← Back to Skills Marketplace
samuelkahessay

Code Mentor

by samuelkahessay · GitHub ↗ · v1.0.2
cross-platform ⚠ suspicious
7769
Downloads
3
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install code-mentor
Description
Comprehensive AI programming tutor for all levels. Teaches programming through interactive lessons, code review, debugging guidance, algorithm practice, project mentoring, and design pattern exploration. Use when the user wants to: learn a programming language, debug code, understand algorithms, review their code, learn design patterns, practice data structures, prepare for coding interviews, understand best practices, build projects, or get help with homework. Supports Python and JavaScript.
Usage Guidance
Install only if you are comfortable with a coding tutor that may read selected code files, run local test suites, and save progress notes. Do not use the test runner on untrusted repositories or projects containing secrets unless you run it in an isolated environment, and review or delete references/user-progress/learning_log.md if you do not want session history retained.
Capability Analysis
Type: OpenClaw Skill Name: code-mentor Version: 1.0.2 The skill is classified as suspicious due to several high-risk capabilities, although without clear evidence of intentional malicious intent. The `SKILL.md` contains direct instructions to the AI agent to update `references/user-progress/learning_log.md`, which, while benign in purpose, demonstrates a form of prompt injection. More significantly, the `scripts/run_tests.py` script executes user-provided code via external test runners (`pytest`, `unittest`, `jest`), allowing for potential arbitrary code execution if a malicious user provides a crafted test file. Additionally, the `scripts/analyze_code.py` and `scripts/complexity_analyzer.py` scripts can read and process arbitrary files, which could be leveraged by a malicious agent to access sensitive local data and output its content.
Capability Assessment
Purpose & Capability
Tutoring, code review, static analysis, and test feedback fit the stated purpose, but the optional test runner invokes pytest, unittest, and Jest against user-selected targets, which can execute arbitrary project code on the host.
Instruction Scope
The skill uses broad programming-help triggers and instructs the agent to update a learning log after each session, creating side effects that are not gated by an explicit opt-in flow.
Install Mechanism
No hidden install hook or automatic setup behavior was found. Optional dependencies are documented, but requirements use lower-bound version ranges rather than pinned versions.
Credentials
Reading user-selected code files is expected for a code mentor, but direct test execution and unrestricted file-path analysis are high-impact if used on untrusted repositories or sensitive local files.
Persistence & Privilege
The README, SKILL.md, and bundled learning log disclose automatic progress persistence, but there is no clear consent, retention, minimization, disable, or deletion mechanism.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install code-mentor
  3. After installation, invoke the skill by name or use /code-mentor
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
- Updated metadata: author and version information revised, new license and compatibility sections added. - Language support now explicitly limited to Python and JavaScript. - Added a .DS_Store file (no functionality change). - No core skill logic or documentation content updated beyond metadata adjustments.
v1.0.1
Version 1.0.1 Changelog - No file changes detected in this release. - Functionality and features remain unchanged from the previous version.
v1.0.0
Initial release of Code Mentor — a comprehensive AI programming tutor for all levels. - Offers interactive lessons, code review, debugging guidance, algorithm practice, project mentoring, and design pattern exploration. - Supports 40+ programming languages including Python, JavaScript, TypeScript, Java, C++, Go, and Rust. - Adapts teaching style and content to the user's experience level and preferred learning style. - Provides eight distinct teaching modes, from concept learning to interview prep and project guidance. - Uses guided questioning (Socratic method) for debugging and code review, focusing on user learning and understanding.
Metadata
Slug code-mentor
Version 1.0.2
License
All-time Installs 0
Active Installs 0
Total Versions 3
Frequently Asked Questions

What is Code Mentor?

Comprehensive AI programming tutor for all levels. Teaches programming through interactive lessons, code review, debugging guidance, algorithm practice, project mentoring, and design pattern exploration. Use when the user wants to: learn a programming language, debug code, understand algorithms, review their code, learn design patterns, practice data structures, prepare for coding interviews, understand best practices, build projects, or get help with homework. Supports Python and JavaScript. It is an AI Agent Skill for Claude Code / OpenClaw, with 7769 downloads so far.

How do I install Code Mentor?

Run "/install code-mentor" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Code Mentor free?

Yes, Code Mentor is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Code Mentor support?

Code Mentor is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Code Mentor?

It is built and maintained by samuelkahessay (@samuelkahessay); the current version is v1.0.2.

💬 Comments