Teach your AI agent to write Podlite. One command install ⭐️. Works with Claude Code, Codex CLI, Cursor, GitHub Copilot, and anything that supports Agent Skills.
<div align="center">
[](https://podlite.org)
</div>
# Podlite Skills
> Your AI writes Markdown. Teach it something better.
[](https://github.com/podlite/podlite-skills)
One command. Works with [Claude Code](https://claude.ai/code), [Codex CLI](https://github.com/openai/codex), [Cursor](https://cursor.sh), [GitHub Copilot](https://github.com/features/cursor), and [35+ AI agents](https://skills.sh):
```bash
npx skills add podlite/podlite-skills
```
**Why?** Markdown loses structure when AI generates it — mismatched indentation, broken nesting, no typed attributes. Podlite gives your AI explicit block boundaries and machine-readable attributes that survive copy-paste and context loss.
⭐ **Found this useful? [Star the repo](https://github.com/podlite/podlite-skills)** — it helps others discover it.
## Skills
| Skill | Description |
|-------|-------------|
| [podlite-markup](skills/podlite-markup/SKILL.md) | Create and edit Podlite markup — docs, specs, ideas, structured content |
## Installation
### skills.sh (recommended)
One command, [35+ agents](https://skills.sh):
```bash
npx skills add podlite/podlite-skills
```
### Claude Code (manual)
```bash
cp -r skills/ /path/to/your/project/.cursor/skills/
```
### Codex CLI
```bash
cp -r skills/ ~/.codex/skills/
```
### Other tools
Drop `SKILL.md` where your agent looks for skills. See [agentskills.io/specification](https://agentskills.io/specification).
## What is Podlite?
Podlite is a markup language that reads like Markdown but has real structure — block boundaries, typed attributes, inline formatting. Think Markdown that machines can actually parse.
```raku
=begin pod :type('page') :tags<tutorial>
=TITLE My Document
=head1 Introduction
Podlite is B<readable> like Markdown but I<structured> like YAML.
=item Human-Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.