AGENT SKILL

ds-watch-pr

Watches a pull request through CI and review, fixes real findings and stops when it is ready, merged or blocked. Use when the user asks to watch, monitor or babysit a PR, or /ds-watch-pr.

License 许可
MIT
最近更新
2026-11-15
Stars
★ 0
Forks
0

01 前言 Front Matter

name
ds-watch-pr
description
Watches a pull request through CI and review, fixes real findings and stops when it is ready, merged or blocked. Use when the user asks to watch, monitor or babysit a PR, or /ds-watch-pr.

02 资源文件 1

03 SKILL.md 正文

Keep one PR moving until it is green and reviewed, with as little noise as possible.

The watcher is scripts/watch_pr.py in this skill's folder. Call it by absolute path. It needs python3 and a logged-in gh.

python3 <skill>/scripts/watch_pr.py <pr> [--repo owner/name] [--until ready|green|any] [--interval 30] [--max-minutes 60]

It prints one line per new check failure, finished check run, comment or review, then a final stop: line. Exit 0 means the condition is met or the PR merged. Exit 1 means you must act. Exit 2 means bad input. ready waits for green checks, a mergeable branch and no change request. green waits for checks only.

Steps

  1. Handle what already exists: failed checks and comments newer than the last push.
  2. Start the watcher. Run it in the harness's background or monitor tool if it has one, so each line wakes you. Otherwise run it as one long foreground command.
  3. On each event, read the source before you change code. Decide if the finding is real.
  4. For a real bug or CI failure: make the smallest fix, run the failing check locally, push, then restart the watcher.
  5. For a false positive or out-of-scope request: reply with a short reason through ds-pr-comments, resolve the thread and list it as a follow-up.
  6. Tell real test failures apart from infrastructure flakes. Re-run a flake once before you call it a flake.
  7. If the base branch moved or the branch is behind, rebase, push with --force-with-lease and restart.
  8. Before you call the PR ready, git fetch and read the PR again. It must not be BEHIND or DIRTY.

Stop when

  • The watcher exits 0. Report the PR as ready, or merged.
  • Five fix-and-push cycles pass without exit 0. Report what still fails.
  • Another PR makes this one obsolete. Stop and ask before closing it.
  • gh reports a rate limit. Check gh api rate_limit and wait for the reset once. Do not loop.

Rules

  • One watcher per PR. Never write your own sleep or polling loop.
  • When an event needs no action, say nothing. No "still waiting" messages.
  • Merge only if the user asked for it. Otherwise report ready.
  • Keep the PR small. Prefer fixes that delete or narrow code.

Greeneek working contract

This skill is installed in the Greeneek repository. Where a step below conflicts with these rules, these rules win.

  • Restate the goal in one line, read the real files before editing, and work on main in small vertical slices. Preserve uncommitted and concurrent work; never reset, force-push, or overwrite another session's changes.
  • Evidence before "done": run the real check and record the exact command and its output. Never weaken a test, add a blind retry, raise a timeout without a diagnosed cause, or delete a failing assertion to get green.
  • Agent waves never commit, push, tag, or publish. No npm auto-publish on main; release tags are immutable and Item 8 stays last.
  • Live model lanes stay BLOCKED without GREENEEK_API_KEY; mocked coverage is never reported as real-CLI verification.
  • Registrations are effects, ESM everywhere, and misconfiguration fails at the earliest resolvable point.
  • Source of truth: .agents/notes/proposed/process/2026-11-01-v0.3.9-master-release-plan.md. Append evidence to its Execution ledger and keep its Resume State current in the same commit as the change.

Greeneek-specific override

This skill needs a PR number and a logged-in gh. When either is missing, report the exact missing input and do not claim CI status. Read runner verdicts with gh run view --job <id> --log-failed; a green local run is not a green workflow, and S0-03 requires the whole workflow green twice on one SHA.

04 同仓库更多 Skills