job-babysitting skillA
job-babysitting is agent-read markdown (skill) from uchicago-dsi/ai-sci-skills: Directly monitor long-running jobs or pipelines, classify them as healthy, waiting, stalled, failed, completed, or unknown, and choose the next action. Use when the active agent needs to babysit training runs, batch jobs, services, experiments, or scheduled work over time..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Job Babysitting ## Treat Babysitting As State Classification - Babysitting means maintaining an evidence-backed view of whether work is progressing and intervening only when the evidence supports it. - Compose this skill with scheduler, experiment, or domain skills. Use those skills for platform-specific commands and this skill for monitoring logic. - Reuse the project's existing monitoring signals before inventing a new dashboard or parser. - The active agent owns the monitoring loop end to end. Do not hand the work to a separate service, timer, watcher, or one-off agent. ## Run The Monitoring Loop Directly 1. Define the requested terminal or decision condition. 2. Define progress signals and their expected cadence before polling. 3. Inspect scheduler or process state, then verify logs and expected artifacts. 4. Classify the state and take only the proportionate next action. 5. Report the evidence, wait for the next meaningful cadence, and repeat. - Continue until the terminal condition is met, the user stops monitoring, or a genuine blocker requires new authority or information. …
Read the whole file at its exact version.
How to install
mdr add uchicago-dsi/ai-sci-skills/job-babysitting@git:20260921.9b3de7cmdr add uchicago-dsi/ai-sci-skills/job-babysitting@sha256:e0801cab9d6f8f19Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_nwuf633o7kbkmlkv)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260921.9b3de7c latest | 2026-09-21 | 9b3de7c | 8,538 B | A | view · diff |
| git:20260712.08fd83c | 2026-07-12 | 08fd83c | 5,410 B | A | view · diff |
| git:20260320.999ac68 | 2026-03-20 | 999ac68 | 4,229 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8538 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
uchicago-dsi/ai-sci-skills · 20 stars · license MIT · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_nwuf633o7kbkmlkv GET https://markdownregistry.com/api/v1/resolve?ref=uchicago-dsi/ai-sci-skills/job-babysitting GET https://markdownregistry.com/api/v1/blob/e0801cab9d6f8f1939eff19613f25988fde8c24a30f1e81c580be2382b2ca37e
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.