Babysit Runs

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.

201 stars 12 forksDevOps & Cloud

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add swyxio/skills --skill babysit-runs
Manual install
git clone --depth 1 https://github.com/swyxio/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/babysit-runs ~/.claude/skills/babysit-runs

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 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

Inspect actual processes, owners, logs and retained results. Adopt a matching live run rather than launch a duplicate. Discover routine facts from existing metadata and task history instead of re-interviewing the user.

Keep a compact continuation brief in the existing run metadata or monitor prompt:

- Goal, operating mode, scope, checkout, command, owner and run/log/artifact locations.
- Requested model/provider, shared concurrency ceiling, independent transfer limits and applicable resource/cost bounds.
Read the full skill on GitHub

Details

Skill name
babysit-runs
Repository
swyxio/skills
Path
babysit-runs/SKILL.md
License
MIT
Repo updated
16 November 2026

FAQ

What does the Babysit Runs skill do?

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.

How do I install the Babysit Runs skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add swyxio/skills --skill babysit-runs. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Babysit Runs popular?

It lives in swyxio/skills, which has 201 GitHub stars and 12 forks.

Related skills

Accelevents API

201

swyxio/skills

Use when reading or updating AI Engineer Europe speaker records through the Accelevents REST API, especially for full-record PUT updates, auth header quirks, and preserving existing speaker fields.

Software Development12

Accelevents Speaker Sync

201

swyxio/skills

Use when website speaker, session, schedule, room, track, or headshot changes must be synchronized back to Accelevents for AI Engineer Europe 2026.

AI, LLMs & Agents12

Agents SDK

201

swyxio/skills

Build or debug stateful applications that specifically use Cloudflare's `agents` package, including Agent classes, routing, callable methods, synchronized state, scheduling, AIChatAgent, durable execution, or Agents SDK client hooks. Do not trigger for generic AI-agent design, the OpenAI Agents SDK, or ordinary Durable Object work that does not use the Cloudflare Agents SDK.

AI, LLMs & Agents12

Cloudflare

201

swyxio/skills

Route an ambiguous or cross-product Cloudflare platform request to the appropriate product, documentation, or narrower local skill. Use when the user needs help choosing among Cloudflare compute, storage, AI, networking, security, media, or infrastructure products. Do not trigger when the request already names a specific Cloudflare product or matches a narrower installed skill.

DevOps & Cloud12

Align Me

201

swyxio/skills

Elicit user preferences and resolve material ambiguity before a long autonomous run. Use when the user invokes $align-me or /align-me, or asks to be interviewed, grilled, aligned, or given a batch of decisions before implementation, migration, deployment, design, or other consequential work.

DevOps & Cloud12

Cloudflare Do Turn Based Multiplayer

201

swyxio/skills

Design, implement, debug, or verify a remote turn-based multiplayer game whose rooms run on Cloudflare Durable Objects. Use for room and invite identity, reconnectable seats, WebSocket hibernation, concurrent turns, action idempotency, revision conflicts, or cross-browser game-state agreement. Do not trigger for generic Durable Object applications or local-only games.

DevOps & Cloud12

Browse the most popular Claude skills, all devops & cloud skills, or write your own with the skills generator.