generative-computinggenerative-computingOfficialยท3 Agent Skills Included

mellea

Build reliable, testable AI workflows with structured Python functions

Turns typed Python functions into structured LLM calls with enforced Pydantic schemas and automatic retries. Replaces brittle prompts and flaky agents with verifiable requirements, sampling strategies, and multi-backend support. Includes agent skills for authoring new skills, auditing test markers, and enforcing logging conventions.
npx skills add generative-computing/mellea --all -g -y
Available:

Gives AI coding agents the project's build commands, testing rules, coding standards, and skill locations, with CLAUDE.md delegating to AGENTS.md and routing new capability requests to the skill-author skill.

All Skills in This Repository (3)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install Mellea?โ–ผ

Run `npx skills add generative-computing/mellea --all -g -y` in your terminal to install all skills in this suite globally.

What problem does Mellea solve?โ–ผ

Mellea replaces brittle prompts and flaky agents with structured, testable AI workflows. It enforces typed outputs, validates requirements, and retries failed generations automatically.

Which LLM backends does Mellea support?โ–ผ

Mellea works with Ollama, OpenAI, HuggingFace, WatsonX, LiteLLM, and Bedrock, so you can swap providers without rewriting your code.

Do these skills work with Claude Code and IBM Bob?โ–ผ

Yes. All skills follow the agentskills.io standard and run in Claude Code, IBM Bob, and other compatible AI coding tools.

Can I create my own agent skills with this repo?โ–ผ

Yes. The built-in skill-author skill scaffolds, validates, and installs new cross-compatible SKILL.md files for you.

Related Repositories in Software Engineering

View All in Software Engineeringโ†’