> ## Documentation Index > Fetch the complete documentation index at: https://docs.labelbox.com/llms.txt > Use this file to discover all available pages before exploring further. # Create a skill and immutable version > Creates a skill from a SKILL.md document and returns it. The document's frontmatter supplies the skill's name and description, which are validated against the Agent Skills standard: the name must be lowercase letters, digits, and single hyphens, and a description is required because it is the only signal the model has when deciding whether to use the skill. Send a multipart/form-data body with a `bundle` part instead to upload a zipped skill directory, whose scripts/ and references/ are mounted into the sandbox for sessions that attach it. ## OpenAPI ````yaml /managed-agents/openapi.yaml post /managed-agents/v1/skills openapi: 3.1.0 info: title: Managed Agents API version: 0.13.0 description: >- The Recursion Managed Agents REST API. Authenticate with a Recursion API key as a bearer token. An organization-scoped key acts in its own organization and needs nothing else; a tenant-scoped key must also send `x-organization-id` with an organization id or `default`. Field names follow each operation's published schema. servers: - url: https://api.recursion.labelbox.com security: - bearerAuth: [] paths: /managed-agents/v1/skills: post: tags: - Skills summary: Create a skill and immutable version description: >- Creates a skill from a SKILL.md document and returns it. The document's frontmatter supplies the skill's name and description, which are validated against the Agent Skills standard: the name must be lowercase letters, digits, and single hyphens, and a description is required because it is the only signal the model has when deciding whether to use the skill. Send a multipart/form-data body with a `bundle` part instead to upload a zipped skill directory, whose scripts/ and references/ are mounted into the sandbox for sessions that attach it. operationId: managedAgentsCreateSkill requestBody: content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsSkillRequest' multipart/form-data: schema: $ref: >- #/components/schemas/ManagedAgentsFormDataSkillBundleUploadRequest required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsSkill' description: >- A reusable procedure an agent loads when it judges the procedure relevant. Its name and description are disclosed in every turn; the instructions enter the conversation only when the agent activates it. Updating a skill mints a new immutable SkillVersion. '400': description: The request was rejected by schema or semantic validation. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '401': description: The caller is unauthenticated. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '403': description: The caller lacks a required permission or capability. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorForbidden' '404': description: No such resource is reachable for this caller. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorNotFound' '409': description: >- The request conflicts with the resource state, or with an in-flight idempotent replay. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '413': description: The request exceeds a size or transaction budget. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '415': description: The request body uses a media type this operation does not accept. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorUnsupportedMediaType' '429': headers: Retry-After: description: Seconds the caller should wait before retrying. schema: type: string style: simple description: A rate limit is exhausted. Honor `Retry-After`. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '500': description: An unexpected server-side failure. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '502': description: The service returned an invalid response. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorBadGateway' '503': headers: Retry-After: description: Seconds the caller should wait before retrying. schema: type: string style: simple description: A dependency is unavailable. Retryable. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '504': headers: Retry-After: description: When to retry, as delay seconds or an HTTP date. schema: type: string description: The service did not respond before the timeout. Retryable. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorGatewayTimeout' components: schemas: ManagedAgentsSkillRequest: description: >- Request body for creating or updating a skill. The document is the source of truth: the skill's name and description come from its frontmatter. Publishing a new version of an existing skill goes through createSkillVersion, which mints one rather than editing the last. properties: display_title: description: Human-readable title for listings. Defaults to the frontmatter name. type: string document: description: >- The complete SKILL.md: YAML frontmatter delimited by --- on the very first line, then Markdown instructions. name and description are required in the frontmatter and are read from it. type: string manifest: description: >- Relative paths of files bundled with the skill, listed to the model when it activates the skill. Paths must stay inside the skill directory. items: type: string type: array metadata: additionalProperties: {} description: >- Caller-owned key/value data stored with the skill and returned unchanged. type: object skill_group_id: description: >- Catalog group to file this skill under. Send an empty string to remove it from its group; omit to leave the group unchanged. Grouping is for browsing and bulk attachment only and is never disclosed to the model. type: - 'null' - string required: - document type: object example: display_title: example document: example manifest: - example metadata: key: example skill_group_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d ManagedAgentsFormDataSkillBundleUploadRequest: description: >- Multipart body carrying a zipped skill directory in the bundle part. The document, name and description still come from the archive's SKILL.md. properties: bundle: contentMediaType: application/octet-stream description: >- A zipped skill directory: SKILL.md at its root or one level down, plus optional scripts/, references/ and assets/. Files under scripts/ are mounted executable. format: binary type: string display_title: description: Human-readable title for listings. Defaults to the frontmatter name. type: string metadata: description: >- Caller-owned key/value data as a JSON object, since a form part cannot carry structure. Rejected rather than dropped when it does not parse. type: string skill_group_id: description: >- Catalog group to file this skill under. Present and empty removes it from its group; omit the part to leave the group unchanged. type: string type: object example: bundle: example display_title: example metadata: example skill_group_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d ManagedAgentsSkill: description: >- A reusable procedure an agent loads when it judges the procedure relevant. Its name and description are disclosed in every turn; the instructions enter the conversation only when the agent activates it. Updating a skill mints a new immutable SkillVersion. properties: created_at: description: Server-assigned RFC 3339 timestamp of when the skill was created. format: date-time type: string description: description: >- When to use this skill. Disclosed to the model in every turn, so it is the whole routing signal: write it as the condition under which the skill applies. type: string display_title: description: >- Human-readable title shown wherever skills are listed. Defaults to the name. type: string latest_instruction_chars: description: >- Length in characters of the newest version's instructions, the body disclosed to the model when it activates the skill. Zero for a skill with no version yet. Instructions are truncated at 64000 characters when a session assembles them. format: int64 type: integer latest_skill_version_id: description: >- Server-maintained id of the newest version of this skill; agents that attach it without pinning a version use this one. type: string latest_version_number: description: >- How many versions this skill has, which is also the number of the newest one, since versions are numbered from 1 in creation order. Zero for a skill with no version yet. format: int64 type: integer metadata: additionalProperties: {} description: >- Caller-owned key/value data stored with the skill and returned unchanged. type: object name: description: >- The skill's addressable name, lowercase with single hyphens, e.g. cut-release. This is what an agent passes to the activation tool. type: string organization_id: description: >- Organization that owns the skill. Server-assigned from the caller's credentials; a value sent in a request body is ignored. type: string skill_group_id: description: >- Catalog group this skill is filed under, if any. Grouping is for browsing and for attaching a set of skills to an agent in one entry; it is never disclosed to the model and does not scope the skill's name. type: string skill_id: description: >- Server-assigned id of the skill, used in the skill and skill-version routes. type: string source: description: >- Where the skill came from: platform, organization, or repository. Decides which skill wins a name collision, most specific first. type: string updated_at: description: >- Server-assigned RFC 3339 timestamp of the most recent update to the skill. format: date-time type: string required: - organization_id - skill_id - name - description - source - created_at - updated_at type: object example: created_at: '2026-02-18T09:30:00.000Z' description: example display_title: example latest_instruction_chars: 1 latest_skill_version_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d latest_version_number: 1 metadata: key: example name: example-name organization_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d skill_group_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d skill_id: 9f8b1c2d-3e4f-5a6b-7c8d-9e0f1a2b3c4d source: example updated_at: '2026-02-18T09:30:00.000Z' ManagedAgentsApiError: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - analytics - analytics_not_ready - artifact_fetch_unavailable - artifact_generation_mismatch - artifact_hash_mismatch - artifact_invalid_events - artifact_invalid_json - artifact_not_allowlisted - artifact_size_mismatch - atomic_ingest_timeout - auth_unavailable - automation_event_source_invalid - automation_memory_unavailable - automation_reference_invalid - automation_runs_unconfigured - automations_unconfigured - bad_gateway - built_in_catalog_unavailable - built_in_integrations_unconfigured - compute_offerings_unavailable - conflict - content_store_request_canceled - content_store_unavailable - content_store_upload_timeout - credential_encryption_unconfigured - delegate_preparation_failed - entity_family_not_permitted - environment_not_verified - evaluation_cancellation_pending - evaluation_deletion_pending - event_admission_unavailable - event_ingress_unavailable - event_source_verification_credential_invalid - event_sources_unconfigured - execution_unconfigured - file_quota_exceeded - file_storage_unconfigured - forbidden - gateway_timeout - gestalt_unconfigured - github_rate_limited - github_unavailable - handoff_access_invalid - handoff_access_unavailable - handoff_access_unsupported - handoff_capture_unavailable - handoff_requires_retest - handoff_revoke_unavailable - handoff_signal_unavailable - idempotency_conflict - idempotency_in_progress - idempotency_unavailable - ingest_policy_changed - ingest_policy_not_found - ingest_policy_revoked - integrations_unconfigured - internal_error - invalid_json - invalid_pull_request_review_result - invalid_request - invalid_scope - invariant_violation - live_fleet_unconfigured - managed_agents_unavailable - missing_dependency - model_gateway_metadata_missing - model_gateway_unconfigured - model_gateway_unreachable - mutation_transaction_budget_exceeded - not_found - page_token_expired - payload_too_large - persistence_busy - precondition_failed - precondition_required - provider_registration_unsupported - provider_selection_unsupported - rate_limit_exceeded - rate_limited - repository_automation_unconfigured - request_too_large - reserved_source_type - revision_conflict - run_log_store_unavailable - runner_image_resolution_failed - sandbox_provider_disabled - service_unavailable - session_analyst_busy - session_analyst_model_unavailable - session_analyst_unconfigured - session_start_admission_unavailable - session_start_not_admitted - setup_fallback_environment_unsafe - setup_run_finished - setup_run_in_progress - setup_run_limit - setup_run_not_started - setup_runs_unavailable - skill_storage_unconfigured - slack_channels_rejected - slack_channels_unavailable - slack_channels_unconfigured - slack_connection_malformed - slack_event_intake_unavailable - slack_installation_mismatch - slack_missing_scope - slack_rate_limited - slack_reapproval_required - source_ownership_mismatch - source_revision_conflict - spanner_unavailable - streaming_unsupported - submission_transaction_budget_exceeded - task_version_number_conflict - team_board_unconfigured - too_many_streams - unauthorized - unsupported_media_type - vault_creation_retired - version_content_conflict - webhook_delivery_too_large - workspace_boundary_denied message: type: string minLength: 1 description: Human-readable error message. details: description: Optional structured error details. type: object propertyNames: type: string additionalProperties: {} required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorForbidden: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - forbidden message: type: string minLength: 1 description: Human-readable error message. details: description: Optional structured error details. type: object propertyNames: type: string additionalProperties: {} required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorNotFound: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - not_found message: type: string minLength: 1 description: Human-readable error message. details: description: Optional structured error details. type: object propertyNames: type: string additionalProperties: {} required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorUnsupportedMediaType: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - unsupported_media_type message: type: string minLength: 1 description: Human-readable error message. details: description: Optional structured error details. type: object propertyNames: type: string additionalProperties: {} required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorBadGateway: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - bad_gateway message: type: string minLength: 1 description: Human-readable error message. details: description: Optional structured error details. type: object propertyNames: type: string additionalProperties: {} required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorGatewayTimeout: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - gateway_timeout message: type: string minLength: 1 description: Human-readable error message. details: description: Optional structured error details. type: object propertyNames: type: string additionalProperties: {} required: - code - message additionalProperties: false description: Standard flat error response. securitySchemes: bearerAuth: type: http scheme: bearer description: A Recursion API key, created in the console under API keys. ````