babysit-my-prs
Skill816 starsChanged 10 days agoApache-2.0View on GitHub
Triage and shepherd all open PRs owned by the current GitHub user, isolating each writable worker in its own worktree. Use when asked to babysit or monitor the user's PR fleet.
- Commits and pushes
1 other project uses a version of this.
Adopted by
Most recently taken up by
- venables/skillstheir own version, first seen Sep 12, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- venables/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- babysit-prSkill
- closeout-reviewSkill
- implement-to-draft-prSkill
- integrationSkill
- mutation-checkSkill
- reviewSkill
- closeout-reviewSkill
- mutation-checkSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Clean: no actionable feedback, required checks present and green, and no conflict.
- Very specific: line 21
When parallel agents are available and the user requested action, delegate one worker per work-needed PR.
- Distinctive: line 27
If recurring monitoring is available and requested, schedule a sweep with a non-overlapping cadence, keep lock/deferred state outside the …
- Distinctive: line 33
Every sweep reports open, in-flight, dispatched, deferred, and clean counts and prints the full deferred-decision ledger.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Babysit My PRs
Authenticate gh, derive the current user and origin repository, then discover
all open PRs authored by that user. Never touch another author's branch.
For each PR, collect CI state, required-job presence, base divergence, merge state, inline review threads, top-level reviews, and PR comments. Classify it as:
- Work needed: a mechanical base merge, settled CI fix, or concrete review correction.
- Deferred: a semantic conflict, optional suggestion, integration-host failure, scope/security/design judgment, or ambiguous feedback.
- Clean: no actionable feedback, required checks present and green, and no conflict.
When parallel agents are available and the user requested action, delegate one
worker per work-needed PR. Each worker must use a separate detached worktree,
acquire a per-PR lock, and follow babysit-pr. Push
with git push origin HEAD:refs/heads/<branch>; never update the parent
checkout's branch ref. Do not dispatch deferred items.
If recurring monitoring is available and requested, schedule a sweep with a non-overlapping cadence, keep lock/deferred state outside the repository, and run an initial sweep immediately. If the environment has no scheduler, perform one sweep and state that limitation; do not emulate a daemon with a blocking sleep loop.
Every sweep reports open, in-flight, dispatched, deferred, and clean counts and prints the full deferred-decision ledger. Stop recurring monitoring only when asked. Running workers may finish, but no new workers should be dispatched after stop.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.