pr-babysit
Skill0 starsChanged 4 days agoMITView on GitHub
Watch a GitHub PR end to end. Two lanes: Hermes orchestrates and ships; Grok Build fixes. Run Step R0 to identify the lane, then read only that lane's references.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- elastic/kibanatheir own version, first seen Nov 1, 2026
- turntuptechnologies-ai/skillstheir own version, first seen Aug 6, 2026
- VincentChuWaiChow/vanguard-frontier-agentictheir own version, first seen Jul 31, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- elastic/kibana★ 21ksame name
- VincentChuWaiChow/vanguard-frontier-agentic★ 23same name
- turntuptechnologies-ai/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 repository75 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/skill-authoring/tools/AGENTS.mdAGENTS.md
- aes-docsSkill
- aes-fixSkill
- aes-layerSkill
- aes-migrationSkill
- android-emulator-linux-gpsSkill
- computer-useSkill
- flatpak-chromium-automationSkill
- qwen-webSkill
- grok-buildSkill
- hermes-agentSkill
- omnirouteSkill
- orcaSkill
- account-managerSkill
- brave-setupSkill
- password-managerSkill
- codegraphSkill
- deep-cleanSkill
- dogfoodSkill
- reviewSkill
- systematic-debuggingSkill
- blender-arwakySkill
- comfyuiSkill
- llm-writingSkill
- vision-arwakySkill
- playwright-toolingSkill
- setup-ci-quality-gatesSkill
- statuslineSkill
- systemd-headless-serviceSkill
- xdg-spec-complianceSkill
- figcraft-builderSkill
- figcraft-iconsSkill
- figcraft-motionSkill
- figcraft-prototyperSkill
- figcraft-reviewSkill
- figcraftSkill
- figcraft-svgSkill
- figcraft-typographySkill
- github-authSkill
- issue-makerSkill
- issue-workerSkill
- mergifySkill
- releasingSkill
- repo-managerSkill
- ascii-artSkill
- ascii-videoSkill
- gif-searchSkill
- media-acquisitionSkill
- docxSkill
- emailSkill
- google-workspaceSkill
- notionSkill
- pdfSkill
- pptxSkill
- xlsxSkill
- competitor-news-monitorSkill
- product-price-monitorSkill
- weekly-review-planningSkill
- arxivSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
Read only the winning lane's references.
- Distinctive: line 35
Read only the winning lane's references:
≈ “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
PR Babysitter
Watch a standalone GitHub PR end to end: register it, keep it green, merge it when --ship is active. The pipeline is event-driven — CI re-runs and new review threads each trigger a fresh pass.
Global Rules
This file is the lane identification step only. The lane is determined from physical signals, in this order. Each is observable without asking the agent to name itself. Each agent's launcher stamps a fixed attribution env var into every command it runs. The model cannot set these; only the launcher can.
if [[ -n "${HERMES_AGENT:-}" ]]; then echo HERMES
elif [[ -n "${GROK_AGENT:-}" ]]; then echo GROK
else echo UNSET; fiHERMES→ Hermes lane. Stop.GROK→ Grok lane. Stop.UNSET→ stop and report. Do not guess the lane.
Marker provenance:
- Hermes re-exports
AI_AGENT=hermes-agentandHERMES_AGENT=trueon every command. - Grok Build runs with
GROK_AGENT=1.
Read only the winning lane's references. Do not read the other lane's.
Routing
Read only the winning lane's references:
Hermes lane
| Step | Reference | Purpose |
| 0 | references/hermes/step-0-watch-and-spawn.md | Verify auth, fetch PR, register in the watchlist, check CI once; if red or open threads, spawn a Grok worktree on the head branch and drop the fix brief |
| 1 | references/hermes/step-1-wait-and-reverify.md | Wait for the fix pass; re-run the CI check on the live head SHA; update last_status |
| 2 | references/hermes/step-2-merge.md | Merge (only when ship is true and the ship-ready gates pass on a live re-query); retire the worktree |
| 3 | references/hermes/step-3-final-report.md | Final report to the user (fix passes, outcome, open items, watchlist state) |
Grok lane
| Step | Reference | When it runs |
| 0 | references/grok/step-0-add-pr.md | PR details, repo, head/base refs for the pass |
| 1 | references/grok/step-1-watch-ci.md | Always, at the start of the pass |
| 2 | references/grok/step-2-auto-fix.md | CI reports a red check; loops back to step 1 after each push. Commit title grammar: Conventional Commits inline |
| 3 | references/grok/step-3-decision-tree.md | After each step 2 push and always before declaring the PR green; CI logs ambiguous → references/grok/step-3-troubleshoot.md |
| 4 | references/grok/step-4-merge.md | Ship-ready gate checks; Grok reports merge-ready (Hermes performs the merge) |
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.