跳到正文
cccskills
免费在 GitHub 公开

issue-to-pr-resolver

Take a GitHub issue through implementation in a worktree, tests, and a draft pull request. The skill then checks CI results and review threads, applies fixes, and repeats the review cycle until the pull request is ready for maintainer review.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Implement a GitHub issue end-to-end — create a worktree branch, implement the feature with tests, create a draft PR, then iteratively resolve all CI failures and review comments until the PR is clean. Use when you need to fully implement a GitHub issue from start to merge-ready. Triggers on "implement issue", "resolve issue", "/issue-to-pr-resolver <number>".

homeassistant-ai/ha-mcp星标 5,357(GitHub 5,357 + cccskills 0)
集成工具GitHub

实测评分 未实测

查看安装方法

适用场景

  • Implementing a GitHub issue end to end
  • Creating a draft pull request from an issue
  • Resolving CI failures and review comments

包含的文件(1)

  • SKILL.md4.5 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Issue-to-PR Resolver

Implement GitHub issue #$ARGUMENTS in homeassistant-ai/ha-mcp end-to-end.

Phase 1: Setup

Read the issue:

gh issue view "$ARGUMENTS" --repo homeassistant-ai/ha-mcp --json title,body,labels,comments,author

Create a worktree from repo root:

cd "$(git rev-parse --show-toplevel)"
git checkout master && git pull origin master
git worktree add "worktree/issue-$ARGUMENTS" -b "feature/issue-$ARGUMENTS"
git -C "worktree/issue-$ARGUMENTS" submodule update --init --recursive
cd "worktree/issue-$ARGUMENTS"

Phase 2: Implement

  • Analyze codebase structure and patterns before writing code
  • Follow project conventions (see AGENTS.md for patterns, naming, error handling)
  • Write tests — all new MCP tools in src/ha_mcp/tools/ need E2E tests
  • Make atomic, well-described commits using conventional commit prefixes

Philosophy: Work autonomously. Don't ask about every small decision. Fix unrelated test failures encountered. Document all choices for the final summary.

If a non-obvious choice has significant consequences, present the available options to the user and let them choose.

Phase 3: Create PR

Write the PR body to local/pr-body-$ARGUMENTS.md first. local/ is git-ignored, so a new worktree does not have it; create it with mkdir -p local if it does not exist. Build the body from .github/pull_request_template.md: keep its headings, put Closes #$ARGUMENTS and the description under ## What does this PR do?, and delete ## Future improvements unless the user has confirmed work to defer. Then push and create the PR:

git push -u origin "feature/issue-$ARGUMENTS"
PR_NUMBER=$(gh pr create --draft \
  --repo homeassistant-ai/ha-mcp \
  --title "<descriptive title>" \
  --body-file "local/pr-body-$ARGUMENTS.md" | grep -oE '[0-9]+$')

Wait for CI:

gh pr checks "$PR_NUMBER" --repo homeassistant-ai/ha-mcp --watch

Before marking ready (gh pr ready), update the PR description to reflect all changes made.

Phase 4: Resolution Loop

Repeat until all checks green and no unresolved threads:

Check for issues:

gh pr checks "$PR_NUMBER" --repo homeassistant-ai/ha-mcp
gh api repos/homeassistant-ai/ha-mcp/pulls/"$PR_NUMBER"/comments \
  --jq '.[] | {id, path, line, author: .user.login, body}'
gh api graphql -F pr="$PR_NUMBER" -f query='query($pr: Int!) { repository(owner:"homeassistant-ai", name:"ha-mcp") { pullRequest(number:$pr) { reviewThreads(first:100) { nodes { id isResolved comments(first:1) { nodes { databaseId body } } } } } } }'

Resolve each comment (both steps required):

# 1. Reply on the inline thread
gh api repos/homeassistant-ai/ha-mcp/pulls/"$PR_NUMBER"/comments/<COMMENT_ID>/replies \
  -f body="✅ Fixed in [commit]. [explanation]"
# or: -f body="📝 Not addressing because [reason]."

# 2. Resolve the thread via GraphQL
gh api graphql -f query='mutation($threadId: ID!) { resolveReviewThread(input: {threadId: $threadId}) { thread { id isResolved } } }' \
  -f threadId="<PRRT_...>"

After pushing fixes, wait and re-check:

gh pr checks "$PR_NUMBER" --repo homeassistant-ai/ha-mcp --watch

Phase 5: Final Report

Once all checks pass and all threads resolved:

gh pr comment "$PR_NUMBER" --repo homeassistant-ai/ha-mcp --body "## Implementation Summary

**Choices Made:**
- [key technical decisions with rationale]

**Problems Encountered:**
- [issues faced and how resolved]
- [unrelated test failures fixed, if any]
"

Report to user: PR number, status, key choices.

Rules

  • Never commit to master — always work in the worktree
  • Always create PRs as draft — never mark ready without user request
  • Maximum 5 resolution iterations before reporting blockers
  • Discovered improvements: fix-in-place by default. See AGENTS.md § Boy Scout Rule — Handling Discovered Improvements for the full rubric. Never open a follow-up PR or issue without explicit user approval; never populate ## Future improvements without the user explicitly confirming the work is out of scope.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

bat-adhoc

免费

Design and run focused acceptance scenarios to check MCP tools through real agent CLIs such as Claude or Gemini. Review task completion, tool failures, and detailed run output, and compare branches when investigating a regression.

中文简介正在准备中。当前显示英语简介。

  • Validate MCP tool changes in a pull request
  • Check whether a tool regression occurs from an agent’s perspective
  • Run an end-to-end scenario with Claude or Gemini CLI
homeassistant-ai/ha-mcp53572026年10月29日 更新

Compare MCP tool behavior in a target version with a released baseline. It selects relevant prebuilt scenarios, designs custom regression stories, runs them with agent CLIs, verifies outcomes, and reports behavior, tool usage, and cost trends.

中文简介正在准备中。当前显示英语简介。

  • Compare tool behavior between a release and a code change
  • Choose test stories that exercise modified MCP tools
  • Create regression scenarios for changed code paths
homeassistant-ai/ha-mcp53572026年10月29日 更新

Review an external GitHub pull request for security concerns, test coverage, change size, and alignment with its linked issue or stated purpose. It summarizes findings and drafts a constructive review comment for you to approve before posting.

中文简介正在准备中。当前显示英语简介。

  • Review an external contribution before deciding whether it is ready to merge
  • Check whether a pull request has tests for its changed code
  • Assess whether a contributor’s changes match the linked issue
homeassistant-ai/ha-mcp53572026年10月29日 更新

Finds authors of merged pull requests who are missing from a README contributors list, drafts concise descriptions of their work, and updates the list only after the user approves the proposed additions.

中文简介正在准备中。当前显示英语简介。

  • Find recent merged PR authors missing from the contributor list
  • Draft factual one-line summaries of contributors’ changes
  • Update a README after reviewing proposed additions
homeassistant-ai/ha-mcp53572026年10月29日 更新

Analyze a GitHub issue by exploring related code, checking relevant external details, and assessing implementation complexity and architectural choices. The skill drafts a structured issue comment and recommends labels for maintainers to review.

中文简介正在准备中。当前显示英语简介。

  • Assessing the complexity of a GitHub issue
  • Planning implementation approaches
  • Preparing an issue analysis and labels
homeassistant-ai/ha-mcp53572026年10月29日 更新

Manage your own GitHub pull request by checking CI results, review comments, and unresolved threads. Triage feedback, make code fixes, reply to comments, resolve threads, and recheck until outstanding issues are cleared.

中文简介正在准备中。当前显示英语简介。

  • Check CI and review feedback on your own pull request
  • Triage bot and human comments and fix relevant issues
  • Resolve review threads after replying with an update
homeassistant-ai/ha-mcp53572026年10月29日 更新

查看 homeassistant-ai 的全部技能

报告此技能的问题