Skip to content
TinyFat Docs

Skills & Tools

Your agent comes with pre-installed skills that extend its capabilities. Skills are documentation files that teach your agent how to use specific tools and APIs.

Pre-installed skills

Section titled “Pre-installed skills”

Skills are installed at /opt/skills/ in two directories:

pi-skills

Section titled “pi-skills”

Core skills from the pi-mono project:

SkillDescription
beadsIssue tracking with Beads CLI
brave-searchWeb search via Brave API
browserBrowser automation (requires headed environment)
google-calendarGoogle Calendar CLI (requires setup)
google-driveGoogle Drive CLI (requires setup)
google-mailGmail CLI (requires setup)

tiny-skills

Section titled “tiny-skills”

TinyFat platform-specific skills:

SkillDescription
email-outboxHow to send emails via the outbox pattern
workspaceUnderstanding the agent’s filesystem

Built-in tools

Section titled “Built-in tools”

Your agent has access to core tools without any additional setup:

File operations

Section titled “File operations”
  • Read and write files anywhere in /data
  • Create directories
  • List directory contents

Shell commands

Section titled “Shell commands”
  • Run any Linux command via bash
  • Access to common utilities (git, curl, jq, etc.)

Code editing

Section titled “Code editing”
  • Surgical file edits (find and replace)
  • Full file rewrites

Container utilities

Section titled “Container utilities”

The sandbox container includes these pre-installed tools:

Core:

  • git — Version control
  • curl, wget — HTTP requests
  • jq, yq — JSON/YAML processing
  • ripgrep (rg) — Fast text search
  • fd-find (fdfind) — Fast file finding
  • tree, less — File browsing

Databases:

  • sqlite3 — SQLite client
  • psql — PostgreSQL client

Python:

  • python3 — Python interpreter
  • uv — Fast Python package manager
  • fpdf2 — PDF generation (pre-installed)

Developer:

  • gh — GitHub CLI
  • tmux — Terminal multiplexer
  • Node.js 22 LTS

Adding capabilities

Section titled “Adding capabilities”

Install Python packages

Section titled “Install Python packages”
Terminal window
uv pip install pandas matplotlib

Packages persist in your agent’s storage.

Install Node packages

Section titled “Install Node packages”
Terminal window
npm install -g some-package

API keys

Section titled “API keys”

Some skills require API keys:

SkillKey neededHow to add
Brave SearchBRAVE_API_KEYDashboard → Settings → API Keys
Google APIsOAuth setupContact support

Skill loading

Section titled “Skill loading”

Your agent automatically has access to skill documentation. When you ask about a capability, the agent reads the relevant skill file to understand how to use it.

Example prompt:

“Search the web for recent news about AI agents”

The agent will:

  1. Recognize this needs web search
  2. Load the brave-search skill
  3. Execute the search
  4. Return results

PDF generation

Section titled “PDF generation”

Your agent can create PDFs using Python’s fpdf2 library:

from fpdf import FPDF


pdf = FPDF()
pdf.add_page()
pdf.set_font("helvetica", size=12)
pdf.cell(200, 10, text="Hello World!", new_x="LMARGIN", new_y="NEXT")
pdf.output("/data/output.pdf")

The agent can then email you the PDF as an attachment.

Limitations

Section titled “Limitations”

No browser automation

Section titled “No browser automation”

The sandbox doesn’t have a display server. Browser-based skills (Puppeteer, Playwright) won’t work. Use API-based alternatives like Brave Search or Firecrawl.

No Docker

Section titled “No Docker”

Can’t run Docker inside the sandbox (no nested containers).

Limited network

Section titled “Limited network”

Outbound HTTP is allowed, but some services may be blocked.

Custom skills

Section titled “Custom skills”

Want to add custom skills? Create markdown files in your MEMORY.md with instructions:

## My Custom Tool


When asked to do X, follow these steps:
1. ...
2. ...

The agent will incorporate these instructions into its behavior.

Next steps

Section titled “Next steps”