Agent skill
github-notification-triage
Triage GitHub notifications and report actions needed.
Install this agent skill to your Project
npx add-skill https://github.com/notque/claude-code-toolkit/tree/main/skills/github-notification-triage
SKILL.md
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
# 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:
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)
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:
python3 scripts/github-notification-triage.py --mark-read --save
Exit Codes
| Code | Meaning |
|---|---|
| 0 | Success |
| 1 | Error (auth failure, API error, script not found) |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
voice-writer
Unified voice content generation pipeline with mandatory validation and joy-check. 9-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".
image-auditor
Non-destructive image validation for accessibility and health.
video-editing
Video editing pipeline: cut footage, assemble clips via FFmpeg and Remotion.
comment-quality
Review and fix temporal references in code comments.
e2e-testing
Playwright-based end-to-end testing workflow.
anti-ai-editor
Remove AI-sounding patterns from content.
Didn't find tool you were looking for?