Agent Skills › stella/stella › finish-pr

finish-pr

GitHub

驱动现有PR收敛至可审查或可合并状态。通过隔离环境、独立代码审查及CI验证,循环处理反馈直至达成目标。严格遵循仓库策略,仅在用户明确要求时执行合并。

.agents/skills/finish-pr/SKILL.md stella/stella

Trigger Scenarios

用户要求完成PR的审查流程 需要修复PR中的代码缺陷或CI失败 希望将PR推进至可合并状态

Install

npx skills add stella/stella --skill finish-pr -g -y
More Options

Non-standard path

npx skills add https://github.com/stella/stella/tree/main/.agents/skills/finish-pr -g -y

Use without installing

npx skills use stella/stella@finish-pr

指定 Agent (Claude Code)

npx skills add stella/stella --skill finish-pr -a claude-code -g -y

安装 repo 全部 skill

npx skills add stella/stella --all -g -y

预览 repo 内 skill

npx skills add stella/stella --list

SKILL.md

Frontmatter
{
    "name": "finish-pr",
    "description": "Drive an existing pull request to a converged review state by addressing feedback and CI repeatedly; merge only when the user explicitly requests it."
}

Finish PR

Bring an existing pull request to a current-head state that is reviewable or mergeable. This is a convergence workflow: repeat review and validation until a terminal condition is reached.

1. Establish Authority and Isolation

Resolve the PR, repository, branch, current head SHA, base branch, draft state, required checks, review state, and applicable repository instructions. Work from a clean isolated checkout of the PR head. Preserve unrelated changes.

Pin every GitHub query and mutation to the resolved full owner/name repository and PR number. Require every refreshed PR to retain that identity, and evaluate checks, reviews, replies, resolutions, and merge eligibility only for its exact current head SHA. Stop and restart the evaluation when the head changes.

Rebase or restack according to repository policy before trusting results. Review conflict resolutions and push safely. Preserve an explicit draft state unless the user asks to mark the PR ready.

Merge, deployment, and protection bypass each require explicit user authority. A request to finish review does not imply any of them.

2. Review Independently

Inspect the complete semantic diff against the correct base and fix confirmed defects. Run proportionate focused checks, then the repository's canonical CI-equivalent verification when practical. Treat generated artifacts by their canonical source and check the generated delta for drift.

3. Converge Reviews and CI

Run /rabbit-round for the current head. Push accepted fixes before replying to review threads. Then refresh reviews and required checks for the new head.

When bots or CI are still running, use the environment's monitor or wait mechanism; do not occupy the shell with sleep polling. Repeat only when new evidence arrives: a completed check, new review, new commit, or changed thread state.

Investigate failures from their logs and fix causes within scope. Do not rerun a failed job repeatedly without a reason, weaken checks, reseed baselines, dismiss valid reviews, or bypass protections merely to make the PR green.

Never request an automated review (@coderabbitai review, @codex review, or a timed re-request after a rate limit); reviews arrive on their own. Budget the loop: at most two review rounds after the first green head. When actionable findings keep arriving past that, keep the green head and triage the remaining findings yourself with a concrete accept, push-back, or defer. Open one named follow-up PR for the accepted fixes; make it stacked only when repository policy or the existing branch stack requires that. Then reply to each deferred finding with that PR's URL, and resolve the thread where the finding has one: the named follow-up is the disposition, not a promise. A deferred top-level comment stays open; the reply is its terminal state.

The budget never defers a release-blocking defect. A finding that names a security, authorization, data-loss, or data-corruption defect, and survives verification, is fixed on this head however late it arrives: shipping a known defect to keep a round count is the outcome the budget exists to avoid.

4. Stop at a Real Terminal State

The latest pushed head has converged only when:

  • required CI is green
  • automated reviewers are terminal, not pending
  • no actionable automated finding remains in a review thread or a top-level comment: each is implemented, already addressed, pushed back with evidence, or deferred to a named follow-up PR, and no verified release-blocking defect was deferred
  • no unresolved human request for changes remains
  • no blocking review or merge conflict remains

If convergence requires a user decision, new authority, unavailable credentials, or an external state change, report the exact blocker and the evidence already collected.

Merge only when explicitly requested. Use the repository's documented merge entry point (a merge script or queue) when one exists; a raw merge command bypasses its assertions. Never use admin authority to bypass a correctness failure. After any authorized merge, verify the PR state and report the resulting commit.

Report the PR URL, latest head, review and CI state, changes made, validation run, and whether the terminal state is ready, merged, or blocked.

Version History

  • e41bf51 Current 2026-09-22 09:02
  • 7b52e43 2026-09-09 03:27

    新增安全/数据缺陷不可延期的强约束;优化了Bot发现的处理逻辑与顶层评论的状态终结机制。

  • dd81665 2026-08-16 07:08

Same Skill Collection

.agents/skills/click-around/SKILL.md
.agents/skills/conventions-ai/SKILL.md
.agents/skills/conventions-db/SKILL.md
.agents/skills/conventions-i18n/SKILL.md
.agents/skills/conventions-ingestion/SKILL.md
.agents/skills/conventions-mcp/SKILL.md
.agents/skills/conventions-perf/SKILL.md
.agents/skills/conventions-scale/SKILL.md
.agents/skills/conventions-security/SKILL.md
.agents/skills/conventions-use-effect/SKILL.md
.agents/skills/conventions-ux/SKILL.md
.agents/skills/dev/SKILL.md
.agents/skills/new-handler/SKILL.md
.agents/skills/open-pr/SKILL.md
.agents/skills/plan/SKILL.md
.agents/skills/product-deep-think/SKILL.md
.agents/skills/product-think/SKILL.md
.agents/skills/rabbit-round/SKILL.md
.agents/skills/regression-hunt/SKILL.md
.agents/skills/security-audit/SKILL.md
.agents/skills/update-deps/SKILL.md
.ai/local-skills/click-around/SKILL.md
.ai/local-skills/conventions-ai/SKILL.md
.ai/local-skills/conventions-db/SKILL.md
.ai/local-skills/conventions-i18n/SKILL.md
.ai/local-skills/conventions-ingestion/SKILL.md
.ai/local-skills/conventions-mcp/SKILL.md
.ai/local-skills/conventions-perf/SKILL.md
.ai/local-skills/conventions-scale/SKILL.md
.ai/local-skills/conventions-security/SKILL.md
.ai/local-skills/conventions-use-effect/SKILL.md
.ai/local-skills/conventions-ux/SKILL.md
.ai/local-skills/dev/SKILL.md
.ai/local-skills/new-handler/SKILL.md
.ai/local-skills/open-pr/SKILL.md
.ai/local-skills/plan/SKILL.md
.ai/local-skills/product-deep-think/SKILL.md
.ai/local-skills/rabbit-round/SKILL.md
.ai/local-skills/security-audit/SKILL.md
.ai/local-skills/update-deps/SKILL.md
.claude/skills/conventions-ai/SKILL.md
.claude/skills/conventions-db/SKILL.md
.claude/skills/conventions-i18n/SKILL.md
.claude/skills/conventions-ingestion/SKILL.md
.claude/skills/conventions-mcp/SKILL.md
.claude/skills/conventions-perf/SKILL.md
.claude/skills/conventions-scale/SKILL.md
.claude/skills/conventions-security/SKILL.md
.claude/skills/conventions-use-effect/SKILL.md

Metadata

Files
0
Version
e41bf51
Hash
74cb841f
Indexed
2026-08-16 07:08

inicio - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-09-27 06:57
浙ICP备14020137号-1