A lightweight AI agent framework for vertical domain applications | A lightweight AI Agent framework for specialized domains
Skill Claude CodeCodex
A set of rules for writing algorithm code that can later be checked automatically and packaged as MCP services, which let AI tools call specific functions. It covers function structure, type annotations, documentation, dependencies, and basic code quality.
Skill Claude CodeCodex
Rules for analysing Python projects and identifying functions that could become MCP tools, which are callable functions exposed to an AI system.
Skill Claude CodeCodex
A set of rules and templates for packaging a Python MCP service in Docker. Docker packages an application and its dependencies into a repeatable container that can run on another machine.
Skill Claude CodeCodex
A reference skill for agricultural digital systems, covering field terms, data requirements, workflow guidance, and compliance considerations.
Skill Claude CodeCodex
Domain guidance for monitoring unmanned aircraft, covering the combined picture of airspace activity and alerts tied to time, location, and sensor sources.
Skill Claude CodeCodex
Guidance for monitoring cross-border payments for money laundering and sanctions risks. It explains terms such as suspicious transactions and watchlists, which can include sanctioned people or politically exposed persons.
Skill Claude CodeCodex
Background guidance for working on cross-border online shops, including product classification, service commitments, pricing, taxes, data transfers, and consumer protection.
Skill Claude CodeCodex
Domain guidance for low-altitude electric aircraft, known as eVTOL aircraft, including approved routes, capacity, speed, height, and collision handling.
Skill Claude CodeCodex
Reference guidance for coordinating several connected services into one application-level workflow. It covers stable interfaces, data passed between services, call order, retries, and logging.
Skill Claude CodeCodex
Domain guidance for rural healthcare, including triage, which sets care priority, and follow-up care for people with ongoing conditions.
Skill Claude CodeCodex
Domain guidance for AI systems used in homes, including shared context such as time, household members, and device status.
Skill Claude CodeCodex
A set of rules and a Python structure for wrapping a service so AI clients can call its tools through MCP, an open protocol for connecting models to external tools. It uses server-sent events over HTTP for communication.
Skill Claude CodeCodex
Technical guidance for recognizing human actions in video without training a new machine-learning model or using an LLM. It describes a pipeline that samples video frames, estimates body poses, measures movement, and assigns labels with rules.
Skill Claude CodeCodex
A set of rules for building financial risk models for fraud detection, credit assessment, and suspicious-transaction monitoring. It covers data preparation, model choices, evaluation, and audit-ready outputs.
Skill Claude CodeCodex
A set of rules for building financial time-series forecasting models for values such as exchange rates, prices, trading volume, and credit limits. Time-series data is ordered by time, so future information must not enter the past during training.
Skill Claude CodeCodex
A set of rules for building models that check international trade compliance, such as sanctions-list screening, HS product-code classification, and document review. HS codes are standard numbers used to classify traded goods.
Skill Claude CodeCodex
A set of instructions for designing clinical algorithms, including their intended patients, inputs, units, prediction outcomes, time periods, and limits. It requires sources, runnable entry points, example inputs, and explicit gaps when important information is missing.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: