Preview. Start with a disposable workspace and an approved canonical
sample bundle. This guide uses the current multipart contract; it does not
define a new Skill package format.
Publish a Skill
Prepare a ZIP bundle withSKILL.md at its root and only the supporting files
the Skill needs. The metadata multipart part carries the Skill name, optional
description, and target workspace. The body part carries the ZIP.
Bulk-create Skills
Use the bulk endpoint when an application needs to create a one-time batch of new skill bundles. It accepts at most 100 items. Each item in theitems JSON
array supplies the same metadata used for one Skill and a body_part name. The
multipart request includes a ZIP body under each of those names.
Preview. A bulk response is
207 Multi-Status, even when some items were
created. Read every returned item instead of treating the HTTP status alone as
a successful import.items array follows the request order. A 201 item includes the
created skill. A rejected item includes its own status and problem document;
successful items are not rolled back. For a duplicate-content rejection, the
problem can include existing_artifact_id, which identifies the skill that
already holds that content.
Use the returned IDs to inspect every created skill and record failed item
indexes for a corrected retry. Do not resubmit a whole batch until you know
which items were created.
Find and retrieve a version
Use the current Skill when you need the latest maintained package. Use a pinned version when an environment needs reproducible content. The Skill API category covers listing, searching, reading a selected version, and downloading its bundle. Verify that the selected version contains the files your consuming environment expects.application/zip, not JSON. Compare the downloaded
package with the source bundle before a consuming environment uses it.