Skip to content
Agentmart
Submit a tool

code-review

Perform a code review imitating the owner's personal review style.

Skill by kubasejdak-org

IndexedMIT
Write a review

Chalk Labs

Need help deploying code-review?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/kubasejdak-org-code-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.

We use your email only for this newsletter. Privacy

About

Perform a code review imitating the owner's personal review style. Use for reviewing C++ files, diffs, or PRs. Trigger on: "review", "code review", "review this", "check this code", "review PR".

No 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/code-review

What's inside

Skill name
code-review
Description
Perform a code review imitating the owner's personal review style. Use for reviewing C++ files, diffs, or PRs. Trigger on: "review", "code review", "review this", "check this code", "review PR".
License
MIT
Instructions
145 lines in SKILL.md · view on GitHub

Files (8)

  • SKILL.md
  • objectives.md · references/common/
  • tests.md · references/common/
  • design.md · references/cpp/
  • formatting.md · references/cpp/
  • idioms.md · references/cpp/
  • layout.md · references/cpp/
  • naming.md · references/cpp/

SKILL.md (first lines)

# Code Review Skill

Performs a structured code review using the owner's personal style rules. Reviews changed files by default (git diff),
or specific files/directories when provided.

## Argument Parsing

Parse `$ARGUMENTS` to extract (all optional):

- **aspect** — one of:
    - Groups: `style` (formatting + naming + layout), `craft` (idioms + design), `intent` (objectives + tests)
    - Individual aspects: `formatting`, `naming`, `layout`, `idioms`, `design`, `objectives`, `tests`
    - If omitted, all aspects are reviewed
- **`--group`** — one of: `severity` (default), `file`, `aspect`
- **paths** — one or more file or directory paths to review. If omitted, use `git diff` to find changed files

Examples:

- _(empty)_ → full review of git diff, grouped by severity
- `style` → formatting + naming + layout review of git diff
- `craft` → idioms + design review of git diff
- `intent` → objectives + tests review of git diff
- `formatting` → formatting-only review of git diff
- `naming src/Foo.cpp` → naming review of that file
- `src/network/ --group=file` → full review of that directory, grouped by file
- `idioms src/Bar.hpp --group=aspect` → idioms review, grouped by aspect

## Step 1: Determine Files to Review

- If paths were given: read those files directly
- Otherwise: run `git diff --name-only HEAD` (or `git diff --cached --name-only` if staged) to get changed files
- If no changed files found, ask the user which files to review

## Step 2: Detect Language

Determine language from file extensions:

- `.cpp`, `.c`, `.cc`, `.cxx`, `.hpp`, `.h`, `.hxx` → C/C++
- Other languages not yet supported. Note this to the user and skip those files

## Step 3: Load Reference Files

If the argument is a **group**, expand it to its constituent aspects:

| Group    | Aspects                    |
| -------- | -------------------------- |
| (none)   | _all aspects_              |
| `style`  | formatting, naming, layout |
| `craft`  | idioms, design             |
| `intent` | objectives, tests          |

Then load files for each aspect using the table below.

**Aspect guide** — which aspect a rule belongs to and which file it loads:

| Aspect       | Guiding question                                      | Common file     | Language file          |
| ------------ | ----------------------------------------------------- | --------------- | ---------------------- |
| `formatting` | How does the code look? (formatting, spacing, braces) | —               | `{lang}/formatting.md` |
| `naming`     | What are identifiers called?                          | —               | `{lang}/naming.md`     |
| `layout`     | Where does code live? (files, classes, namespaces)    | —               | `{lang}/layout.md`     |
| `idioms`     | Which construct or syntax is used on this line?       | —               | `{lang}/idioms.md`     |
| `design`     | How is this class or module structured?               | —               | `{lang}/design.md`     |
| `objectives` | Does this change do what it claims?                   | `objectives.md` | —                      |
| `tests`      | Is the change adequately tested?                      | `tests.md`      | —                      |

`{lang}` maps to:

| Language | Directory |
| -------- | --------- |
| C / C++  | `cpp`     |

## Step 4: Perform the Review

Read each file to review. Apply rules from the loaded reference files. For each finding:

- Identify the exact location (`file:line` or `file:line-line`)
- State what rule is violated
- Give a concrete suggestion or show the corrected form when helpful
- Assign severity:
    - **critical** — correctness bugs, UB, security issues, API contract violations
    - **high** — design issues, maintainability, deviation from project conventions
    - **low** — minor style preferences, optional polish

Focus on the diff/changed lines first, flag pre-existing issues only if they are critical or if the change interacts
with them.

## Step 5: Format Output

### `--group=severity` (default)

```markdown
## Critical

- `src/Foo.cpp:42` — [finding]
- `src/Bar.hpp:10` — [finding]

## High

- `src/Foo.cpp:17` — [finding]

## Low

- `src/Foo.hpp:3` — [finding]
```

### `--group=file`

```markdown
## src/Foo.cpp

- :42 [critical] — [finding]
- :17 [high] — [finding]

## src/Bar.hpp

- :10 [critical] — [finding]
```

### `--group=aspect`

From kubasejdak-org/dotfiles-ai, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Apr 9, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from kubasejdak-org

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get code-review running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying code-review?

CallGet help
Cite this page

code-review skill. Agent Mart. https://agentmart.dev/skills/kubasejdak-org-code-review (last updated 2026-10-24)