Background job management — start, monitor, wait, stop long-running commands. ALWAYS invoke this skill when the user asks to run background tasks, check job status, read job output, or manage long-run
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add YaoApp/yao --skill yao-job -a cursor -y
Background job management — start, monitor, wait, stop long-running commands. ALWAYS invoke this skill when the user asks to run background tasks, check job status, read job output, or manage long-running commands.
Background job management — start, monitor, wait, stop long-running commands. ALWAYS invoke this skill when the user asks to run background tasks, check job status, read job output, or manage long-running commands.
yao_job_start — Start a command. background false (default) blocks until done and returns output_tail; background true returns immediately.job_idyao_job_list — List jobs. Supports --status filter and --limit/--offset pagination.yao_job_get — Get full details for a job (or daemon by ID).yao_job_output — Read process output (works for both job and daemon IDs).yao_job_wait — Block until a background job finishes or timeout expires. Jobs only, not daemons.yao_job_stop — Kill a running job.| Param | Required | Default | Description |
|---|---|---|---|
command | yes | — | Shell command to execute |
description | yes | — | Concise 5–10 word summary |
background | no | false | true returns immediately; false blocks until done |
args | no | — | Additional arguments (rarely needed; prefer inline in command) |
working_dir | no | workspace | Working directory |
max_duration_ms | no | — | Kill the job after this many milliseconds |
| Param | Default | Description |
|---|---|---|
status | all | Filter: running, stopping, completed, failed, cancelled, all |
limit | 20 | Max items per page |
offset | 0 | Skip first N items |
| Param | Required | Description |
|---|---|---|
job_id | yes | Job or daemon ID |
offset | no | Byte offset to read from (0 = beginning) |
Output read behavior:
offset in a single read (no limit parameter).lossy=true in the response.size = total bytes the process has produced; offset = earliest readable byte position.size=20000000, offset≈10000000, lossy=true — the first ~10 MB was discarded.| Param | Required | Default | Description |
|---|---|---|---|
job_id | yes | — | Job ID |
timeout_ms | no | 60000 | Timeout in milliseconds |
All responses are JSON. Job objects contain:
id, kind, session_id, status, description, background,
command, command_argv, command_line, pid, pgid, user,
started_at, finished_at, duration_ms, exit_code, signal, detail, seq
Returns the job object plus output_tail (≤4KB tail of stdout+stderr):
{ "id": "job_...", "status": "completed", "exit_code": 0, ..., "output_tail": "hello world\n" }
{ "jobs": [...], "total": 130, "offset": 0, "limit": 20, "has_more": true }
{ "job": { ... }, "timed_out": false }
{ "job": { ... }, "detail": "already in terminal state (failed); no action taken" }
Structured JSON with code and message:
{ "error": { "code": "invalid_argument", "message": "job_id is required" } }
Codes: invalid_argument, not_found, internal.
background true (not bare --background) for commands expected to run longer than 30 seconds.description.yao_job_output to check progress.yao_job_wait to block until a background job completes rather than polling.When a background job finishes, the system delivers a <BackgroundJobReceipt> XML message. Upon receiving it:
status, exit_code, cause, and output_tail.status=failed, investigate and take corrective action.status=completed, acknowledge and continue the task.