All Skills

Classifies HTML pages, forms, and fields using machine learning to detect page types, form types, and field types from HTML content or URLs.

Generate images, videos, audio, and more using fal.ai AI models, with support for text-to-image, image-to-video, text-to-speech, speech-to-text, image editing, upscaling, model search, workflow creation, and cost estimation.

Quantize large language models to 8/4/3/2/1-bit precision without calibration data, using multiple optimized backends and integrations with HuggingFace Transformers, vLLM, and PEFT/LoRA.

High-performance numerical computing with JAX, covering functional transformations, Flax NNX, and best practices for ML research.

Scales Python ML workloads across clusters using Ray's distributed tasks, actors, data, and serving capabilities.

Annotates single-cell RNA-seq data by scoring marker genes, transferring labels with CellTypist, or reasoning over cluster markers with an LLM.

Fine-tune instruction-following LLMs with Unsloth's optimized SFTTrainer, covering dataset formatting, chat templates, training configuration, and thinking-model patterns.

Provides Python code patterns for making HTTP requests with httpx, covering sync and async clients, authentication, streaming, timeouts, retries, and WebSocket support.

Build, deploy, and interact with Juicebox V5 projects, including revnets, hooks, and omnichain deployments, with API references, implementation details, UI generation, and GraphQL queries.

Generates type-safe TypeScript clients from OpenAPI specs using Orval, covering configuration, React Query/SWR hooks, custom mutators, and MSW mocks.

Runs the CAAM operator skill using Codex and the local shell, following the source skill's domain behavior and output expectations.

Runs the casr operator skill in a Codex environment, reading the source skill for behavior and using the local shell with JSON/NDJSON command surfaces.

Runs the CASS operator skill in a Codex environment, using the local shell and referencing the source skill for domain behavior.

Scaffolds a coder-eval task suite in a repository by scanning for testable components, writing one real task, and validating it.

Mines SpecStory coding histories from any agent into a persistent corpus, surfaces reproducible workflows with corroborated evidence, and interactively forges chosen ones into skills installed across agent harnesses.

Persists context across sessions by compiling sources into a local SQLite store and markdown tree, then retrieves relevant memory via embedding search.

Turns a natural-language request into one or more coder-eval task YAML files with minimal prompts and weighted success criteria, validated against the coder-eval CLI.

Quickly look up concise, community-maintained command examples instead of full man pages.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Bootstraps a local Python environment for a skill package by creating a venv and installing dependencies with a stdlib-only script.

Defines when to create Epic, Feature, UserStory, or Task tickets and adds concise guidance to SKILL.md.

Master index of Odoo 18 development guides, covering modules, models, views, security, testing, and more.

Guides implementation of accessible web interfaces to meet WCAG 2.2 AA, WAI-ARIA 1.2, and WCAG2ICT standards, covering semantic HTML, ARIA patterns, focus management, and automated validation.

Generate A2UI 0.8 protocol compliant UI code for agent-driven interfaces, including JSONL messages for surface updates, data model updates, and rendering.

Implements real-time pub/sub messaging with Ably's edge infrastructure, covering presence, message history, and token authentication.

Provides Kelvin Garr's fixed AICA brand identity and Next.js 14 implementation guide for building his personal sites and AICA-branded projects.

Generates and refactors content optimized for AI Overviews, ChatGPT, and Gemini with a structure that is easy to cite and summarize.

Provides consulting workflows for Epic EMR configuration, including ClinDoc, Bridges interfaces, HL7 messaging, provider matching, and orderset builds.

Establishes a two-party working posture where the user directs and the agent executes, surfacing every genuine fork as a batched single-select question with a recommended default.

Autonomously implements large Elixir/Phoenix features end-to-end: discovers complexity, plans with specialist agents, implements with verification, reviews code, and cycles back on issues.

Spawns GLM-5 powered teammates with thinking mode for coding, review, testing, planning, and research tasks.

Loads one or more predefined role files to focus work on a specific task, activated by commands like "role [name]".

Adds a persistent pattern or rule that Ralph will remember and apply to future stories.

Manages personal local Agent Skill files by detecting reusable material, searching for similar skills, and creating or updating SKILL.md folders after user approval.

Creates, reads, edits, and analyzes Word documents (.docx) using pandoc, LibreOffice, and docx-js, including formatting, tables, images, and tracked changes.

Creates, reads, edits, and converts PowerPoint (.pptx) files, including extracting text, generating slide images, and applying design guidance.