WITAN

Docs · Render · Calc · Lint · Pricing · Agent Skills · Install Witan

---

# Skills for your agent

The CLI ships with two skill files that teach agents how to
use Witan effectively. Add them to your agent and it will know how
to use every command.

## What are skills?

Skills are markdown files that give your agent the context
it needs to use a tool correctly. Instead of the agent guessing at
CLI flags or API shapes, a skill file provides the full reference —
commands, parameters, return types, and recommended workflows — in
a format the agent reads at the start of a task.

Witan ships two skills in the witan-cli repository, each covering
a different part of the toolkit.

## xlsx-code-mode

Workbook scripting with 30+ purpose-built functions.

This skill teaches your agent to use witan xlsx exec — the
single-tool interface for reading, writing, searching, tracing,
and computing against any workbook.

With this skill, your agent can:

- Read cells, ranges, rows, and columns (including token-efficient TSV)
- Search with text, regex, or numeric matching
- Write values, formulas, and formatting in a single call
- Trace formula dependencies (precedents and dependents)
- Evaluate formulas without writing, lint, and render — all in one execution

→ Learn more about Exec
→ View skill file on GitHub

## read-source

Extract text from source documents for spreadsheet workflows.

This skill teaches your agent to use witan read — the document
extraction tool for PDFs, Word docs, presentations, HTML pages,
and Markdown files that contain data you need to work with.

With this skill, your agent can:

- Extract text from PDF, DOCX, PPTX, HTML, and Markdown files
- Navigate large documents with outline, page ranges, and line offsets
- Read documents from local paths or URLs
- Pipeline source data into spreadsheet population workflows

→ View skill file on GitHub

## Adding skills to your agent

    npx skills add witanlabs/witan-cli

This installs both skill files into your project. Most agents support skills natively — see the docs for yours:

- Claude Code
- Codex
- Deep Agents
- OpenClaw

Your agent reads the skill at the start of any relevant task, giving
it full context on available commands and recommended workflows.

---

© Witan Labs Inc. 2026
hello@witanlabs.com · API Docs · GitHub · Research · Terms · Privacy