copilot-pr-review
Full GitHub Copilot PR review feedback loop — add Copilot as reviewer, poll for review, respond to comments, resolve threads, re-request review, and repeat…
Skill by mthalman
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mthalman-copilot-pr-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/copilot-pr-review
What's inside
- Skill name
copilot-pr-review- Description
- Full GitHub Copilot PR review feedback loop — add Copilot as reviewer, poll for review, respond to comments, resolve threads, re-request review, and repeat until clean. Use when the user asks to 'run Copilot review', 'get Copilot feedback', 'request Copilot PR review', or when a PR needs automated code review from the Copilot reviewer bot.
- License
- MIT
- Instructions
- 116 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- api-commands.md · references/
- reliability.md · references/
SKILL.md (first lines)
# Copilot PR Review Run the full GitHub Copilot code reviewer feedback loop on an open pull request: add Copilot as reviewer, poll for its review, respond to each comment, resolve threads, re-request review, and repeat until clean. **Bot identity:** `copilot-pull-request-reviewer[bot]` > **WARNING:** The bot login is NOT `Copilot`, NOT `copilot[bot]`, NOT > `github-copilot`. It is exactly > `copilot-pull-request-reviewer[bot]`. Using the wrong name silently fails or > returns "not found". ## Prerequisites - `gh` CLI installed and authenticated. - An open pull request. - The authenticated user has write access to the repository. - A clean working tree, or an explicit decision to manage existing local changes before applying review fixes. ## Context detection 1. Infer `owner/repo` from `git remote get-url origin`. 2. Infer the PR number from the current branch with `gh pr view --json number --jq .number`. 3. If either cannot be inferred, ask for it instead of guessing. ## Six-step loop ### Step 1: add Copilot as reviewer Use the GitHub API directly. `gh pr edit --add-reviewer` does not work for bot accounts. Open `references/api-commands.md` when you need the exact `gh api` command to request Copilot, verify requested reviewers, fetch comments, reply, resolve threads, or re-request review. ### Step 1.5: establish review baseline Before requesting or re-requesting review, count existing reviews from `copilot-pull-request-reviewer[bot]` and store `BASELINE_COUNT`. Step 2 must look for a **new** review where the count exceeds that baseline, not merely any old Copilot review. ### Step 2: poll for Copilot's review Poll until a new review from `copilot-pull-request-reviewer[bot]` appears. Default cadence is 60 seconds for up to 15 minutes unless project context requires a different timeout. If polling is unreliable, use the commands and checks in the reliability reference. Open `references/reliability.md` when polling, merge conflicts, unresolved threads, context budget, or pre-rerequest verification need deeper handling. ### Step 3: fetch review comments Fetch line-level comments for the new review. If the review body says Copilot generated no comments, the PR is clean. If it generated comments, process every comment before Step 5. ### Step 4: respond to each comment For each comment: 1. Read and understand the comment. 2. Make the fix on the PR branch. 3. Create **one commit per comment**. 4. Push the commit. 5. Reply to the comment with the fixing commit SHA. 6. Resolve the review thread. > **PowerShell warning:** Do not use `-f "body=@$tempFile"`; PowerShell posts > the literal file path. Store the reply in a variable and pass > `-f "body=$bodyVar"` directly. ### Gate before Step 5 You MUST complete Steps 3-4 for **all** comments before re-requesting review. Do not re-request until every comment has been read, fixed, committed, pushed, replied to, and resolved. Skipping this gate prevents the loop from converging. ### Step 5: re-request Copilot review After all comments are processed and threads are resolved, refresh `BASELINE_COUNT`, then request Copilot again through the API. ### Step 6: repeat until clean Return to Step 2. Poll for a review newer than the refreshed baseline. If it has no comments, the loop is complete. If it has comments, repeat Steps 3-5. ## Anti-patterns - **NEVER use `gh pr edit --add-reviewer`** for bot accounts. - **NEVER filter by `.user.login=="Copilot"`**; use `copilot-pull-request-reviewer[bot]`. - **NEVER batch multiple comment fixes into one commit**. - **NEVER skip replies or thread resolution** after fixing a comment. - **NEVER re-request review while current comments remain unprocessed**. - **NEVER use `gh api ... -f 'reviewers[]=Copilot'`**; it can appear to succeed while doing nothing. ## Output contract Report: - repository and PR number; - baseline counts for each review round; - every Copilot comment processed, with fix commit SHA and thread resolution status; - verification run before re-requesting or completing; - final Copilot review state: clean, issues remaining, or blocked with evidence.
From mthalman/agents, MIT.
More from mthalman/agents
- 0.592score
dispatching-parallel-agents
mthalman
Use when facing 2+ substantial tasks that can run without shared state or sequential dependencies, or when a high-value uncertain task justifies an explicitly…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
claude-extension-type-identifier
mthalman
Use when determining what type of Claude Code extension (command, skill, or agent) a prompt or description should be classified as.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
logo-design
mthalman
Use when designing logos, creating brand marks, or helping with visual identity work - provides expert logo design process including discovery, strategic…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
manual-worktree-session
mthalman
Create a Git worktree manually and attach an in-place Copilot child session when large repositories such as the dotnet VMR exceed native session/worktree…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
azure-pipeline-monitor
mthalman
Monitor an Azure DevOps (ADO) pipeline run to completion — the whole run or a single stage/job — using a blocking poller that estimates expected duration from…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
markdown-toolkit
mthalman
Use when generating or validating GitHub Flavored Markdown structure and mechanics, including headings, links, tables, lists, code fences, anchors, templates…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
code-refactorer
mthalman
Expert code refactoring that strictly preserves existing behavior.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
code-reviewer
mthalman
Review code changes for correctness, performance, safety, and quality when the user explicitly asks for a code review.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
defend-the-diff
mthalman
Interrogate an existing code change through focused questions, evidence-backed answers, and independent judgment so the change is explainable, correct…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
designing-ui-color
mthalman
Use when selecting colors for interfaces, evaluating color combinations, creating palettes, resolving stakeholder color conflicts, or when colors "feel wrong"…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
designing-ui-typography
mthalman
Use when designing typography for web/app interfaces, selecting fonts, setting up type scales, addressing performance/accessibility concerns, or handling…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
blast-radius
mthalman
Analyze what a proposed or completed code change could break outside the visible diff, identify the small set of safety assumptions the change depends on, and…
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 26
- Last commit (this folder)
- Oct 6, 2026 (22 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mthalman/agents
- Website
- mthalman.github.io/agents/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mthalman
- 0.592score
claude-extension-type-identifier
mthalman
Use when determining what type of Claude Code extension (command, skill, or agent) a prompt or description should be classified as.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
code-refactorer
mthalman
Expert code refactoring that strictly preserves existing behavior.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
manual-worktree-session
mthalman
Create a Git worktree manually and attach an in-place Copilot child session when large repositories such as the dotnet VMR exceed native session/worktree…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
azure-pipeline-monitor
mthalman
Monitor an Azure DevOps (ADO) pipeline run to completion — the whole run or a single stage/job — using a blocking poller that estimates expected duration from…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
logo-design
mthalman
Use when designing logos, creating brand marks, or helping with visual identity work - provides expert logo design process including discovery, strategic…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
code-reviewer
mthalman
Review code changes for correctness, performance, safety, and quality when the user explicitly asks for a code review.
SkillAFreshness: A★ 1Claude Code +9
Cite this page
copilot-pr-review skill. Agent Mart. https://agentmart.dev/skills/mthalman-copilot-pr-review (last updated 2026-10-24)