pr-automation
Best for CI/CD automation teamsWorks with GitHub
⌘source
- author
@iOfficeAI- repo
- iOfficeAI/AionUi
- language
- TypeScript
★22kstars
1.9kforks
Apr 19, 2026
✦overview.md
Key Features
- ·Poll open PRs and check CI status
- ·Run automated reviews and fixes
- ·Merge eligible PRs automatically
- ·Label-based state machine for orchestration
- ·Daemon script manages automation loop
Use Cases
- →Automating PR review and merge workflows in CI/CD pipelines
- →Processing backlog of open PRs with automated checks
- →Reducing manual intervention for trusted contributor PRs
Best for
- ✓CI/CD automation teams
- ✓Projects with frequent PRs from trusted contributors
Not ideal for
- !One-off manual PR reviews
- !Projects requiring extensive human oversight
FAQs
name
pr-automation
description
PR Automation Orchestrator: poll open PRs, check CI, run review, fix, and merge eligible PRs.
Use when: (1) Invoked by daemon via scripts/pr-automation.sh, (2) User says "/pr-automation".
PR Automation
Orchestrate the full PR automation lifecycle using a label-based state machine. Each invocation performs at most one "heavy" action (review or fix), then exits. Pure skips continue within the same session to find the next eligible PR.
Announce at start: "I'm using pr-automation skill to process PRs."
Usage
/pr-automation
No arguments required. The daemon script scripts/pr-automation.sh manages the automation loop.
Configuration
TRUSTED_CONTRIBUTORS_TEAM: detected from REPO org (e.g. iOfficeAI/trusted-contributors)
CRITICAL_PATH_PATTERN: env var, default in scripts/pr-automation.conf
LARGE_PR_FILE_THRESHOLD: env var (default: 50), also in scripts/pr-automation.conf
PR_DAYS_LOOKBACK: env var (default: 7), also in scripts/pr-automation.conf
REPO is detected automatically at runtime — do not hardcode it:
REPO=$(gh repo view --json nameWithOwner --jq '.nameWithOwner')
ORG=$(echo "$REPO" | cut -d'/' -f1)
Label State Machine
| Label | Meaning | Terminal? |
$install
1-click copynpx skills add iOfficeAI/AionUi --skill pr-automationSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
3/ 5
goodMostly clear, but there are still a few confusing or poorly structured parts.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.