# Skills

> Reusable context and instructions for AI agents — loaded on demand, not crammed into prompts.

**URL:** https://inference.sh/docs/skills/overview
**Last updated:** 2026-09-18

---

**Reusable context and instructions for AI agents — loaded on demand, not crammed into prompts.**

Skills are packages of instructions, reference docs, and scripts that agents retrieve when relevant. Instead of a massive system prompt that slows every response, your agent sees a short list of available skills and loads what it needs.

---

## How Skills Work

When you add skills to an agent:

1. The agent's `skill_get` tool lists available skills (name + description)
2. When relevant, the agent calls `skill_get("skill-name")` to load the full content
3. Supporting files (references, scripts, examples) are loaded on demand via `skill_get("skill-name", "references/api-docs.md")`

This **progressive disclosure** pattern keeps the context window focused. The same approach is used by Claude Code, Cursor, and other leading agents.

```
User: "Review this pull request"

Agent: [calls skill_get(skill="code-review")]
       → loads code review guidelines

Agent: "Based on our code review guidelines, here's my analysis..."
```

---

## The Agent Skills Standard

Skills follow the [Agent Skills](https://agentskills.io) open standard — a shared format that works across tools. A skill is a directory with a `SKILL.md` entry point plus optional supporting files:

```
my-skill/
├── SKILL.md           # entry point — yaml frontmatter + markdown instructions
├── references/        # domain docs, API specs — loaded on demand
│   └── api-docs.md
├── scripts/           # executables the agent can run
│   └── helper.py
├── examples/          # example outputs showing expected format
│   └── sample.md
└── templates/         # templates for the agent to fill in
    └── template.md
```

inference shell implements this standard natively — skills you create here work on inference shell agents, Claude Code, Cursor, Windsurf, and any tool that supports the spec.

---

## Two Ways to Consume Skills

| | inference shell agents | Local agents (Claude Code, Cursor, etc.) |
|---|---|---|
| **How it works** | Agent calls `skill_get` → content fetched from URL at runtime | Skill directory on local filesystem, agent discovers by scanning |
| **Loading** | On-demand via HTTP | On-demand from disk |
| **No setup needed** | Just add the skill to your agent config | Install the skill directory to `~/.claude/skills/` |
| **Paths work everywhere** | `skill_get("my-skill", "references/api-docs.md")` | Relative path from SKILL.md: `references/api-docs.md` |

The same paths work in both models. SKILL.md says `references/api-docs.md` — that works as a `skill_get` argument against our API and as a relative filesystem path locally.

---

## What's Next

- [Creating skills](/docs/skills/creating) — build and publish skills on inference shell
- [The registry](/docs/skills/registry) — browse, search, and share public skills
- [Adding skills to agents](/docs/skills/adding-to-agents) — attach skills to your inference shell agents
- [Using with other agents](/docs/skills/other-agents) — install skills to Claude Code, Cursor, and more
- [Search API](/docs/api/rest/search) — programmatic discovery (`/suggest`, `/search`)
- [Knowledge API](/docs/api/rest/knowledge) — observations, references, and preferences (indexed for search)