agentleFS
SperaxSperax/sperax-skills/AGENTS.md

sperax-skills

AGENTS.md8 starsChanged 9 months agoMITView on GitHub

This repository contains 38 open-source AI agent skills for DeFi, Web3, and the Sperax ecosystem. Skills are Markdown-based knowledge files designed for the ClawHub registry. Each skill is a folder under skills/ containing a SKILL.md with: Use gitmoji prefixes: - โœจ feat: โ€” new skill - ๐Ÿ“ docs: โ€” documentation - ๐Ÿ› fix: โ€” factual correction - โ™ป๏ธ refactor: โ€” restructure - ๐Ÿ”ง chore: โ€” tooling/config

The file

Files
AGENTS.md

AGENTS.md โ€” Repository Guidelines

Project Overview

This repository contains 38 open-source AI agent skills for DeFi, Web3, and the Sperax ecosystem. Skills are Markdown-based knowledge files designed for the ClawHub registry.

Structure

sperax-skills/
โ”œโ”€โ”€ skills/               # 38 skill folders, each containing SKILL.md
โ”œโ”€โ”€ bin/                  # CLI scripts (publish, validate)
โ”œโ”€โ”€ docs/                 # Contributor documentation
โ”œโ”€โ”€ scripts/              # Development utilities
โ”œโ”€โ”€ .github/              # CI workflows, templates
โ””โ”€โ”€ .well-known/          # ClawHub discovery metadata

Commands

# Validate all skills
./bin/validate.sh

# Validate one skill
./bin/validate.sh skills/sperax-usds-guide

# Publish all skills to ClawHub
./bin/publish-all.sh

# Dry-run publish
./bin/publish-all.sh --dry-run

# Generate llms.txt / llms-full.txt
./scripts/generate-llms-txt.sh

Skill Format

Each skill is a folder under skills/ containing a SKILL.md with:

---
name: skill-slug
description: One-line summary.
metadata:
  openclaw:
    emoji: "๐Ÿ“Š"
    homepage: "https://sperax.io"
---

Content Rules

  • Read-only / educational โ€” no execution, no transaction logic
  • Public-safe โ€” no internal paths, keys, schemas, or architecture
  • Agent-friendly โ€” structured Markdown with tables, formulas, examples
  • Minimum 100 lines per skill, at least one table, one practical example

Commit Style

Use gitmoji prefixes:

  • โœจ feat: โ€” new skill
  • ๐Ÿ“ docs: โ€” documentation
  • ๐Ÿ› fix: โ€” factual correction
  • โ™ป๏ธ refactor: โ€” restructure
  • ๐Ÿ”ง chore: โ€” tooling/config

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.