Instructions file
Instructions for marduk191/qwen3_mcp, covering qwen3 mcp server, two server modes, http mode (browser chat), open http://localhost:3847/chat.html and mcp mode (lm studio direct).
12 6mo ago A 5,679 tokens
original MIT
Skill Claude CodeCodex
Use this skill when building, debugging, or modifying Google Chrome extensions. Triggers on: any mention of 'Chrome extension', 'browser extension', 'manifest.json', 'content script', 'background script', 'service worker' (in extension context), 'popup.html', 'chrome.tabs', 'chrome.runtime', 'chrome.storage'…
12 6mo ago A 95 tokens
original MIT
code-review
03Skill Claude CodeCodex
A skill that teaches the AI how to perform thorough code reviews.
12 6mo ago A 0 tokens
original MIT
Skill Claude CodeCodex
Use this skill when creating, modifying, or debugging ComfyUI custom nodes. Triggers on: 'ComfyUI custom node', 'ComfyUI node development', 'ComfyUI plugin', 'INPUTTYPES', 'NODECLASSMAPPINGS', 'RETURNTYPES', 'defineschema', 'io.ComfyNode', or any request to build a new node for ComfyUI. Covers both V1 (current) and V3…
12 6mo ago A 100 tokens
original MIT
Skill Claude CodeCodex
Use this skill when creating, modifying, or debugging ComfyUI image generation workflows. Triggers on: 'ComfyUI workflow', 'ComfyUI pipeline', 'txt2img', 'img2img', 'inpainting', 'ControlNet', 'KSampler', 'Flux workflow', 'SDXL workflow', 'SD3.5 workflow', 'LoRA', 'IPAdapter', or any request to build an image…
12 6mo ago A 99 tokens
original MIT
Plugin Claude Code
Security-focused differential review of code changes with git history analysis and blast radius estimation.
12 6mo ago A
tokens not measured
original MIT
Command
Performs security-focused differential review of code changes.
12 6mo ago A 16 tokens
original MIT
Skill Claude CodeCodex
Performs security-focused differential review of code changes (PRs, commits, diffs). Adapts analysis depth to codebase size, uses git history for context, calculates blast radius, checks test coverage, and generates comprehensive markdown reports. Automatically detects and prevents security regressions.
12 6mo ago A 61 tokens
copy · 94% MIT
docx
09Skill Claude CodeCodex
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
12 6mo ago A 168 tokens
copy · 86% MIT
Skill Claude CodeCodex
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
12 6mo ago A 77 tokens
copy · 100% MIT
mcp-builder
11Skill Claude CodeCodex
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
12 6mo ago A 61 tokens
copy · 100% MIT
Plugin Claude Code
Modern Python best practices. Use when creating new Python projects, and writing Python scripts, or migrating existing projects from legacy tools.
12 6mo ago A
tokens not measured
original MIT
PreToolUse
13Hook
Runs before the agent uses a tool for Bash tool calls, executing intercept-legacy-python.sh via bash. From marduk191/qwen3_mcp.
12 6mo ago A
tokens not measured
copy · 58% MIT
Skill Claude CodeCodex
Configures Python projects with modern tooling (uv, ruff, ty). Use when creating projects, writing standalone scripts, or migrating from pip/Poetry/mypy/black.
12 6mo ago A 39 tokens
original MIT
Skill Claude CodeCodex
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…
12 6mo ago A 67 tokens
copy · 78% MIT
shadcn-ui
16Skill Claude CodeCodex
Expert guidance for integrating and building applications with shadcn/ui components, including component discovery, installation, customization, and best practices.
12 6mo ago A 31 tokens
copy · 100% MIT
Plugin Claude Code
Static analysis toolkit with CodeQL, Semgrep, and SARIF parsing for security vulnerability detection.
12 6mo ago A
tokens not measured
original MIT
codeql
18Skill Claude CodeCodex
Run CodeQL static analysis for security vulnerability detection, taint tracking, and data flow analysis. Use when asked to analyze code with CodeQL, create CodeQL databases, write custom QL queries, perform security audits, or set up CodeQL in CI/CD pipelines.
12 6mo ago A 57 tokens
original MIT
Skill Claude CodeCodex
Parse, analyze, and process SARIF (Static Analysis Results Interchange Format) files. Use when reading security scan results, aggregating findings from multiple tools, deduplicating alerts, extracting specific vulnerabilities, or integrating SARIF data into CI/CD pipelines.
12 6mo ago A 56 tokens
copy · 88% MIT
semgrep
20Skill Claude CodeCodex
Run Semgrep static analysis for fast security scanning and pattern matching. Use when asked to scan code with Semgrep, write custom YAML rules, find vulnerabilities quickly, use taint mode, or set up Semgrep in CI/CD pipelines.
12 6mo ago A 50 tokens
original MIT
Plugin Claude Code
Skills from the Trail of Bits Application Security Testing Handbook (appsec.guide).
12 6mo ago A
tokens not measured
original MIT
Skill Claude CodeCodex
AddressSanitizer detects memory errors during fuzzing. Use when fuzzing C/C++ code to find buffer overflows and use-after-free bugs.
12 6mo ago A 35 tokens
copy · 95% MIT
aflpp
23Skill Claude CodeCodex
AFL++ is a fork of AFL with better fuzzing performance and advanced features. Use for multi-core fuzzing of C/C++ projects.
12 6mo ago A 33 tokens
copy · 81% MIT
atheris
24Skill Claude CodeCodex
Atheris is a coverage-guided Python fuzzer based on libFuzzer. Use for fuzzing pure Python code and Python C extensions.
12 6mo ago C 32 tokens
copy · 95% MIT