All Skills

Generates a high-fidelity UI screen or wireframe from a text prompt using Stitch. This is the core text-to-UI generation tool — the heart of the Stitch workflow.

Generates design variants of existing Stitch screens using the native variant API. Explore alternative layouts, color schemes, fonts, or content with configurable creativity levels.

Guide for using nerdctl, a Docker-compatible CLI for containerd. This skill should be used when the user wants to manage containers, images, volumes, or networks using nerdctl.

Complete reference for the Jaz REST API — the accounting platform backend. Use this skill whenever building, modifying, debugging, or extending any code that calls the API — including API clients, integrations, data seeding, test data, or new endpoint work. Contains every field name, response shape, error, gotcha, and edge case discovered through live production testing.

Master defensive Bash programming techniques for production-grade scripts. Use when writing robust shell scripts, CI/CD pipelines, or system utilities requiring fault tolerance and safety.

Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.

Control Quote/0 electronic screen devices via Dot API. Use when the user needs to interact with Quote/0 devices for - getting device information or status, displaying text content, displaying images, switching content, or listing device tasks.

Apply typography, color theory, spacing systems, and iconography principles to create cohesive visual designs. Use when establishing design tokens, building style guides, or improving visual hierarchy and consistency.

Generates feature specification documents based on provided code and functional descriptions. Focuses on system analysis and product logic rather than implementation details. Code is treated as the single source of truth.

An "AI-Spec-Driven" workflow for complex tasks, triggered ONLY when explicitly requested. It aligns agent execution with rigorous planning (Spec -> Implementation -> Task Tracking) to mimic Antigravity planning mode.

Executes tasks using the Claude Code CLI (`claude`). Automatically determines the safest permission mode (plan, acceptEdits, or bypassPermissions) based on the task type.

Complete guide for Pyth Network - decentralized oracle providing real-time price feeds for DeFi. Covers price feed integration, confidence intervals, EMA prices, on-chain CPI, off-chain fetching, and streaming updates for Solana applications.

Maintain product requirements docs as source-of-truth artifacts, including story decomposition, link hygiene, conflict detection, and changelog-ready summaries. Use when adding/changing/removing requirements, fixing requirement drift, or preparing requirements-focused commit summaries.

Create Git commit messages following Conventional Commits format with automatic type and scope detection. Use when asked to "commit changes", "create a commit", "write commit message", or when ready to commit staged code. Supports feat, fix, docs, refactor, test, build, ci, chore, and revert types with project-specific scope determination based on file paths and directory structure.

Set up a PreToolUse hook in .claude/settings.json that blocks dangerous commands — rm -rf, force push, database drops, and others — before they execute. Teaches the pattern of safety hooks for any Claude Code project. Trigger words: safety, guard, block dangerous, protect, prevent destructive, safe mode, dangerous commands, risky operations.

Automate New Relic observability workflows -- manage alert policies, notification channels, alert conditions, and monitor applications and browser apps via the Composio MCP integration.

Automate SimilarWeb tasks via Rube MCP (Composio). Always search tools first for current schemas.

Creates and registers Tambo components - generative (AI creates on-demand) and interactable (pre-placed, AI updates). Use when defining components, working with TamboComponent, withTamboInteractable, propsSchema, or registering components for AI to render or update.

Tambo CLI reference for project setup and component installation. Agent-friendly with non-interactive mode and exit codes. Use when running tambo init, tambo add, npx tambo commands, or browsing the component library. For guided project creation with tech recommendations, use start-from-scratch skill. For adding Tambo to existing projects, use add-to-existing-project skill.

Ingest URLs, documents, and transcripts into a searchable knowledge base. Query past research and curated documentation using full-text search. Trigger words: ingest, knowledge base, look up, search knowledge, what do we know about, research, index this, add to knowledge base.

Use when the user asks about Claude Code best practices, how to write agents, how to use hooks, how to manage context, or how to work effectively with Claude Code's native systems

Use this skill when the user asks to "download and export a site", "crawl and extract content", "archive a website", "export as WARC/ZIP/PDF", or wants a complete crawl-extract-export pipeline. Crawls the site, extracts structured content, and exports in the requested format.

Structured 4-phase debugging methodology that prevents blind probing and guesswork. Forces root cause identification before any fix attempt. Use when encountering bugs, errors, unexpected behavior, test failures, or when something "just stopped working." Trigger words: debug, bug, error, broken, not working, fix this, something's wrong, investigate, root cause, why is this failing, trace the issue.

A collection of best practices and tips for developing applications using Vue.js. This skill MUST be apply when developing, refactoring or reviewing Vue.js or Nuxt projects.