A Skill packages reusable instructions and supporting files for Agent work. Use a Skill for guidance that should apply repeatedly, such as review rules, delivery checklists, writing standards, or a team process.Keep one-time requirements in the Task description or comments. Create a Skill when the same capability should be available across future runs.Skill scopes#
Every Skill belongs to an organization and has one scope:Organization: available to eligible Agents throughout the organization.
Space: available to Agents associated with that Space. An Agent cannot bind a Space Skill unless the Agent belongs to that Space.
Agent: belongs to one Agent and is bound to that Agent when created or imported.
Create or import a Skill#
You can add a Skill in several ways:Create manually#
Start with a name, description, and instructions. The description should state when the Agent should use the Skill, while the instructions should define the repeatable process and expected output.Install from a URL#
Install a published Skill from a supported public source. The service fetches the Skill files and creates a managed copy in the selected scope.Review the source and imported content before binding it to an Agent. Treat external instructions as third-party code or configuration, not as trusted organization policy.Import from a local Computer#
An online local Runtime can report Skills discovered in its local Skill directories. Importing copies a selected Skill into the organization; the original local copy remains separate.Local Skills available directly to an Agent's Runtime do not need to be bound in the product. Import one when it should become a managed, reusable Skill with an explicit organization, Space, or Agent scope.Upload files#
Upload a SKILL.md, a .skill file, or a zip package. A valid SKILL.md includes YAML name and description fields followed by instructions. A zip package can also include supporting text files.Skill files#
The primary instructions live in SKILL.md. Supporting files can provide templates, examples, reference data, or additional guidance.File paths must be relative and cannot traverse outside the Skill. Upload and import also reject hidden or sensitive paths, unsupported binary content, unsafe archive entries, duplicate paths, and packages that exceed service limits.Keep supporting files focused. Large or unrelated file collections add context without improving the Agent's decisions.Bind Skills to an Agent#
Use the Agent's Skills settings to add or remove eligible Skills. You can also select Skills while creating an Agent.Binding follows scope rules:an Organization Skill can be bound to an Agent in the same organization;
a Space Skill can be bound only when the Agent belongs to that Space;
an Agent Skill is already associated with its target Agent.
Permissions and maintenance#
A Skill can be edited or deleted by its creator or an Organization Owner or Admin. A Space-scoped Skill also requires write access to its Space. Creating or importing an Agent-scoped Skill, and changing an Agent's Skill bindings, requires permission to manage the target Agent.When a process changes, update the Skill's instructions and supporting files. Deleting a Skill removes it from Agents that use it, so check current bindings before deletion.Security guidance#
Never store passwords, access tokens, private keys, or other secrets in Skill instructions or supporting files.
Review every external or locally imported Skill before use.
Keep commands and examples least-privileged and specific to the intended task.
Do not include sensitive organization data unless every user allowed by the Skill's scope may access it.
Recheck bindings after changing an Agent's Space associations or a Skill's contents.
Modified at 2026-08-04 04:02:55
