Code Review
imbenrabi/Financial-Modeling-Prep-MCP-Server
Review a PR or working diff against this repo's intent layer (the AGENTS.md hierarchy), toolception pitfalls, and core invariants.
Review pull requests in mcp-windows for concrete bugs in MCP and CLI contracts, Windows UI automation, element identity, snapshots, bounded searches, and service lifetime.
Install Code Review
$ npx skills add sbroenne/mcp-windows --skill code-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sbroenne/mcp-windows code-review --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/sbroenne/mcp-windows.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/code-review .claude/skills/code-review && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "code-review" agent skill from https://github.com/sbroenne/mcp-windows/tree/main/.github/skills/code-review into .claude/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-review", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/sbroenne/mcp-windows/tree/main/.github/skills/code-reviewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add sbroenne/mcp-windows --skill code-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sbroenne/mcp-windows code-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sbroenne/mcp-windows.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.github/skills/code-review .agents/skills/code-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "code-review" agent skill from https://github.com/sbroenne/mcp-windows/tree/main/.github/skills/code-review into .agents/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-review", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sbroenne/mcp-windows --skill code-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sbroenne/mcp-windows code-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sbroenne/mcp-windows.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.github/skills/code-review .cursor/skills/code-review && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "code-review" agent skill from https://github.com/sbroenne/mcp-windows/tree/main/.github/skills/code-review into .cursor/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-review", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/sbroenne/mcp-windows.git --path .github/skills/code-review--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add sbroenne/mcp-windows --skill code-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sbroenne/mcp-windows code-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sbroenne/mcp-windows.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.github/skills/code-review .gemini/skills/code-review && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "code-review" agent skill from https://github.com/sbroenne/mcp-windows/tree/main/.github/skills/code-review into .gemini/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-review", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install sbroenne/mcp-windows code-reviewInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add sbroenne/mcp-windows --skill code-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sbroenne/mcp-windows.git skills-src && mkdir -p .github/skills && cp -r skills-src/.github/skills/code-review .github/skills/code-review && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "code-review" agent skill from https://github.com/sbroenne/mcp-windows/tree/main/.github/skills/code-review into .github/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-review", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sbroenne/mcp-windows --skill code-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sbroenne/mcp-windows code-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sbroenne/mcp-windows.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.github/skills/code-review .opencode/skills/code-review && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "code-review" agent skill from https://github.com/sbroenne/mcp-windows/tree/main/.github/skills/code-review into .opencode/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-review", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
code-review- GitHub stars
- 105
- Token cost
- ~1.6k tokens
- SKILL.md length
- 841 words
- Files
- 1
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- MIT
At a glance
Review pull requests in mcp-windows for concrete bugs in MCP and CLI contracts, Windows UI automation, element identity, snapshots, bounded searches, and service lifetime.
- Works in 4 steps: Read the current PR head, diff, linked… → Follow repository instructions and → Trace affected callers and result… → …
- Pull request reviews and re-reviews
- SKILL.md covers Establish the intended behavior, Prioritize these failure modes, Gather evidence safely and Report actionable findings
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Code Review is an agent skill from sbroenne/mcp-windows. Review pull requests in mcp-windows for concrete bugs in MCP and CLI contracts, Windows UI automation, element identity, snapshots, bounded searches, and service lifetime. Use for pull request reviews and re-reviews, including changes to batches, tool permissions, tests, and guidance.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Pull requests, MCP servers and Code review. It works with Model Context Protocol, .NET and Windows. The repository describes itself as: Let AI agents control Windows applications. Click buttons, type text, toggle settings — all by name, not coordinates. Uses the Windows UI Automation API to find UI elements… The licence is MIT.
When your agent uses it
- Pull request reviews and re-reviews
- Including changes to batches
- Tool permissions
Example prompts
- “/code-review”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Read the current PR head, diff, linked issues, and acceptance criteria. Distinguish
- Follow repository instructions and
- Trace affected callers and result consumers, not just the edited method. Relevant
- For re-reviews, inspect existing threads and the complete review summaries, including
What it can do on your machine
Read from SKILL.md and the folder at commit a76b3ee. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Code Review loads about 1.6k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 841 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from sbroenne/mcp-windows at commit a76b3ee, republished under its MIT licence (© sbroenne). 841 words, ~1,649 tokens.
Download SKILL.mdSave it as
.claude/skills/code-review/SKILL.md (or your agent's skills folder).- name
- code-review
- description
- Review pull requests in mcp-windows for concrete bugs in MCP and CLI contracts, Windows UI automation, element identity, snapshots, bounded searches, and service lifetime. Use for pull request reviews and re-reviews, including changes to batches, tool permissions, tests, and guidance.
Review Windows MCP changes
Review for observable correctness and user impact, not preferred coding style. Do not edit product code, merge pull requests, or change repository settings during a review.
Establish the intended behavior
- Read the current PR head, diff, linked issues, and acceptance criteria. Distinguish deliberate breaking changes from accidental regressions; do not demand compatibility that the change explicitly excludes.
- Follow repository instructions and testing guidance. Use the existing implementation and tests to confirm what the public interface actually promises.
- Trace affected callers and result consumers, not just the edited method. Relevant surfaces include tool registration and schemas, raw request validation, CLI parsing and dispatch, shared automation services, batches, tool permissions, result models, recovery hints, help, and examples.
- For re-reviews, inspect existing threads and the complete review summaries, including suppressed findings. Check each against the latest code. Do not repeat a fixed finding or assume that an unresolved thread still represents a bug.
Prioritize these failure modes
| Area | What to verify |
|---|---|
| Input contracts | Omitted, null, empty, whitespace, unknown, and mode-inappropriate arguments remain distinguishable where the contract requires it. A schema alone does not prove the runtime rejects an argument. Check validation before binding erases property presence. |
| MCP/CLI parity | Both entry points reach the same operation behavior. CLI aliases, quoting, child arguments, relative paths, working directories, output, and exit codes preserve intent. Do not infer an alias is invalid without checking the parser. |
| Target identity | An ID resolves the original observed control or fails. Replacement, handle/process reuse, provider failure, owner restart, eviction, and automation-thread disposal must not redirect it through a name or position search. |
| Read and action scope | A failed explicit target must not widen into whole-window text, OCR, another table, or an unrelated dialog. Parent/proximity references and coordinate fallbacks must belong to the intended window and control. |
| Batches and permissions | Validate the entire request before side effects. Dependency checks and execution must parse steps identically. Null steps and invalid property presence are handled. Disabled tools cannot be requested through batch steps or attached snapshots. Only an unambiguous discovery result may supply a later action's reference. |
| Bounded work | Enforce limits before bulk fetching or allocating results, not afterward. Incomplete searches cannot prove absence or uniqueness. Check deadlines, final probes, cancellation, and cleanup without arbitrary timeout padding. |
| Service lifetime | Check caller isolation, pipe permissions, startup coordination, build compatibility, request/output limits, and resource ownership. Whole batches must not interleave; read-only waits must not block their triggering actions. Do not replay requests after an uncertain response. |
| Windows input and outcomes | Verify foreground ownership, focus, current coordinates/DPI, and input return values before acting. Dispatch, dialog disappearance, and an actual application outcome are different evidence. Cleanup must not close user applications or release another operation's resources. |
| Snapshots | Differences must refer to the caller's known baseline and reconstruct the current tree, including actionable IDs. Missing or outdated baselines require a full response. Do not preserve an old ID by assigning it to a replacement control. |
| Measurements and guidance | Compare actual serialized outputs using equivalent captures and metadata. Do not relabel historical benchmarks. Verify examples and recovery hints against current argument names, validation, and MCP/CLI ownership. |
MCP instances and the CLI daemon intentionally have separate runtime state. Shared implementation does not imply shared sessions. Consult the architecture guidance in the repository before proposing another service or session abstraction.
Show full SKILL.md (285 more words)Show less
Gather evidence safely
- Use available read-only GitHub context for related code, issues, and CI results. Verify that a result covers the current commit; a green older run is not evidence for new changes. If context or tools are unavailable, state that limitation.
- Consult FlaUI and pywinauto for changed Windows automation, modal-dialog, and wait behavior. Use the sister-project references in the repository instructions for cross-cutting service patterns; do not assume another project's comments prove its implementation or that Office-specific behavior applies here.
- Start with the smallest relevant existing tests when execution is available. Prefer real SDK invocation and separate CLI-process regressions for boundary bugs. Pure unit tests are useful for parsing, budgets, comparisons, and controlled clocks.
- Never connect review tooling to a live user desktop or enable desktop-input tests on a shared machine. Use dedicated Windows CI evidence for mouse/keyboard behavior. Do not run paid LLM tests or Office/browser benchmarks without explicit permission.
- Do not weaken assertions, insert tool hints into task-focused LLM prompts, blindly rerun side-effecting operations, or label a failure harmless because a retry passed.
Report actionable findings
For each finding, identify the triggering input or state, the actual versus required behavior, its user impact, and the relevant code path or regression evidence. Attach the finding to an appropriate changed line and describe a focused correction.
Report concrete issues introduced or materially worsened by the change. Follow enough surrounding code to rule out existing guards before commenting. Avoid speculative redesigns, style-only findings, duplicate symptoms of one root cause, and unrelated pre-existing problems. Do not invent findings to meet a quota.
Use plain English. Distinguish confirmed bugs, unverified risks, and unavailable validation. If no actionable issue is found, say so without implying unrun tests passed.
© sbroenne, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .github/skills/code-review of sbroenne/mcp-windows.
Open the folder on GitHubat commit a76b3ee
Compare with similar skills
Code Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Code Review this skillsbroenne/mcp-windows | 105 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Code Reviewimbenrabi/Financial-Modeling-Prep-MCP-Server | 150 | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Code Reviewoaslananka/kicad-mcp-pro | 119 | — | ~3.9k | Automated safety check: Pass | MIT | |
| Code Reviewcodewithmukesh/dotnet-claude-kit | 751 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Code Review WorkflowResgrid/Core | 229 | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| MAUI PR Performance Analysisdotnet/maui | 23k | — | ~2.4k | Automated safety check: Pass | MIT |
Similar skills
Code Review
oaslananka/kicad-mcp-pro
A skill your agent uses for GitHub Copilot pull request and code reviews in oaslananka/kicad-mcp-pro.
Code Review
codewithmukesh/dotnet-claude-kit
MCP-powered multi-dimensional code review for .NET projects.
Code Review Workflow
Resgrid/Core
Structured code review workflow for .NET projects using Roslyn MCP tools.
- Official
MAUI PR Performance Analysis
dotnet/maui
Interprets pinned managed benchmark evidence for a dotnet/maui pull request and writes a narrative for the performance review workflow, without running or publishing anything.
Review PR
PrefectHQ/fastmcp
Assess a FastMCP pull request for justified behavior, compatibility, and correctness, then follow CI and review feedback to a revision-specific verdict.
More from sbroenne/mcp-windows
Windows Automation
sbroenne/mcp-windows
Guidance for reliable, token-efficient Windows automation through MCP.
Windows CLI
sbroenne/mcp-windows
Guidance for driving Windows desktop automation from the wincli command-line tool - the token-efficient entry point that mirrors the Windows MCP server.
Related
Works with
Categories
Questions about Code Review
What does Code Review do?
Review pull requests in mcp-windows for concrete bugs in MCP and CLI contracts, Windows UI automation, element identity, snapshots, bounded searches, and service lifetime. Code Review is an agent skill from sbroenne/mcp-windows. Review pull requests in mcp-windows for concrete bugs in MCP and CLI contracts, Windows UI automation, element identity, snapshots, bounded searches, and service lifetime.
When should I use Code Review?
Code Review fits situations like: pull request reviews and re-reviews; including changes to batches; tool permissions.
How do I install Code Review in Claude Code?
Run `npx skills add sbroenne/mcp-windows --skill code-review -a claude-code`. Or copy the skill folder (.github/skills/code-review in sbroenne/mcp-windows) into .claude/skills/code-review in your project. Claude Code loads it when a task matches its description.
How do I install Code Review in Codex?
Run `npx skills add sbroenne/mcp-windows --skill code-review -a codex`. Or copy the skill folder (.github/skills/code-review in sbroenne/mcp-windows) into .agents/skills/code-review in your project. Codex loads it when a task matches its description.
Can I use Code Review in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sbroenne/mcp-windows --skill code-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-review, .gemini/skills/code-review, .github/skills/code-review and .opencode/skills/code-review in your project.
What does Code Review need to run?
SKILL.md names no scripts, command-line tools or credentials: Code Review is instructions for the agent only.
Does Code Review access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Code Review safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Code Review use?
Code Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Code Review use?
About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Code Review?
Skills that share tags, products or a category with Code Review: Code Review (imbenrabi/Financial-Modeling-Prep-MCP-Server, 150 stars), Code Review (oaslananka/kicad-mcp-pro, 119 stars), Code Review (codewithmukesh/dotnet-claude-kit, 751 stars) and Code Review Workflow (Resgrid/Core, 229 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Code Review?
sbroenne (a GitHub user) maintains it in sbroenne/mcp-windows, which has 105 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 6, 2026.
Source: sbroenne/mcp-windows on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.