github-notification-triage

Triage GitHub notifications and report actions needed.

290 stars

Best use case

github-notification-triage is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Triage GitHub notifications and report actions needed.

Teams using github-notification-triage should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/github-notification-triage/SKILL.md --create-dirs "https://raw.githubusercontent.com/notque/claude-code-toolkit/main/skills/github-notification-triage/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/github-notification-triage/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How github-notification-triage Compares

Feature / Agentgithub-notification-triageStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Triage GitHub notifications and report actions needed.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# GitHub Notification Triage Skill

Fetch, classify, and report on GitHub notifications. The script does the heavy lifting — this skill orchestrates invocation and presents results.

## Commands

```bash
# Report-only (default): show what needs attention, no modifications
python3 scripts/github-notification-triage.py

# Mark informational notifications as read after reporting
python3 scripts/github-notification-triage.py --mark-read

# Save report to ~/.claude/reports/notifications/
python3 scripts/github-notification-triage.py --save

# Cron/scheduled mode: auto-clear noise and save report
python3 scripts/github-notification-triage.py --mark-read --save
```

## Instructions

### Step 1: Run the triage script

Run report-only by default:

```bash
python3 scripts/github-notification-triage.py
```

### Step 2: Present the report

Display the script output directly to the user. The report classifies notifications into:
- **Action required** — PRs awaiting review, mentions, assigned issues
- **Informational** — CI results, bot comments, automated updates (safe to clear)

### Step 3: Handle follow-up

If the user responds with any of the following, re-run with `--mark-read`:
- "clean them up"
- "mark read"
- "clear the noise"
- "yes" (in response to a prompt about clearing informational items)

```bash
python3 scripts/github-notification-triage.py --mark-read
```

Confirm how many notifications were marked read after the run completes.

### Cron/scheduled mode

When invoked on a schedule (no interactive user), use both flags to auto-clear and persist the report:

```bash
python3 scripts/github-notification-triage.py --mark-read --save
```

## Exit Codes

| Code | Meaning |
|------|---------|
| 0    | Success |
| 1    | Error (auth failure, API error, script not found) |

Related Skills

github-actions-check

290
from notque/claude-code-toolkit

Check GitHub Actions CI status and report failures.

x-api

290
from notque/claude-code-toolkit

Post tweets, build threads, upload media via the X API.

worktree-agent

290
from notque/claude-code-toolkit

Mandatory rules for agents in git worktree isolation.

workflow

290
from notque/claude-code-toolkit

Structured multi-phase workflows: review, debug, refactor, deploy, create, research, and more.

workflow-help

290
from notque/claude-code-toolkit

Interactive guide to workflow system: agents, skills, routing, execution patterns.

wordpress-uploader

290
from notque/claude-code-toolkit

WordPress REST API integration for posts and media uploads.

wordpress-live-validation

290
from notque/claude-code-toolkit

Validate published WordPress posts in browser via Playwright.

with-anti-rationalization

290
from notque/claude-code-toolkit

Anti-rationalization enforcement for maximum-rigor task execution.

voice-writer

290
from notque/claude-code-toolkit

Unified voice content generation pipeline with mandatory validation and joy-check. 8-phase pipeline: LOAD, GROUND, GENERATE, VALIDATE, REFINE, JOY-CHECK, OUTPUT, CLEANUP. Use when writing articles, blog posts, or any content that uses a voice profile. Use for "write article", "blog post", "write in voice", "generate content", "draft article", "write about".

voice-validator

290
from notque/claude-code-toolkit

Critique-and-rewrite loop for voice fidelity validation.

vitest-runner

290
from notque/claude-code-toolkit

Run Vitest tests and parse results into actionable output.

video-editing

290
from notque/claude-code-toolkit

Video editing pipeline: cut footage, assemble clips via FFmpeg and Remotion.