Skip to content
Back to skills

Policyengine Github Agent Skill

ASecurity

Guidance for working with the PolicyEngine GitHub agent bot

  • 666 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added June 10, 2026
ai-agentsreactgit

Security analysis

A100/100

Scanned June 10, 2026

npx -y skills add majiayu000/claude-skill-registry --skill policyengine-github-agent-skill --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Policyengine Github Agent Skill?

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

Security grade badge for Policyengine Github Agent Skill
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majiayu000-policyengine-github-agent-skill/badge)](https://www.skillsdirectory.com/skills/majiayu000-policyengine-github-agent-skill)

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: policyengine-github-agent-skill
description: Guidance for working with the PolicyEngine GitHub agent bot
---

# PolicyEngine GitHub Agent Skill

## For Users 👥

The PolicyEngine GitHub agent is an automated bot that can be invoked on GitHub issues and pull requests using `@policyengine` mentions. It helps with code reviews, bug fixes, and implementing features across PolicyEngine repositories.

## For Contributors 💻

### Critical: Avoiding Doom Loops

**NEVER use '@policyengine' or '@policyengine-auto' in bot responses.** These mentions trigger the bot and create infinite loops where the bot repeatedly responds to itself.

#### Why This Matters

When the bot posts a comment containing `@policyengine`, GitHub notifies the bot account, which triggers another invocation. This creates a chain reaction of bot responses that can generate dozens or hundreds of comments before being stopped. See [PR #22](https://github.com/PolicyEngine/policyengine-github-agent/pull/22) for a real example of this issue.

#### Safe Alternatives

Instead of mentioning the bot directly:

❌ **Don't do this:**
- "Thanks @policyengine for the suggestion!"
- "I've addressed @policyengine's feedback"
- "cc @policyengine-auto"

✅ **Do this instead:**
- "I've implemented the suggested changes"
- "The feedback has been addressed"
- "Updated based on the review comments"
- Simply refer to "the bot" or "the agent" without the @ mention

### Bot Invocation

The bot can only be invoked by members of the [PolicyEngine/core-developers](https://github.com/orgs/PolicyEngine/teams/core-developers) team. Non-members will receive a permission error.

### Response Style

When the bot responds to issues or PRs:
- Keep responses concise and actionable
- Focus on the technical task at hand
- Avoid unnecessary pleasantries or acknowledgments
- Never include @ mentions of the bot usernames

## Resources

- [policyengine-github-agent repository](https://github.com/PolicyEngine/policyengine-github-agent)
- [PR #22: Stop doom loops](https://github.com/PolicyEngine/policyengine-github-agent/pull/22)

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.