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

# Skills

> Understand the skill package that teaches an agent when and how to perform a task.

A skill is a package that teaches an agent when to take on a type of work and
how to complete it. Its canonical entry point is `SKILL.md`; the package may
also contain workflows, references, scripts, and assets.

## Two jobs

Every skill has two distinct jobs:

1. **Activation:** help the agent recognize when this skill applies.
2. **Execution:** guide the agent toward a correct, verifiable result.

A skill can fail either job. If the agent never selects it, improving the
workflow body will not fix activation. If it activates correctly but produces a
weak result, adding trigger phrases will not fix execution.

## Source and installed copies

Before changing a skill, identify its canonical source and the installed copy
the agent actually reads. A repository source, global installation, project
installation, immutable Library revision, and Cloud snapshot may represent
different versions.

SelfTune should always report which revision it observed, tested, changed, or
published.

## What good evidence looks like

Test requests that should activate the skill, nearby requests that should not,
and realistic tasks that exercise its workflow. Real usage can reveal language
and failure modes that the original author did not anticipate. Synthetic tests
are useful, but they should be identified as generated evidence.

Continue with [Evidence and health](/concepts/evidence-and-health) or
[Improve a skill](/guides/improve-a-skill).

Resolve the canonical source, installed copy, and content revision before
making claims about a skill. Diagnose activation and execution separately. Do
not edit a generated or installed copy when a repository source owns it unless
the user explicitly chooses that destination.