Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.gigabrain.gg/llms.txt

Use this file to discover all available pages before exploring further.

Skills are how your SuperAgent learns new capabilities. Want it to trade perps on HyperLiquid? Install the hyperliquid skill. Want it to research Polymarket? Install polymarket. Want it to do something no one’s built yet? Write your own in 10 minutes.
SuperAgents use the Agent Skills open standard - the same skill format supported by Claude Code, OpenClaw, Cursor, GitHub Copilot, Windsurf, Gemini CLI, and 26+ other platforms. Any skill built for those platforms works on a SuperAgent, and any skill you write for your SuperAgent works on those platforms.

​
How skills work

A skill is just a folder with a SKILL.md file and optional scripts. The SKILL.md contains markdown instructions that teach the agent what the skill does and how to use it. No SDK, no API wrapper, no boilerplate - just plain language instructions and the tools to back them up. 
my-skill/
  SKILL.md          # Instructions (required)
  scripts/          # Executable code (optional)
  references/       # Extra docs loaded on demand (optional)
When your agent encounters a task that matches a skill’s description, it loads the instructions and follows them. Skills are loaded efficiently - metadata first, full instructions only when needed. Inside skill examples, SKILL_DIR means “the directory containing the SKILL.md file being used.” SuperAgents should resolve that path from the opened skill file instead of relying on a pre-injected CLAUDE_SKILL_DIR environment variable.

​
Official skills

These ship with every SuperAgent and cover the core trading stack:
SkillWhat it does
hyperliquidTrade perpetual futures and spot on HyperLiquid. Market, limit, bracket, and TWAP orders. Position management, account analytics.
polymarketDiscover, research, and trade prediction markets. Odds analysis, event tracking, portfolio management.
brainMarket research via the Brain API. Web search, news, sentiment analysis, on-chain insights.
portfolio-trackerPortfolio overview, P&L tracking, position monitoring across chains.
evm-walletEVM wallet operations - transfers, balance checks, transaction history.
solana-walletSolana wallet operations - transfers, balance checks, token management.
solana-swapToken swaps on Solana via Jupiter.

Browse all official skills

Full source code and documentation for every official skill.

​
Installing skills

To install a community skill, paste the GitHub link to your agent in chat. The agent will install and sync the skill automatically. Browse skills from any of these registries:

skills.sh

Vercel’s open directory with 110,000+ skills. The largest Agent Skills registry.

ClawHub

OpenClaw’s registry with 2,800+ curated skills.

GitHub

Official Gigabrain skills, open source.
Any skill built for Claude Code, OpenClaw, Cursor, or any Agent Skills-compatible platform works on a SuperAgent. Just paste the link.

​
Writing your own skills

You don’t need to be a developer. A skill is just a markdown file that teaches your agent something new. If you can describe it clearly, your agent can learn it.

​
Example: a simple research skill

A skill that gives your agent access to a custom data source. The SKILL.md describes what it does and how to call the script: 
---
name: fear-greed
description: Check the Crypto Fear & Greed Index. Use when the user asks
  about market sentiment, fear/greed levels, or overall market mood.
license: MIT
metadata:
  author: you
  version: "1.0"
---

# Fear & Greed Index

Check current crypto market sentiment.

## Usage

```bash
uv run "$SKILL_DIR/scripts/fear_greed.py"
```

Returns the current index value (0-100), classification
(Extreme Fear / Fear / Neutral / Greed / Extreme Greed),
and the previous day's value for comparison.

## Interpretation

- 0-25: Extreme Fear - historically a buying opportunity
- 25-45: Fear - market is cautious
- 45-55: Neutral
- 55-75: Greed - market is confident
- 75-100: Extreme Greed - consider taking profits
The scripts/fear_greed.py file fetches the API and prints the result. Scripts declare their own dependencies via PEP 723 inline metadata and run in isolation via uv run - no dependency conflicts between skills. That’s it. Your agent now knows when to check market sentiment, how to call the script, and how to interpret the results.

​
SKILL.md format

The frontmatter defines metadata:
FieldRequiredDescription
nameYesLowercase, hyphens only, max 64 chars
descriptionYesWhat it does and when to use it, max 1024 chars
licenseNoLicense identifier (e.g. “MIT”)
compatibilityNoEnvironment requirements
metadataNoKey-value pairs (author, version, etc.)
The body is markdown instructions. Keep it under 500 lines - use a references/ directory for detailed documentation that loads on demand.

​
Managing skills

​
Enable or disable

From the agent’s Skills tab on the dashboard, toggle any skill on or off. The agent restarts automatically when skills change. Disabled skills are completely invisible to the agent.

​
Skill tiers

TierSourceHow it works
OfficialGigabrainGG/skillsMaintained by Gigabrain. Auto-synced to every agent.
Third PartySkills manifestCommunity skills synced from Git repos.
CustomUser-installedSkills you write and install directly.

​
Next steps

SuperAgents

Learn about the SuperAgent architecture

Agent Skills Specification

The full open standard specification

Official Skills

Browse source code and documentation

ClawHub

Discover community-built skills