An AI-powered specialized code reviewer for Q/kdb+ designed to catch performance bottlenecks, type errors, and security vulnerabilities in high-frequency trading codebases.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install q-kdb-code-review
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install q-kdb-code-review using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is q-kdb-code-review?
q-kdb-code-review is a technical analysis tool within the Openclaw Skills registry built specifically for the unique and terse syntax of the Q programming language. Developed for quantitative developers and kdb+ administrators, it provides a deep understanding of Q idioms that general-purpose AI models often overlook. By analyzing scripts for common pitfalls like inefficient joins or missing attributes, it ensures that trading infrastructure remains both fast and reliable.
This skill bridges the gap between the extreme density of Q code and modern development standards. As an essential part of the Openclaw Skills collection, it uses intelligent routing to send complex algorithmic logic to high-tier LLMs while handling standard table operations with faster, cost-effective models. This ensures developers get the highest quality feedback without unnecessary overhead.
q-kdb-code-review Use Cases
- Detecting missing
s#org#attributes that cause O(n) performance degradation in asof joins. - Identifying type errors and implicit casts that lead to silent data corruption in financial calculations.
- Auditing Q scripts for security vulnerabilities like unprotected IPC handlers and unescaped signals.
- Optimizing legacy kdb+ code by replacing iterative each-loops with high-performance vector operations.
How q-kdb-code-review Works
- The developer triggers the review by running the
/review-qcommand on a local script or directory. - The skill extracts the code and identifies the relevant context, such as schema definitions or timer callbacks.
- Using the Openclaw Skills framework, the request is routed through Astrai to the most capable AI model for the specific code complexity.
- The AI analyzes the code against a specialized knowledge base of kdb+ performance patterns and finance-domain best practices.
- A structured report is generated, categorizing findings into critical bugs, performance warnings, and style suggestions with actionable code fixes.
q-kdb-code-review Setup
To integrate this skill from the Openclaw Skills library into your workflow, follow these steps:
- Sign up for an API key at as-trai.com.
- Set your environment variable in your terminal:
export ASTRAI_API_KEY="your_key_here"
- (Optional) For Bring Your Own Key (BYOK) support, add your preferred provider keys:
export ANTHROPIC_API_KEY="sk-ant-..."
export OPENAI_API_KEY="sk-..."
- Start reviewing your Q files immediately:
/review-q --file tick.q --strict
q-kdb-code-review Data Schema & Taxonomy
The skill organizes its analysis and configuration using a structured metadata approach:
| Component | Type | Description |
|---|---|---|
| Source Code | Input | Local .q or .k files read via the CLI. |
| Strictness Level | Parameter | Defines the depth of analysis (standard, strict, or security). |
| Review Output | Markdown | A formatted report mapping issues to specific line numbers in the source. |
| Provider Keys | Env Var | Secured API keys for various LLM providers used in the Openclaw Skills ecosystem. |
| Model Selection | Metadata | Information on which AI model was routed for the specific code block. |
q-kdb-code-review Advanced Features
- Intelligent Routing: Automatically directs complex CEP logic to powerful models while using faster models for basic schema scripts.
- Security Auditing Focus: Specialized mode to detect Q injection, unprotected .z.pw, and exposed ports.
- Vectorization Suggestions: High-level analysis that identifies opportunities to replace loops with 100x faster vector operations.
- Multi-Provider Support: Seamlessly switch between Anthropic, OpenAI, DeepSeek, and other providers within the Openclaw Skills infrastructure.
SKILL.md
Loading
Related Openclaw Skills
Astrai Code Review
An intelligent AI code review agent that optimizes costs by routing diffs to the most efficient model based on complexity.
ClawPressor
ClawPressor is an intelligent session context compressor that uses NLP summarization to reduce token usage and extend session lifetime.
GoldenSeed
GoldenSeed provides deterministic entropy streams from fixed seeds, ensuring perfectly reproducible randomness for testing and procedural generation.
SnapOG
SnapOG is a high-performance API for generating professional social media images, OG cards, and marketing visuals from customizable templates.
Vynn Backtester
A natural language quantitative backtesting engine for trading strategy validation and financial analysis.
Vestige Memory Skill
A sophisticated local cognitive memory system that utilizes FSRS-6 spaced repetition to provide AI agents with persistent, human-like recall capabilities.
Featured*
