Monitor a pull request until CI status or Copilot review is available. Use when: monitor PR, watch PR, land PR, wait for CI, wait for checks, wait for review, check PR status. Starts two async terminal tasks (CI + Copilot review) and reacts when either completes.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "monitor-pr" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/vscode-team-kit/main/monitor-pr/skills/monitor-pr/SKILL.md 2. Save it as ~/.claude/skills/monitor-pr/SKILL.md 3. Reload skills and tell me it's ready
Monitor a pull request by running two scripts in async terminals: one that waits for a Copilot code review, and one that waits for CI to finish. When either terminal exits, the host's async-terminal runtime notifies the agent on its next turn, so the agent can react without polling.
Host requirement: this skill assumes the agent host can run long-lived background terminals and notify the agent when they exit — for example, VS Code Chat's
run_in_terminalwithmode=asyncplusget_terminal_output/kill_terminal. Hosts without that capability will need to adapt the procedure (e.g. foreground the scripts and block on them).
gh CLI installed and authenticated.NO_PENDING_COPILOT_REVIEW — this skill only waits for Copilot reviews, it does not request them.Extract the PR number from the conversation context. Determine the repo with:
gh repo view --json nameWithOwner -q .nameWithOwner
Run BOTH of these scripts in separate async terminals (mode=async on run_in_terminal, or your host's equivalent). Use a small timeout, such as timeout=1000, so the tool returns quickly after the monitor process starts. Do NOT await them and do NOT poll or sleep; the runtime will notify you on a later turn when each script exits.
The scripts live inside this skill directory, at <skill-dir>/scripts/wait-for-ci.mts and <skill-dir>/scripts/wait-for-copilot-review.mts. Always invoke them by absolute path — derive the skill directory from the absolute path of this SKILL.md, not from the current working directory. The agent's CWD is usually the user's project repo, not this plugin.
Terminal A — wait for Copilot code review:
node <skill-dir>/scripts/wait-for-copilot-review.mts <pr-number> <owner/repo>
Terminal B — wait for CI:
node <skill-dir>/scripts/wait-for-ci.mts <pr-number> <owner/repo>
After launching both, record their terminal IDs and stop. Return control to the user with a brief status message, for example: "Monitoring PR #N — waiting for CI and Copilot review."
When you are notified that one of these terminals has exited, read its output with get_terminal_output and act on the RESULT: line. The terminal output already contains everything you need — read it carefully before taking any action.
| Script | Result | Exit | Action |
|---|---|---|---|
wait-for-copilot-review.mts | UNRESOLVED_COPILOT_REVIEW_COMMENTS | 0 | Unresolved Copilot comments existed before monitoring started. The output lists each comment (file, line, body). Follow step 4 below. |
wait-for-copilot-review.mts | NO_PENDING_COPILOT_REVIEW | 0 | No Copilot review is currently in flight and there are no unresolved Copilot comments. Report the status and move on — do not try to request a review yourself. |
wait-for-copilot-review.mts | NEW_COPILOT_REVIEW | 0 | A new Copilot review arrived after monitoring started. The output lists each new inline comment (file, line, body). Follow step 4 below. |
wait-for-copilot-review.mts | COPILOT_REVIEW_ERROR | 2 | Report the script or gh error output to the user. |
wait-for-ci.mts | CI_PASSED | 0 | CI is green. Report the status and keep waiting for the review terminal if it is still running. |
wait-for-ci.mts | CI_FAILED | 1 | Follow step 5 below. |
…
Add emoji reactions to GitHub issues or pull requests quickly.
Let AI agents read and write memory with environment-aware storage fallback.
Gather independent multi-model plans and debates for implementation and architecture decisions.
Get high-signal second opinions on plans, designs, and implementations early.
Create and manage AST ban rules to block specific code syntax patterns.
Set up Component Explorer with CLI, MCP, and VS Code tooling.