All Skills

Context management specialist for multi-agent workflows and long-running

Battle-tested rules for AI coding agents. 10 skills covering React, Next.js, TypeScript, Express, Python, error handling, testing, security, API design, and performance. Each rule targets specific, concrete behaviors that actually change agent output — not generic best practices. Use when writing, reviewing, or refactoring code in any of these stacks.

Web accessibility compliance specialist. Use when conducting WCAG compliance

Creates platform-specific ad copy for paid campaigns with A/B variants. Use when the user asks about ad copy, PPC ads, Google Ads, Facebook ads, LinkedIn ads, or paid campaign copy.

Use when configuring or running Python quality tools (ruff, ty, pytest, coverage, CI gates) and when enforcing a pre-merge quality checklist.

Display knowledge base status and recent learnings

Spawn, monitor, and communicate with persistent Claude Code sessions running in the background. Use when a task needs to run without blocking the current session, when the user asks to do something in the background, or when a long-running task needs its own context window. Trigger words: background task, spawn session, persistent, run in background, parallel, separate session, async task.

Audit an existing evaluation workflow and produce severity-ranked findings with concrete next actions. Use when inheriting an eval setup, diagnosing quality regressions, or checking LLM evaluation process maturity.

Guide for building SumUp payment integrations that cover both terminal (card-present) and online (card-not-present) checkout flows using SumUp SDKs and APIs. Use when implementing or debugging SumUp checkout creation, payment processing, reader pairing, Card Widget integrations, Cloud API reader checkouts, or authorization setup with API keys/OAuth and Affiliate Keys.

Systematically identify and categorize failure modes in evaluated traces using Truesight datasets and error-analysis tools. Use when quality issues are unclear, after major pipeline changes, or when incidents indicate drift.

Formats Git commit messages following Conventional Commits conventions. Use when the user asks to commit, write a commit message, format commits, or mentions conventional commits, staged changes, or release notes.

Ship updates people actually want to read. Structures release notes, changelog entries, and product updates with what-changed, why-it-matters, and what-to-do-next. Use when writing changelogs or release announcements.

Use this skill when the user asks to "audit a site", "analyze a website", "review a site", "site health check", or wants a comprehensive analysis including technology stack, issues, and recommendations. Orchestrates a full crawl, enrichment capture, observation analysis, and findings report.

Use when creating slide decks with Marp/Marpit Markdown (marp), including authoring slide content, designing slide color schemes, and building SVG diagrams or illustrations for the deck.

Judge flagged trace outputs and promote judged items back to datasets. Use when an evaluation run requires human judgment or when review queue items need to be judged for promotion into the dataset.

# RAG Scaffold Skill Generate production-ready RAG pipeline boilerplate code with best practices built-in. ## When to Use Use `/rag-scaffold` when: - Starting a new RAG project from scratch - Need a reference implementation with best practices - Want to quickly prototype a RAG system - Learning R

Creates strategic content schedules with themes, dates, and publishing cadence. Use when the user asks about content calendars, publishing schedules, content planning, editorial calendars, or content strategy timelines.

Analyzes competitor content strategy and identifies differentiation opportunities. Use when the user asks about competitor analysis, content gaps, competitive research, or finding unique angles.

Framework for navigating AI safety, ethics, and capability trade-off discussions. Covers responsible scaling, content policy, bias, privacy, dual-use, and alignment.

Ensures CSS and components only use approved design tokens. Use when the user asks about design system enforcement, hardcoded colors, spacing values, or wants to validate token usage across files.

Multi-LLM collaborative brainstorming and planning. Use when user explicitly requests consultation with multiple AI models (ChatGPT, Gemini, other LLMs) before presenting an implementation plan, or asks to "consult the council", "ask other models", or "get perspectives from other AIs". Queries external LLM APIs, synthesizes their perspectives, and presents an adapted implementation plan.

Enforce mutation safety in Xcode-managed projects and route Apple and Swift documentation through Dash local-first policy with cooldown-gated advisory messaging. Use for risk checks, consent gating, docs fallback decisions, skill-install guidance, or when the user asks to customize this skills safety/docs behavior.

# Image Generation Service Example A complete example of deploying a Stable Diffusion image generation service. ```python import modal import io import base64 # --- Configuration --- MODEL_ID = "stabilityai/stable-diffusion-xl-base-1.0" GPU_TYPE = "A10" # --- Image Definition --- image = ( m

Provides Django web framework expertise including project structure, models, views, admin, Celery tasks, testing, and Python best practices. Use when generating, analyzing, refactoring, or reviewing Django/Python code.