Browse Skills

ctf-pwn.md

486

1 export ctf-pwn

2 from "cyberkaida/reverse-engineering-assistant"

3 Solve CTF binary exploitation challenges by discovering and exploiting memory corruption vulnerabilities to read flags. Use for buffer overflows, format strings, heap exploits, ROP challenges, or any pwn/exploitation task.

2026-01-06

ctf-crypto.md

486

1 export ctf-crypto

2 from "cyberkaida/reverse-engineering-assistant"

3 Solve CTF cryptography challenges by identifying, analyzing, and exploiting weak crypto implementations in binaries to extract keys or decrypt data. Use for custom ciphers, weak crypto, key extraction, or algorithm identification.

2026-01-06

Code Formatting.md

485

1 export Code Formatting

2 from "openshift/hypershift"

3 MANDATORY: When writing Go tests, you MUST use 'When...it should...' format for ALL test names. When writing any Go code, you MUST remind user to run 'make lint-fix' and 'make verify'. These are non-negotiable HyperShift requirements.

2026-01-05

Debug Cluster.md

485

1 export Debug Cluster

2 from "openshift/hypershift"

3 Provides systematic debugging approaches for HyperShift hosted-cluster issues. Auto-applies when debugging cluster problems, investigating stuck deletions, or troubleshooting control plane issues.

2026-01-05

Git Commit Format.md

485

1 export Git Commit Format

2 from "openshift/hypershift"

3 Apply HyperShift conventional commit formatting rules. Use when generating commit messages or creating commits.

2026-01-05

Effective Go.md

485

1 export Effective Go

2 from "openshift/hypershift"

3 Apply Go best practices, idioms, and conventions from golang.org/doc/effective_go. Use when writing, reviewing, or refactoring Go code to ensure idiomatic, clean, and efficient implementations.

2026-01-05

peft-fine-tuning.md

481

1 export peft-fine-tuning

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

2026-01-06

phoenix-observability.md

481

1 export phoenix-observability

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.

2026-01-06

model-pruning.md

481

1 export model-pruning

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.

2026-01-06

qdrant-vector-search.md

481

1 export qdrant-vector-search

2 from "zechenzhangAGI/AI-research-SKILLs"

3 High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

2026-01-06

mlflow.md

481

1 export mlflow

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform

2026-01-06

instructor.md

481

1 export instructor

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library

2026-01-06

hqq-quantization.md

481

1 export hqq-quantization

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

2026-01-06

weights-and-biases.md

481

1 export weights-and-biases

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

2026-01-06

blip-2-vision-language.md

481

1 export blip-2-vision-language

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

2026-01-06

sparse-autoencoder-training.md

481

1 export sparse-autoencoder-training

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

2026-01-06

langsmith-observability.md

481

1 export langsmith-observability

2 from "zechenzhangAGI/AI-research-SKILLs"

3 LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

2026-01-06

gguf-quantization.md

481

1 export gguf-quantization

2 from "zechenzhangAGI/AI-research-SKILLs"

3 GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

2026-01-06

pyvene-interventions.md

481

1 export pyvene-interventions

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

2026-01-06

crewai-multi-agent.md

481

1 export crewai-multi-agent

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.

2026-01-06

model-merging.md

481

1 export model-merging

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

2026-01-06

long-context.md

481

1 export long-context

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.

2026-01-06

outlines.md

481

1 export outlines

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

2026-01-06

speculative-decoding.md

481

1 export speculative-decoding

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

2026-01-06