Skip to content
Back to skills

Shepherd Pull Requests

ASecurity

Run one merge-shepherd tick from the hub over this repository's open pull requests: fast-forward main, arm auto-merge, merge main into behind branches, judge each red Validation check as a rerun or a defect, and name each merged worktree to retire.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 19, 2026
ai-agentspythonshellbash

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned October 19, 2026

npx -y skills add EJRyan89/coding-agent-skills --skill shepherd-pull-requests --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Shepherd Pull Requests?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Shepherd Pull Requests
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ejryan89-shepherd-pull-requests/badge)](https://www.skillsdirectory.com/skills/ejryan89-shepherd-pull-requests)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: shepherd-pull-requests
description: "Run one merge-shepherd tick from the hub over this repository's open pull requests: fast-forward main, arm auto-merge, merge main into behind branches, judge each red Validation check as a rerun or a defect, and name each merged worktree to retire."
argument-hint: "[--dry-run]"
allowed-tools: ["Bash(python -B .claude/skills/shepherd-pull-requests/scripts/shepherd_pull_requests.py *)", "PowerShell(python -B .claude/skills/shepherd-pull-requests/scripts/shepherd_pull_requests.py *)"]
disable-model-invocation: true
---

Read and follow `../../../.claude/skills/shepherd-pull-requests/SKILL.md`, a path relative to this file, as the authoritative workflow.
Run its commands from the repository root, the folder that holds `.agents` and `.claude`, and resolve every relative path it names from there.
A command that writes a shim under `.agents` needs an approval to run outside Codex's sandbox, which keeps `.agents` read-only.

Files in this skill

  • SKILL.md977 B
  • agents/openai.yaml43 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.