banana PRO (Gemini 3 Pro Image) and Nano Banana (Gemini 2.5 Flash Image). Use this skill when: (1) Generating images from text prompts, (2) Editing existing images, (3) Creating professional visual assets like infographics, logos, product shots, stickers, (4) Working with character consistency across multiple images, (5) Creating images with accurate text rendering, (6) Any task requiring AI-generated visuals. Triggers on: 'generate image', 'create image', 'make a picture', 'design a logo', 'create infographic', 'AI image', 'nano banana', or any image generation request.
Create and manage specialized Claude Code subagents for task-specific workflows. Use when delegating work to specialized agents, configuring agent permissions, or understanding subagent architecture and best practices.
Use when you have lint errors, formatting issues, or before committing code to ensure it passes CI.
Batch process books through the complete pipeline - generate cropped images for split pages, OCR all pages, then translate with context. Use when asked to process, OCR, translate, or batch process one or more books.
Evaluates and selects the best solution from multiple developer implementations using a comprehensive scoring system. Use this skill when you need to compare competing solutions, score them objectively across multiple dimensions, or select a winning implementation for integration.
Transform requirements into well-structured User Stories using "As a [user], I want [goal], So that [benefit]" format with Given/When/Then acceptance criteria. Use this skill when: - User asks to "write user story", "create story", "add story" - User mentions "user story", "backlog item", "story" - Running /pm.plan and need to break PRD into implementable stories - Creating backlog items for development team - Need to formalize a requirement into standard story format - Converting feature request into actionable story with acceptance criteria Output: ALWAYS write story files to docs/reference/pm/stories/{story-name}.md