babysit-runs SKILL.md skillA

babysit-runs from swyxio/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add swyxio/skills/babysit-runs@git:20261011.a7b8530

Pins git:20261011.a7b8530 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
swyxio/skills
Path
babysit-runs/SKILL.md
Versions recorded
4
Latest version
git:20261011.a7b8530, committed Oct 11, 2026
First version recorded
Sep 16, 2026
Size
14,249 bytes
Repository stars
194
License
MIT

Operate unattended runs through completion, from a single detached pilot to a large batch. Instrument execution, inspect traces and output quality, recover failures, and improve demonstrated performance or reliability problems using the existing workflow and temporary monitoring. Use for supervised pilots, overnight runs and bounded autonomous optimization, not a one-time status check or concurrency advice alone.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Babysit Runs

Operate existing runners toward the authorized outcome at the agreed quality. Prefer targeted repairs over a new scheduler or pipeline rewrite. Use the selected provider/runtime skill when invocation or access needs troubleshooting; use `live-ai-pipelines` only when recovery architecture needs implementation.

## Choose the operating mode

**Completion mode:** finish the authorized workload using the established implementation, repairing defects as needed.

**Pilot-and-improve mode:** exercise an existing or modified workflow on representative inputs, inspect execution and output quality, and make bounded improvements before broader rollout. State what is being tested, the quality baseline, resource/spending limits and the completion boundary. A pilot is complete when the requested behavior is demonstrated and material findings are resolved or clearly reported; optional optimization ideas do not keep it running indefinitely.

## Adopt, detach and schedule
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add swyxio/skills/babysit-runs@sha256:df4d78a10cd576a6

The line at the top of this page pins the label git:20261011.a7b8530, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_fdb27bbte7y4puyl.svg)](https://markdownregistry.com/a/art_fdb27bbte7y4puyl)

8 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Sep 16, 2026 and Oct 11, 2026, about one every 8 days.

versioncommittedcommitsizeaudit
git:20261011.a7b8530 latest2026-10-11 a7b8530 14,249 BA view · diff
git:20261003.6fd282a2026-10-03 6fd282a 11,480 BA view · diff
git:20260916.9d00bd32026-09-16 9d00bd3 8,601 BA view · diff
git:20260916.3fef3ae2026-09-16 3fef3ae 13,131 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (14249 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

GitHub

swyxio/skills · 194 stars · license MIT · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_fdb27bbte7y4puyl
GET https://markdownregistry.com/api/v1/resolve?ref=swyxio/skills/babysit-runs
GET https://markdownregistry.com/api/v1/blob/df4d78a10cd576a6be39644e38309dfa89e7d6a654bdb20fc37ad208441819b1

Your AI assistant 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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from swyxio/skills

AGENTS.md AGENTS.md file
swyxio/skills · AGENTS.md
git:20260328.1e97617 · audit A · 194 stars
accelevents-api SKILL.md skill
swyxio/skills · accelevents-api/SKILL.md · Use when reading or updating AI Engineer Europe speaker records through the Accelevents REST API, especially for…
git:20260528.839ae03 · audit A · 194 stars
accelevents-speaker-sync SKILL.md skill
swyxio/skills · accelevents-speaker-sync/SKILL.md · Use when website speaker, session, schedule, room, track, or headshot changes must be synchronized back to Accelevents…
git:20260528.839ae03 · audit A · 194 stars
agents-sdk SKILL.md skill
swyxio/skills · agents-sdk/SKILL.md · Build or debug stateful applications that specifically use Cloudflare's `agents` package, including Agent classes…
git:20260820.cd23820 · audit A · 194 stars
ai-devblog SKILL.md skill
swyxio/skills · ai-devblog/SKILL.md · Turn coding, debugging, research, architecture, migration, deployment, or product work into a clear, evidence-backed…
git:20261101.b77bec0 · audit A · 194 stars
ai-engineering SKILL.md skill
swyxio/skills · ai-engineering/SKILL.md · Diagnose or improve reliability of a structured, multi-request, rate-limited, or cost-sensitive AI workflow. Use for…
git:20261004.275e470 · audit A · 194 stars
ai-readme SKILL.md skill
swyxio/skills · ai-readme/SKILL.md · Create or substantially revise repository README files that help a specific reader understand a technical project…
git:20260928.efe5ce6 · audit A · 194 stars
align-me SKILL.md skill
swyxio/skills · align-me/SKILL.md · Elicit user preferences and resolve material ambiguity before a long autonomous run. Use when the user invokes…
git:20260928.efe5ce6 · audit A · 194 stars
annotated-video-production SKILL.md skill
swyxio/skills · annotated-video-production/SKILL.md · Plan, edit, render, or audit annotated interviews and host commentary, including source captures, demos, pull quotes…
git:20261103.1acf58f · audit A · 194 stars
antislop-codebase SKILL.md skill
swyxio/skills · antislop-codebase/SKILL.md · Diagnose or execute an explicit repository-wide maintainability cleanup while preserving behavior. Use only when the…
git:20260928.efe5ce6 · audit A · 194 stars
app-ux-paradigms SKILL.md skill
swyxio/skills · app-ux-paradigms/SKILL.md · Apply conventional interaction behavior for keyboard shortcuts, focus, dialogs, overlays, menus, forms, and…
git:20260822.a6cb86f · audit A · 194 stars
autoreview SKILL.md skill
swyxio/skills · autoreview/SKILL.md · Perform a structured final code review of a local diff, commit, branch, or pull request. Use only when the user…
git:20260809.243a0c6 · audit A · 194 stars

Every file in swyxio/skills

Browse by kind, by grade A, or by owner.