dsh-skill-7d-code-reviewer
Run the following command in DeepSeek Harness:
dsh plugin install 7dgroup-ai/dsh-skill-7d-code-reviewer
Paste the following prompt into your AI chat to install this plugin:
Type “install the plugin https://github.com/7dgroup-ai/dsh-skill-7d-code-reviewer” directly into any DSH conversation, and the agent will automatically execute the download and register the skill.
About this plugin
In modern development, code review is a cornerstone of quality assurance and security, yet it often suffers from inconsistency and difficulty integrating smoothly into AI-assisted chat workflows. This template-driven skill plugin bridges that gap by bringing a standardized, professional-grade review process directly into your DeepSeek Harness sessions. Designed as a zero-core-change composable bundle, it mounts seamlessly without modifying the host environment, offering a clean, safe, and instantly reusable experience every time you need a reliable secondary evaluation of your codebase.
At its core, the plugin orchestrates a structured five-step review pipeline: task acceptance and context scanning, followed by on-demand reference loading for deep line-by-line analysis. It classifies findings into critical, medium, and minor severity levels, and evaluates code across four key dimensions—quality, security, performance, and maintainability—on a 1–10 scale. Backed by an embedded knowledge base covering industry best practices and security checklists, it generates both concise text summaries and fully formatted HTML reports. Every dynamic placeholder is strictly HTML-escaped, ensuring secure and predictable output regardless of model behavior.
Whether you are catching bugs before merge requests, conducting security audits on legacy systems, evaluating refactoring candidates, or simply enforcing team coding standards, this tool adapts to your workflow effortlessly. Just invoke it via slash command or natural language within any DSH conversation, and watch as complex structural analysis, severity grading, and visual reporting happen automatically. It turns subjective code critiques into actionable, consistent, and trackable engineering feedback.
Screenshots
Use Cases
- Automated pre-merge code review and risk interception.
- Compliance checks and security vulnerability scanning for legacy systems.
- Multi-dimensional quality scoring and refactoring guidance before complex upgrades.
Best For
- Front-end and back-end developers seeking standardized collaborative workflows.
- Security engineers responsible for system stability and data protection.
- Technical leads and architects aiming to enforce unified team coding standards.
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.

