GitHub
python-json
UTF-8 JSON file I/O utilities to avoid Windows encoding issues (CP-1252 vs UTF-8)
☆ 6View skill
Research AI Skills
Discover Research skills, compare source repositories and read the instructions for each workflow.
Categories: Research
Research Clear filters
Browse skills
GitHub
boofuzz
Protocol fuzzer script development using boofuzz framework. Use when creating network protocol fuzzers, defining protocol PDUs (Protocol Data Units), writing mutation-based fuzzing scripts, or contributing to t...
☆ 6View skill
GitHub
image-files
Image manipulation using ImageMagick command-line tools for resizing, converting, optimizing, and batch processing
☆ 6View skill
GitHub
whisper-transcription
Audio transcription using local whisper.cpp server with CUDA acceleration. HTTP API for speech-to-text conversion.
☆ 6View skill
GitHub
elasticsearch
Elasticsearch 5.2 operations using HTTP API - searching, indexing, bulk operations, scroll API, and alias management
☆ 6View skill
GitHub
duckdb-extensions
Building DuckDB loadable extensions with CMake, FetchContent, and proper metadata handling
☆ 6View skill
GitHub
automated-test-fix-loop
Pattern for automated testing with GitHub issue creation and Claude Code auto-fixing. Creates Test → Fail → Issue → Fix → Repeat cycle until tests pass.
☆ 6View skill
GitHub
csharpener
C# static analysis tool for call graphs, unused code detection, impact analysis, HTML documentation generation, and Graphviz diagram export
☆ 6View skill
GitHub
creating-skills
Guide for creating Claude Code skill documents with YAML frontmatter, instructions, examples, and reference implementations
☆ 6View skill
GitHub
vram-gpu-oom
GPU VRAM management patterns for sharing memory across services (Ollama, Whisper, ComfyUI). OOM retry logic, auto-unload on idle, and service signaling protocol.
☆ 6View skill
GitHub
parquet-files
This describes how to create Parquet files in C#, including updating and multi threaded creation
☆ 6View skill
GitHub
rust
Rust development patterns, project setup, CLI/TUI applications, error handling, and system integration
☆ 6View skill
GitHub
reverse-proxy-deployment
Deploy web applications behind Apache reverse proxy on rivsprod01 with relative URLs and proper path configuration
☆ 6View skill
GitHub
blog-management
Managing Cyril's Workshop blog posts and devblog via API - creating, editing, publishing, and updating content programmatically
☆ 6View skill
GitHub
browserbridge
Real-time browser debugging and interaction via WebSocket bridge server on localhost:3141
☆ 6View skill
GitHub
qwen-ollama
Using Qwen 2.5 models via Ollama for local LLM inference, text analysis, and AI-powered automation
☆ 6View skill
GitHub
code-review-assistant
Perform comprehensive code reviews following SOLID principles and best practices
☆ 6View skill
GitHub
ui-refactor
Tactical user interface design guide for fixing layouts, selecting colors/fonts, and creating professional UIs. Use when the user asks to "make this look better," needs help with CSS/styling decisions, wants to...
☆ 6View skill
GitHub
llm-council
Multi-LLM collaborative brainstorming and planning. Use when user explicitly requests consultation with multiple AI models (ChatGPT, Gemini, other LLMs) before presenting an implementation plan, or asks to "con...
☆ 6View skill
GitHub
model-steering
Control model behavior through persistent edits and steering interventions. Use when modifying model outputs, applying steering vectors, or creating persistently modified model versions.
☆ 6View skill
GitHub
causal-tracing
Causal mediation analysis to identify which model components mediate specific behaviors. Use when investigating how information flows through the network and which neurons or layers are causally responsible for...
☆ 6View skill
GitHub
attribution-patching
Gradient-based approximation to activation patching for scalable circuit analysis. Use when activation patching is too slow or when analyzing many components simultaneously.
☆ 6View skill
GitHub
activation-patching
Causal intervention via activation patching to identify important model components. Use when determining which layers, heads, or positions are causally responsible for model behavior.
☆ 6View skill
GitHub
nnsight-basics
Core nnsight concepts for neural network interpretability. Use when setting up models, tracing activations, saving values, or making basic interventions on model internals.
☆ 6View skill
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.