---
name: my-pr-checker
description: Manage your own GitHub pull requests — check CI status, inline review comments, PR-level comments, resolve review threads, fix issues, and iterate until all checks pass and threads are resolved. Use for managing your own PRs (not external contributions). Triggers on "check my PR", "check PR", "/my-pr-checker <number>".
argument-hint: "<pr-number>"
allowed-tools: Bash, Read, Edit, Write, Glob, Grep, WebFetch, WebSearch
title: my-pr-checker
canonical_url: https://skilld.dev/gh/homeassistant-ai/ha-mcp/my-pr-checker
last_updated: 2026-11-12T06:30:57.000Z
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

> **Skill from skilld.dev.** Follow the user's requested action.
> If the user asked to fork this Skill, follow the fork workflow below. Do not execute the Skill instructions while copying it.
> Otherwise, follow the instructions below for this session. You do not need to install anything.
>
> If the user asked to install this Skill, run `npx skilld install homeassistant-ai/ha-mcp/my-pr-checker`. Install writes the Skill files into the project, so every session loads them.
>
> ## Fork workflow
>
> A fork creates an editable local Skill with its original author and licence. The request authorizes copying and local installation.
> 1. Check `./skills/my-pr-checker`, the project lockfile, and selected Agent targets together. If the local directory or installed Skill exists, stop. Never overwrite an existing directory or Agent target.
> 2. Read [source metadata](https://skilld.dev/api/v1/skills/homeassistant-ai/ha-mcp/my-pr-checker) once. Use sourceUrl, sourceCommit, skillPath, sourceGone, and license. If the source is gone or its path is missing, stop. If license is null, read licence files at the source commit.
> 3. Fetch only the source commit into a temporary Git repository. Do not clone full history. Derive repository_url from sourceUrl, including repository renames. If sourceCommit is absent, resolve the sourceUrl ref once. Set source_commit to that actual commit. Run these commands in one shell call:
>
> ```sh
> git init --quiet "$temporary_dir"
> git -C "$temporary_dir" fetch --quiet --depth=1 "$repository_url" "$source_commit"
> git -C "$temporary_dir" checkout --quiet --detach FETCH_HEAD
> ```
>
> Read applicable licence declarations and notices at that commit. If copying is not permitted, report the restriction and stop.
> 4. Inspect source entries together, then copy the directory containing skillPath into `./skills/my-pr-checker`. Use the user's path if selected. Keep the original SKILL.md, relative links, scripts, binary assets, and executable modes. Exclude .git metadata. Reject symlinks and paths outside the Skill directory. After checking entries, use cp -a where available. A regular source directory needs no custom copy script. Do not save this page wrapper as SKILL.md.
> Preserve author credit, notices, and applicable licence files from repository or parent directories. Add PROVENANCE.md with the Skill page, source URL, actual commit, original path, and licence. Retain any existing PROVENANCE.md and record new provenance separately. Batch source inspection, copying, and provenance work where practical.
> 5. In the project root, run `skilld install ./skills/my-pr-checker --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/my-pr-checker --mode copy --plain`. This known command needs no help lookup. Install does not support --json. Use detected Agent targets, or add --agent for the targets the user selected. Install the local path, never the upstream selector. If installation fails, preserve the local copy and report the exact failure.
> 6. Confirm the local lockfile source and installed Agent copies once. Report the local path, actual commit, and Agent targets. After edits, reinstall the same local path. Upstream updates must not replace it. Do not publish or push unless the user asks.

# My PR Checker

Review and resolve all outstanding issues on PR #$ARGUMENTS in `homeassistant-ai/ha-mcp`.

## Step 1: Full PR Assessment

```bash
# PR overview
gh pr view "$ARGUMENTS" --repo homeassistant-ai/ha-mcp \
  --json title,body,state,reviews,statusCheckRollup,headRefName,additions,deletions,changedFiles

# CI checks
gh pr checks "$ARGUMENTS" --repo homeassistant-ai/ha-mcp

# Inline review comments
gh api repos/homeassistant-ai/ha-mcp/pulls/"$ARGUMENTS"/comments \
  --jq '.[] | {id, path, line, author: .user.login, body}'

# PR-level comments
gh api repos/homeassistant-ai/ha-mcp/issues/"$ARGUMENTS"/comments \
  --jq '.[] | {id, author: .user.login, body}'

# Unresolved review threads
gh api graphql -F pr="$ARGUMENTS" -f query='query($pr: Int!) { repository(owner:"homeassistant-ai", name:"ha-mcp") { pullRequest(number:$pr) { reviewThreads(first:100) { nodes { id isResolved path line comments(first:1) { nodes { databaseId body author { login } } } } } } } }'
```

## Step 2: Triage Comments

- **Human comments**: highest priority
- **Bot comments** (Copilot, Codex, CodeRabbit, etc.): treat as suggestions — assess whether they prevent a bug or improve maintainability; dismiss with explanation if not

Accept if: prevents a bug, improves clarity for future maintainers, aligns with project conventions, addresses security.
Dismiss if: incorrect suggestion, reduces readability, conflicts with project patterns, already handled elsewhere.

## Step 3: Fix Code Issues

```bash
gh pr checkout "$ARGUMENTS" --repo homeassistant-ai/ha-mcp
# make changes
git add <files>
git commit -m "fix: address review feedback - [description]"
git push
```

Fix unrelated test failures encountered (document in final summary).

After each push, if the scope changed, update the PR description:
```bash
gh pr edit "$ARGUMENTS" --repo homeassistant-ai/ha-mcp --body "..."
```

## Step 4: Resolve Each Thread (both steps required)

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

# 1b. PR-level summary comment (when there are multiple inline threads)
gh pr review "$ARGUMENTS" --repo homeassistant-ai/ha-mcp \
  --comment --body "✅ Addressed review feedback in [commit]. [summary]"

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

**Why:** Unresolved threads block merging even after approval.

## Step 5: Wait and Re-check

```bash
gh pr checks "$ARGUMENTS" --repo homeassistant-ai/ha-mcp --watch
```

Repeat Steps 1–5 until:
- All CI checks green ✅
- All review threads resolved ✅
- No new blocking comments ✅

## Step 6: Final Report

If improvements were identified during review, **default to fix-in-place** per AGENTS.md § *Boy Scout Rule — Handling Discovered Improvements*. Only add to the PR description's `## Future improvements` section if the user has explicitly confirmed the work is out of scope. Never self-bucket findings there.

Post a summary comment:
```bash
gh pr comment "$ARGUMENTS" --repo homeassistant-ai/ha-mcp --body "## PR Assessment Summary

✅ **Status**: Ready for review/merge

**Choices Made:**
- [key decisions when resolving issues]

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

## Special Operations

Use these when needed. Re-creating the PR (which closes it) and deleting a comment each need the user's approval for that exact action first:
- **Rebase**: `gh pr checkout "$ARGUMENTS" && git rebase master && git push --force-with-lease`
- **Re-create PR**: `gh pr close "$ARGUMENTS" --repo homeassistant-ai/ha-mcp` then `gh pr create --draft …` with the same branch
- **Delete comment**: `gh api -X DELETE repos/homeassistant-ai/ha-mcp/issues/comments/<id>`
- **Update title**: `gh pr edit "$ARGUMENTS" --repo homeassistant-ai/ha-mcp --title "new title"`

## Rules

- **NEVER merge automatically** unless explicitly asked
- **Be conservative** dismissing feedback — when in doubt, ask the user
- If CI keeps failing on the same issue after 3 attempts, report the blocker rather than looping
