> ## Documentation Index
> Fetch the complete documentation index at: https://docs.suprsend.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent Skills

> Install SuprSend domain knowledge into your AI coding agent. Accurate schemas, CLI flags, and best practices — no hallucinations.

Agent Skills are Markdown knowledge packages that live inside your coding agent — Cursor, Claude Code, GitHub Copilot, Amp, Cline, and others. Once installed, your agent loads the right SuprSend knowledge automatically when it detects a relevant task.

Without Skills, agents guess — and get field names, command flags, and schema structure wrong. With Skills, they have the actual spec.

<Note>
  **Beta** — Skills are under active development. Found an issue? Open one on [GitHub](https://github.com/suprsend/skills).
</Note>

<Card title="Quickstart" icon="bolt" href="/reference/agent-skill-quickstart">
  Install Skills and build your first workflow in under 5 minutes.
</Card>

***

## Available skills

<CardGroup cols={3}>
  <Card title="suprsend-workflow-schema" icon="diagram-project" href="/reference/agent-skill-workflow-schema">
    Schema of all [workflow nodes](https://docs.suprsend.com/docs/workflow-nodes.md). Generate valid workflow JSON from plain English.
  </Card>

  <Card title="suprsend-cli" icon="terminal" href="/reference/agent-skill-cli">
    Every CLI command and flag. Push workflows, sync workspaces, generate types.
  </Card>

  <Card title="suprsend-docs-support" icon="book-open" href="/reference/agent-skill-docs-support">
    LLM-optimized doc endpoints your agent can fetch directly at runtime.
  </Card>
</CardGroup>

***

## How skills work

Skills follow the [agentskills.io](https://agentskills.io/specification) progressive disclosure model, keeping context usage efficient:

<Steps>
  <Step title="At startup">
    Skill name and description load so your agent knows what's available.
  </Step>

  <Step title="On activation">
    When you describe a SuprSend task, the full `SKILL.md` loads into context.
  </Step>

  <Step title="On demand">
    Deep reference files (schema guides, node tables) load only when needed.
  </Step>
</Steps>

***

## Supported agents

| Agent                                                        | Directory           |
| ------------------------------------------------------------ | ------------------- |
| Cursor, Amp, Cline, Codex, Copilot, Warp, Kimi CLI, OpenCode | `.agents/skills/`   |
| Claude Code                                                  | `.claude/skills/`   |
| Continue                                                     | `.continue/skills/` |
| Augment                                                      | `.augment/skills/`  |

***

## Security

All skills pass Gen Agent Trust Hub with zero Socket alerts. Full audit at [skills.sh/suprsend/skills](https://skills.sh/suprsend/skills).

<Warning>
  Skills run with full agent permissions. Review contents before deploying in production.
</Warning>

<CardGroup cols={2}>
  <Card title="GitHub" icon="github" href="https://github.com/suprsend/skills">
    Source code and contribution guide.
  </Card>

  <Card title="skills.sh Registry" icon="shield-check" href="https://skills.sh/suprsend/skills">
    Security audits and version history.
  </Card>
</CardGroup>