> ## Documentation Index > Fetch the complete documentation index at: https://docs.neoagent.io/llms.txt > Use this file to discover all available pages before exploring further. # Run a skill script in the sandbox (SSE) > Run one script of the skill in the tenant's code sandbox and stream its output. The run borrows the integration permissions of `agent_id` in read-only mode: every write to a connected system is refused by the sandbox proxy, and no technician approval is involved. Send unsaved drafts in `files` to run them instead of the saved files; the saved skill is never changed by a run. Response is `text/event-stream` — stream it, don't buffer. Events: `status` `{phase}`, `output` `{stream, data}` as the script prints, and a final `done` `{run_id, outcome, exit_code, failure_reason, duration_ms}`. Closing the stream stops the script. A run is limited to 120 seconds and 500 KB of output, and to 30 runs per hour per user. Read the recorded run back with GET .../test-runs/{run_id}. ## OpenAPI ````yaml https://api.neoagent.io/public-api/openapi.json post /public-api/skills/{skill_id}/test-runs openapi: 3.1.0 info: description: >- Neo's public contract for the dashboard ChatAgent, partner integrations, and MSP automation. Every response is wrapped in a `{data, meta}` envelope; errors use `{error: {code, message, details?}, meta: {request_id}}`. Authenticate with a `Bearer neo_sk__` API key (service account) or a Microsoft Entra ID JWT (dashboard user). Signed-URL endpoints (end-user feedback links) take a `signature` query parameter instead. title: Neo Public API version: 1.0.0 servers: - url: https://api.neoagent.io security: [] tags: - description: Service metadata — health, OpenAPI. name: Meta - description: Agents and workflows — read, version history, delete, stats. name: Agents - description: Agent/workflow execution history, sub-resources, retry/cancel. name: Executions - description: PSA webhook events and their workflow-match results. name: Callbacks - description: Technician-in-the-loop approval requests. name: TIL requests - description: RMM script executions triggered by agents. name: RMM scripts - description: Dispatch-agent field-update decisions. name: Dispatch - description: The authenticated tenant. name: Tenant - description: Agent-builder schema catalogs (raw JSON payloads). name: Schemas - description: Escalate to the Neo team (HubSpot ticket). name: Escalation - description: Tenant settings. name: Settings - description: Tenant API-key management (dashboard JWT only). name: API keys - description: End-user feedback links (signed-URL auth). name: Feedback - description: End-client companies (CRUD + bulk-update). name: End companies - description: Channels — bind a CONVERSATIONAL agent to a transport (Teams). name: Channels - description: PSA/RMM/M365 integration status and connection management. name: Integrations - description: Technician roster (controls TIL routing and paging). name: Technicians - description: Future runs queued for TRIGGERED agents. name: Scheduled work - description: Subscription state and customer-facing credit usage (no provider $). name: Billing - description: Inbox messages and announcements. name: Inbox & Comms - description: Tenant-authored agent skills (CRUD) and the built-in skill catalog. name: Skills paths: /public-api/skills/{skill_id}/test-runs: post: tags: - Skills summary: Run a skill script in the sandbox (SSE) description: >- Run one script of the skill in the tenant's code sandbox and stream its output. The run borrows the integration permissions of `agent_id` in read-only mode: every write to a connected system is refused by the sandbox proxy, and no technician approval is involved. Send unsaved drafts in `files` to run them instead of the saved files; the saved skill is never changed by a run. Response is `text/event-stream` — stream it, don't buffer. Events: `status` `{phase}`, `output` `{stream, data}` as the script prints, and a final `done` `{run_id, outcome, exit_code, failure_reason, duration_ms}`. Closing the stream stops the script. A run is limited to 120 seconds and 500 KB of output, and to 30 runs per hour per user. Read the recorded run back with GET .../test-runs/{run_id}. operationId: public_api.skills_test_run_create_post parameters: - in: path name: skill_id required: true schema: type: string requestBody: content: application/json: examples: run_a_draft: summary: Run an edited script before saving it value: agent_id: 23433 args: - '--month' - 2026-08 entry_path: scripts/reconcile.py files: - content: | print('reconcile v2') path: scripts/reconcile.py schema: $ref: '#/components/schemas/SkillTestRunRequest' required: true responses: '200': content: application/json: schema: properties: data: description: Operation-specific payload. meta: $ref: '#/components/schemas/SuccessMeta' required: - data - meta type: object description: Success. '400': content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' description: Bad request — malformed input. '401': content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' description: Unauthenticated — missing or invalid credentials. '403': content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' description: Forbidden — authenticated but not allowed. '404': content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' description: Not found. '409': content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' description: Conflict — the resource is in a state that blocks this operation. '422': content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' description: Request validation failed. '429': content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' description: Rate limited — see Retry-After. '500': content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' description: Internal server error. security: - bearerAuth: [] components: schemas: SkillTestRunRequest: description: >- POST /skills/{id}/test-runs — run one script of the skill in the tenant sandbox. properties: agent_id: description: >- The agent whose integration permissions the run borrows. Every proxied call (PSA, Microsoft 365, RMM, ...) is authorised as this agent, in read-only mode. Must be an agent of your own tenant that you may edit; Neo-managed and end-user agents are refused. title: Agent Id type: integer args: description: Command-line arguments passed to the script. items: type: string title: Args type: array entry_path: description: >- The script to run, as a path inside the skill, e.g. `scripts/run.py`. title: Entry Path type: string files: description: >- Unsaved drafts to run instead of the saved files at the same paths. The saved skill is not changed. Omit to run the saved skill as it is. items: $ref: '#/components/schemas/SkillFileInput' title: Files type: array required: - agent_id - entry_path title: SkillTestRunRequest type: object SuccessMeta: properties: pagination: $ref: '#/components/schemas/Pagination' request_id: format: uuid type: string timings_ms: additionalProperties: type: number type: object warnings: description: >- Non-fatal warnings about the created/updated resource (e.g. an unhealthy PSA callback). items: type: string type: array required: - request_id - timings_ms type: object ErrorEnvelope: properties: error: properties: code: description: Stable machine-readable error code. type: string details: additionalProperties: true type: object message: type: string required: - code - message type: object meta: properties: request_id: format: uuid type: - string - 'null' type: object required: - error - meta type: object SkillFileInput: properties: content: title: Content type: string path: title: Path type: string required: - path - content title: SkillFileInput type: object Pagination: properties: has_more: type: boolean next_cursor: type: - string - 'null' required: - next_cursor - has_more type: object securitySchemes: bearerAuth: description: >- `Authorization: Bearer ` where `` is either a `neo_sk__` API key (service account) or a Microsoft Entra ID access token (dashboard user). scheme: bearer type: http ````