HN Showcase
Back to browse
GitHub Repository

Decades of operational expertise from logistics, manufacturing, retail and energy. Codified into agent skills - Works with Claude, OpenAI Codex, OpenClaw, Cursor, Gemini, and 26+ platforms.

18 starsPython

Codified decades of domain expertise into open source agent skills

by urav·Feb 25, 2026·2 points·1 comment
Visit ProjectView on HN

AI Analysis

●●●BangerZero to OneBig BrainSolve My Problem

Domain expertise as code: AI agents for supply chain, not just APIs.

Strengths
  • •Genuine domain codification—8 capabilities from 10-20 year veterans, not prompt engineering or API wrappers.
  • •Rigorous eval methodology: 201 scenarios across industries with 93.2% avg score and +11.8pp lift vs. baseline.
  • •Cross-platform compatibility (Claude, OpenAI, Gemini) via Agent Skills standard—not locked to one vendor.
Weaknesses
  • •Limited scale: 8 skills is narrow; ClawHub has 3000+. Extensibility and community adoption unclear.
  • •Sparse README detail—capabilities table lacks decision-tree or example reasoning; harder to evaluate depth without diving into GitHub folders.
Category
AI/ML
Target Audience

Enterprise operations teams, AI platform builders, logistics/manufacturing/retail companies deploying agentic workflows

Similar To

Anthropic's Prompt Caching for operational workflows · OpenAI Assistants with custom Instructions · Langchain agent tooling

Post Description

Hey HN! I'm Urav, the founder of Evos (https://getevos.ai)

Evos started out as doing some AI consulting, while deploying these systems, I kept hitting the same problem: AI agents are terrible at real operational work in core industries. Agents could code the entire system, but asking it to handle a freight exception, or claims deadline issue and it fell apart - it just didn't have the domain knowledge.

So I started translating and codifying what operations experts actually know - the decision frameworks, edge cases, escalation protocols - into agent skills for the Evos platform.

Last week, I noticed there are over 3000 skills on ClawHub, and nearly all of them are dev tool wrappers and API integrations. As far as I could tell, there aren't many skills that teach agents genuine domain expertise for traditional industries - and even fewer coming from verified expertise.

Today, I open sourced the Evos agent skills.

We've published 8 skills for use cases across logistics, manufacturing, retail and energy. Each of them follow the Agent Skills open standard, and work across all the major platforms.

Beyond the skills, I built in an eval suite - 20 to 25 scenarios from real operations, scored against weighted rubrics and also benchmarked agents with the skills vs agents without.

Repo: https://github.com/ai-evos/agent-skills

Would love your feedback from anyone whose been in these industries, or thoughts as a whole.

I'll be parked in the comments - thanks!

Similar Projects

Developer Tools●●Solid

Stato captures and transfers AI coding agent expertise across platforms

Treats an agent's prompts and behaviors like versioned packages — commands such as stato crystallize, snapshot, validate, bridge and registry install create an npm/pip-style workflow for ‘expertise’ with a 7-pass compiler and privacy scanning before export. The composition algebra (slice, graft, merge) plus cross-platform bridge generation (e.g., CLAUDE.md) are clever, concrete features that go beyond simple memory dumps. It’s clearly targeted and useful for teams running agent-driven dev workflows, but it needs registry adoption and cross-agent fidelity evidence to become indispensable.

Big BrainZero to One
prism2
123mo ago