Use when coordinating PR review work as orchestrator. Defines delegation rules, verification, and completion criteria. Trigger with /start-pr-review [PR_NUMBER].
npx claudepluginhub emasoft/emasoft-plugins --plugin emasoft-integrator-agentThis skill uses the workspace's default tool permissions.
This skill defines the coordination workflow for Pull Request reviews. The approach is **coordination-only**: monitor PR status, delegate review tasks to specialized subagents, track completion, and report results.
README.mdreferences/completion-criteria.mdreferences/delegation-rules.mdreferences/human-vs-ai-assignment.mdreferences/merge-failure-recovery.mdreferences/op-classify-work.mdreferences/op-delegate-subagent.mdreferences/op-handle-failure.mdreferences/op-identify-author-type.mdreferences/op-monitor-progress.mdreferences/op-poll-prs.mdreferences/op-report-status.mdreferences/op-verify-completion.mdreferences/orchestrator-responsibilities.mdreferences/polling-schedule.mdreferences/verification-workflow.mdreferences/worktree-coordination.mdscripts/__pycache__/atlas_orchestrator_pr_poll.cpython-314.pycscripts/__pycache__/atlas_verify_pr_completion.cpython-314.pycscripts/eia_orchestrator_pr_poll.pyResponds to GitHub PR review comments for specified numbers or all open PRs using configurable agents, git worktrees for parallel execution, and status checks.
Drives existing GitHub/GitLab PRs/MRs to merge: monitors CI/CD status, fixes issues in PR scope via sub-skills, handles multi-round code reviews, resolves comments until all requirements met.
Conducts deep PR reviews using 6-7 parallel specialized agents for code quality, security, testing, frontend/backend architecture. Use for thorough pull request analysis before merging.
Share bugs, ideas, or general feedback.
This skill defines the coordination workflow for Pull Request reviews. The approach is coordination-only: monitor PR status, delegate review tasks to specialized subagents, track completion, and report results.
Core Principle: This workflow separates coordination from work. The coordinator delegates, monitors, and reports — it does not perform direct review work.
gh) installed and authenticated| Output Type | Format | Description |
|---|---|---|
| Subagent Delegation | Task spawn | Spawned subagent with PR review/fix instructions |
| Status Report | Text/JSON | Current PR status and action recommendations |
| Verification Result | JSON | Pass/fail status for all completion criteria |
| User Notification | Text | Human-readable summary of PR readiness |
| Polling Schedule | Background task | Recurring PR status checks |
eia_orchestrator_pr_poll.py to get list of open PRs and their statuseia_verify_pr_completion.py before reporting readyCopy this checklist and track your progress:
eia_orchestrator_pr_poll.pyeia_verify_pr_completion.pyFollow the decision tree below to determine the appropriate action for any PR review request.
PR Review Request Received
│
├─► Is PR from human or AI agent?
│ ├─► Human PR → Escalate to user for guidance
│ └─► AI/Bot PR → Direct delegation allowed
│
├─► What type of work is needed?
│ ├─► Code review → Delegate to review subagent
│ ├─► Code changes → Delegate to implementation subagent
│ ├─► CI verification → Delegate to CI monitor subagent
│ └─► Status check → Use polling script directly
│
├─► Should I block waiting?
│ └─► NEVER block. Always use background tasks or polling.
│
└─► Is PR ready to merge?
├─► Run completion verification script
├─► All criteria pass → Report to user, await merge decision
└─► Criteria fail → Identify gaps, delegate fixes
Reference: orchestrator-responsibilities.md
Reference: delegation-rules.md
Reference: verification-workflow.md
Reference: worktree-coordination.md
Reference: human-vs-ai-assignment.md
Reference: completion-criteria.md
Reference: polling-schedule.md
Reference: merge-failure-recovery.md
Location: scripts/eia_orchestrator_pr_poll.py
Purpose: Get all open PRs, check status, identify actions needed
When to use: On each polling interval to survey PR landscape
Output: JSON with prioritized action list
# Usage
python scripts/eia_orchestrator_pr_poll.py --repo owner/repo
# Output format
{
"prs": [
{
"number": 123,
"title": "PR Title",
"status": "needs_review|needs_changes|ready|blocked",
"priority": 1,
"action_needed": "delegate_review|delegate_fix|verify_completion|wait"
}
]
}
Location: scripts/eia_verify_pr_completion.py
Purpose: Verify all completion criteria for a specific PR
When to use: Before reporting PR ready, before merge
Output: JSON pass/fail with detailed reasons
# Usage
python scripts/eia_verify_pr_completion.py --repo owner/repo --pr 123
# Output format
{
"pr_number": 123,
"complete": true|false,
"criteria": {
"reviews_addressed": true,
"comments_acknowledged": true,
"no_new_comments": true,
"ci_passing": true,
"no_unresolved_threads": true,
"merge_eligible": true,
"not_merged": true,
"commits_pushed": true
},
"failing_criteria": [],
"recommendation": "ready_to_merge|needs_work|blocked"
}
This workflow must NEVER execute blocking operations. All long-running tasks must be:
The coordinator role is to coordinate, not to implement. Code writing is ALWAYS delegated to implementation subagents.
The coordinator may verify merge readiness but NEVER executes merge without explicit user approval.
Before reporting any status (ready, complete, blocked), always run the verification script to confirm.
PRs from human contributors require different handling. Always escalate to user for guidance on communication and decisions.
# Poll for open PRs requiring action
python scripts/eia_orchestrator_pr_poll.py --repo owner/repo
# For each PR needing review, delegate to review subagent
# (orchestrator spawns subagent with appropriate prompt)
# Verify completion before reporting
python scripts/eia_verify_pr_completion.py --repo owner/repo --pr 123
python scripts/eia_verify_pr_completion.py --repo owner/repo --pr 123
# If complete: true, report to user for merge decision
# If complete: false, identify failing_criteria and delegate fixes
Cause: Subagent may have crashed or become unresponsive Solution: Check subagent logs, re-delegate with simpler scope
Cause: GitHub API rate limiting or cache Solution: Wait briefly, then re-poll. If persistent, check API rate limits.
Cause: Race condition with GitHub webhook processing Solution: Implement quiet period check before final verification
Cause: Insufficient task isolation Solution: Use worktrees for parallel work, enforce file-level isolation
Cause: Notification not triggered Solution: Check notification triggers in polling schedule, ensure report step executes