repo-actions

Generate five anchored action ideas for watched GitHub repositories via GraphQL.

Updated Jun 2, 2026
One-click install
npx skills add https://github.com/Atrium-Hermes/atrium-lighthouse --skill repo-actions-atrium-hermes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: repo-actions
Source: https://github.com/Atrium-Hermes/atrium-lighthouse/tree/main/skills/repo-actions
Command: npx skills add https://github.com/Atrium-Hermes/atrium-lighthouse --skill repo-actions-atrium-hermes

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It converts high-level repo maintenance goals into five concrete, anchored actions for a watched repository, enabling proactive improvements without back-and-forth planning.

Core Features & Use Cases

  • Anchored actions tied to actual repo state (ISSUE, PR, TODO, MISSING file, or DEP)
  • Priority-ranked output with a Top Pick verdict
  • Generated article saved to articles/repo-actions-${TODAY}.md

Quick Start

Ask the AI to generate five anchored, implementable repo actions for the currently watched repository.

Frequently Asked Questions about repo-actions

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate actionable maintenance tasks for a watched GitHub repository?

Concrete GitHub repo actions are identified by analyzing repository state via GitHub GraphQL and local memory, covering issues, pull requests, TODOs, missing files, and dependencies. It outputs a Markdown article with five anchored actions and a Top Pick verdict.

What is a Top Pick verdict in automated issue management?

A Top Pick verdict in issue management is the highest-scored action selected from five concrete repository improvements. It applies gating and scoring based on leverage, concreteness, and novelty to highlight the most impactful task.

How do I prioritize GitHub pull requests and issues automatically?

You can prioritize GitHub pull requests and issues automatically by applying gating and scoring mechanisms that evaluate leverage, concreteness, and novelty. This skill analyzes repository state and outputs a priority-ranked list of five implementable actions.

Does this GitHub automation tool require a watched-repos.md file?

Yes, this GitHub automation tool requires a local memory file named watched-repos.md. The skill uses this file to identify the target repository scope before analyzing state via GitHub GraphQL and generating the anchored action ideas.

Can I use GitHub GraphQL to find missing files and dependencies in my repository?

Yes, you can use GitHub GraphQL to find missing files and dependencies by analyzing repository state alongside local memory. This skill queries the API to identify gaps, applies scoring for leverage and novelty, and outputs actionable improvement tasks.

What are the limitations of automated repo gatekeeping for issue prioritization?

Automated repo gatekeeping for issue prioritization is limited to repositories listed in local memory and relies on GitHub GraphQL API availability. It outputs a static Markdown article rather than executing actions or creating pull requests directly.