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

# Agent skills

> Commit project-specific guidance for Momentic's runtime agents to your repository with .momentic/skills.

Agent skills let you commit project-specific guidance for Momentic's runtime
agents to your repository. Use them to describe how to start and reach the app
under test, authentication and environment details, and any conventions the
agents should follow.

<Warning>Agent skills are in beta and may change.</Warning>

## Layout

Each skill is a directory under `.momentic/skills` containing a `SKILL.md` file:

```text theme={null}
.momentic/
  skills/
    app-startup/
      SKILL.md
    triage/
      SKILL.md
```

`SKILL.md` is Markdown with a YAML frontmatter block:

```markdown theme={null}
---
name: app-startup
description: How to build and serve the app under test.
agents: [explore, triage]
---

Build the app with `pnpm build` and serve it on http://localhost:8888. The
explore agent should target that URL; triage can assume it when reasoning about
environment mismatches.
```

### Frontmatter

| Field         | Required | Description                                                                 |
| ------------- | -------- | --------------------------------------------------------------------------- |
| `name`        | yes      | Skill identifier. Must match the directory name, or the skill is skipped.   |
| `description` | yes      | One-line summary of what the skill covers.                                  |
| `agents`      | no       | Which runtime agents the skill applies to. Omit to apply it to every agent. |

The supported agent targets are `explore`, `result-classification`, and
`triage`.

## How skills are applied

* A skill applies to an agent when its `agents` list includes that agent, or
  when `agents` is omitted. Every applicable skill is always used.
* Matching skills are combined in skill-name order and added to the agent's
  instructions, along with each skill's name and description.
* Target a single agent (e.g. `agents: [triage]`) to prompt that agent
  specifically. Target several agents to reuse the same guidance across them.
* A skill that can't be read — missing frontmatter, invalid YAML, an unknown
  agent target, an empty body, or a name that doesn't match its directory — is
  skipped, and Momentic prints a warning naming the file so you can fix it.

## Skills and prompt flags

Some agents also accept prompt flags for one-off or path-specific guidance. The
[explore agent](/docs/ai/explore), for example, takes `--prompt` and `--prompt-file`.
Skills apply automatically and stack with any prompt flags, so you can commit
shared guidance as skills and still pass one-off instructions per run.