Top Agent Skills

Builds Google Stitch UI projects and generates screens from feature descriptions or export files by calling Stitch MCP tools directly, following Stitch prompting best practices.

Provides domain knowledge on the Causal Dynamics Architecture (CDA), an alternative AI computing architecture based on causal graphs and Hamiltonian dynamics, with references for deep dives.

Provides data-driven endurance cycling coaching using Intervals.icu data, including fitness assessment, workout planning, and power curve analysis.

Create terminal-based charts and visualizations from CSV, JSON, or piped data using tools like YouPlot, Termgraph, Gnuplot, and more.

Implements Microsoft Entra ID authentication for React SPAs using MSAL.js and validates JWTs in Cloudflare Workers with jose, covering Authorization Code Flow with PKCE and common error fixes.

Guides code modifications by reading affected files first, matching existing style, and making minimal, safe changes.

Runs SQL queries and data conversions on CSV, Parquet, and JSON files using the DuckDB command-line interface, including schema inspection and output formatting.

Backs up important files before modification, prompts the user to review changes, and deletes the backup only after explicit confirmation.

Creates, edits, and converts vector graphics and diagrams using LibreOffice Draw, supporting ODG, SVG, PDF, and PNG formats.

Provides a reference for building real-time voice and multimodal AI agents with Pipecat, covering pipeline architecture, speech services, LLM integration, transports, and deployment.

Creates, edits, and converts documents in ODT, DOCX, PDF, and other formats, with mail merge and automation via LibreOffice Writer.

Creates, edits, and converts presentations using LibreOffice Impress, including ODP, PPTX, and PDF formats, with automation via command-line and Python scripting.

Implements code features phase by phase from a JSON or Markdown plan, with configurable unit-test and quality-gate choices, token-budgeted execution, and resumable state.

Turns a brainstorm document into a comprehensive, structured software requirements specification with no word limit.

Generates backend source code files, .env.example, and pr-description.md from BA, TechLead, and PM artifacts, following a configurable seniority level.

Turns raw client requirements into an IEEE 830 software requirements specification through structured clarification and gap analysis.

Automates browser interactions and testing with Playwright, including form filling, screenshots, responsive checks, and login flows, with automatic dev server detection.

Drives a real desktop GUI as a fallback when APIs, CLIs, file edits, and browser automation are unavailable, letting agents click, type, read the screen, and control apps across Windows, macOS, and Linux.

Provides a discovery stub for the Wren CLI, a semantic SQL layer over 22+ databases, with commands to install, set up, connect data sources, generate MDL projects, enrich context, and deploy GenBI dashboards.

Generates copyable scientific figure prompts from research documents, papers, and reference images for AI illustration models.

Scaffolds and operates an Obsidian-based blog content brain dual-optimized for Google rankings and AI citations, covering writing, editorial strategy, and fact-checking.

Access 83 unified crypto data endpoints covering CEX/DEX markets, on-chain SQL across 80+ blockchain tables, wallet labels, prediction markets, social intelligence, news, and DeFi metrics via a local HTTP API with per-call billing.

Orchestrates a strict four-stage shipping pipeline: session critique, validation, commit, and pull request, halting on failure. Supports a critique-only mode for mid-session quality checks.

Writes or updates a HANDOFF.md document to preserve context for the next agent, including goal, progress, what worked, what didn't, and next steps.

Recommends the optimal Claude model tier (Opus, Sonnet, or Haiku) for a given task by analyzing reasoning depth, blast radius, domain expertise, output length, and correctness cost, and suggests parallelization opportunities.

Researches conversation and code context to generate 1-6 targeted clarifying questions when a prompt is vague, then executes the original request.

Guides collaborative dialogue to turn ideas into approved designs and specs before any implementation begins.

Use when creating new skills, editing existing skills, or verifying skills work before deployment.

Guides technical verification of code review feedback before implementation, emphasizing reasoned pushback over performative agreement.

Designs and implements CDN architectures, optimizing cache strategies, edge computing, and security for global content delivery.

Runs 150+ AI apps in the cloud via the inference.sh CLI, covering image generation, video creation, LLMs, web search, 3D generation, and Twitter automation.

Reference for MariaDB window functions and the OVER clause, covering ranking, value navigation, and ordered-set functions with syntax and common pitfalls.

Reference for MariaDB's built-in encryption, hashing, and compression functions, covering AES_ENCRYPT/DECRYPT, SHA2, KDF, COMPRESS, and related functions, with guidance on correct usage and common pitfalls.

Runs a disciplined diagnosis loop for hard bugs and performance regressions, from reproduction through hypothesis testing, instrumentation, fixing, and regression testing.

Create strategic HTML presentations with Chart.js, design tokens, responsive layouts, copywriting formulas, and contextual slide strategies.

Guides collaborative dialogue to turn ideas into fully formed designs and specs, exploring intent, requirements, and design before implementation.

Provides grep-based patterns to verify that code artifacts are real implementations rather than stubs or placeholders, covering React components, API routes, database schemas, and hooks.

Creates a pull request from completed phase work, generates a rich PR body from planning artifacts, optionally runs code review, and prepares for merge.

Interact with X (Twitter) programmatically: post tweets and threads, read timelines, search, upload media, and track engagement using OAuth 1.0a or Bearer token authentication.

Records polished demo videos of web applications using Playwright, with an injected cursor overlay, natural pacing, and a discover-rehearse-record workflow.

Discovers, audits, repairs, adapts, and designs bounded AI-agent loops with explicit triggers, actions, verification, stopping conditions, guardrails, and handoffs.

Provides a creative-direction layer for music videos and short-form edits, defining an angelcore/cloud-trance/hyperpop aesthetic with mood, color, light, and beat-synced editing grammar, and orchestrating video production skills into a pipeline.

Guides test-driven development for Django applications using pytest, factory_boy, and Django REST Framework, covering models, views, serializers, and API testing.

Generate iOS app icons as PNG imagesets for Xcode asset catalogs from SF Symbols or the Iconify API, with options for color, size, and output location.

Guides developers through adding new wsh commands to Wave Terminal, covering file creation, Cobra command structure, flags, block arguments, and RPC integration.

Provides strategic analysis and advice in the voice of Sun Tzu, applying principles from The Art of War to modern challenges.

Emulates the voice and storytelling style of comedian Theo Von, using his signature metaphors, digressions, and vulnerable humor for creative writing or conversational responses.

Provides a strategic advisory persona based on A.G. Lafley, applying the Strategy Choice Cascade and consumer-centric frameworks to business decisions.

Embody the voice and methodology of Colonel John Boyd, applying OODA Loop analysis, maneuver warfare strategy, and systems thinking to competitive and strategic challenges.

Transforms content into the cinematic, vernacular voice of Tom Waits, grounding abstractions in concrete imagery and finding dignity in the downtrodden.

Embody the collective voice and methodology of the Russian feminist punk protest group Pussy Riot, using spectacular transgression, collective identity, and punk politics to challenge authoritarian power.

Assess cloud configuration risks including IAM privilege escalation, public storage exposure, network over-permissioning, and infrastructure-as-code misconfigurations.

Creates platform-specific social media content strategies and posts for LinkedIn, X, Instagram, TikTok, and Facebook, with guidance on goals, audience, and brand voice.

Identifies, qualifies, and tiers investors for a funding round based on stage, sector, geography, check size, and portfolio fit, delivering a prioritized target list.

Design, audit, and improve analytics tracking systems that produce reliable, decision-ready data.

Installs the Atlassian CLI tool and authenticates it with an Atlassian account.

Presents a multiple-choice question to the user via the AskUserQuestion tool, parsing up to four options from a simple command.

Stages all changes, creates a commit with a provided or prompted message, and pushes to the current branch.

Guides implementing features and fixing bugs by writing failing tests first, then minimal code, with verification at each step.

Generates and manages vector embeddings for semantic search and RAG retrieval across knowledge bases, with self-learning capabilities.