How do I install the Code Review skill?

Run npx skillmds@latest add tomevault-io/code-review-294 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Code Review safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Code Review?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Code Review free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Code Review?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Code Review by tomevault-io — Agent Skill

Name: Code Review
Author: tomevault-io

Code Review

Run the quality-triage code-review agent (ML smells, Python smells, technical-debt classification, AST code intelligence) on a path or GitHub URL. Use when the user asks for a code review, quality audit, smell detection, complexity hotspots, or technical-debt analysis of Python code. Use when this capability is needed.

tomevault-io Updated Sep 17, 2026

File contents

code-review skill

This skill drives the code-review CLI / code-review-mcp MCP server from the quality-triage project. The canonical contract is skills.md at the repo root.

When to use

"Review this project / file", "find code smells", "find ML anti-patterns", "what's the technical debt here", "show complexity hotspots".

Setup (once)

uv sync                 # core
uv sync --extra mcp     # if using the MCP server

Preferred: MCP tools

If the code-review MCP server is connected, call its tools directly: detect_python_smells, detect_ml_smells, analyze_code_intelligence, classify_technical_debt, list_python_files, read_file.

CLI fallback

code-review review <path-or-github-url> --output reports/review.md
code-review run-tool python-smells <path> --type all --format json
code-review run-tool ml-smells <path> --format json
code-review run-tool code-intel <path> --format json
code-review run-tool classify-td --text "TODO: ..." --category security
code-review doctor        # verify environment / backends
code-review providers     # show configured LLM providers

Output contract

Executive summary
Critical issues first, with file:line:col
ML-specific issues
Code quality & architecture issues
Technical debt categories
now/next/later remediation plan

Never invent commands, files, or tool names. Prefer the smallest command that answers the question; escalate to a full review only when needed.

Source: KarthikShivasankar/quality-triage — distributed by TomeVault.

---name: code-review-294description: Run the quality-triage code-review agent (ML smells, Python smells, technical-debt classification, AST code intelligence) on a path or GitHub URL. Use when the user asks for a code review, quality audit, smell detection, complexity hotspots, or technical-debt analysis of Python code. Use when this capability is needed.---# code-review skillThis skill drives the `code-review` CLI / `code-review-mcp` MCP server from the`quality-triage` project. The canonical contract is `skills.md` at the repo root.## When to use- "Review this project / file", "find code smells", "find ML anti-patterns", "what's the technical debt here", "show complexity hotspots".## Setup (once)```bashuv sync # coreuv sync --extra mcp # if using the MCP server```## Preferred: MCP toolsIf the `code-review` MCP server is connected, call its tools directly:`detect_python_smells`, `detect_ml_smells`, `analyze_code_intelligence`,`classify_technical_debt`, `list_python_files`, `read_file`.## CLI fallback```bashcode-review review <path-or-github-url> --output reports/review.mdcode-review run-tool python-smells <path> --type all --format jsoncode-review run-tool ml-smells <path> --format jsoncode-review run-tool code-intel <path> --format jsoncode-review run-tool classify-td --text "TODO: ..." --category securitycode-review doctor # verify environment / backendscode-review providers # show configured LLM providers```## Output contract1. Executive summary2. Critical issues first, with `file:line:col`3. ML-specific issues4. Code quality & architecture issues5. Technical debt categories6. now/next/later remediation planNever invent commands, files, or tool names. Prefer the smallest command thatanswers the question; escalate to a full `review` only when needed.---> Source: [KarthikShivasankar/quality-triage](https://github.com/KarthikShivasankar/quality-triage) — distributed by [TomeVault](https://tomevault.io).

Frequently asked questions