ClawdAgent
This repository also configures its own agents. See what ClawdAgent tells them →
Skill Claude Code needs its repo
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best…
Skill Claude Code needs its repo
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.
Skill Claude Code
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
Skill Claude Code
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…
Skill Claude Code
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and…
Skill Claude Code needs its repo
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…
Skill Claude Code
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…
Skill Claude Code
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…
Skill Claude Code
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE…
Skill Claude Code
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…
Skill Claude Code
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
Skill Claude Code
Da7rkx0 represents dark web reconnaissance capabilities used during authorized threat intelligence gathering and security assessments. Understanding dark web monitoring is essential for proactive defense — identifying leaked credentials, sold data, and emerging threats before they are exploited.
Skill Claude Code
FacePlugin is a face recognition SDK used in security contexts for access control systems, identity verification auditing, and biometric security assessments. Understanding face recognition technology is critical for auditing biometric authentication systems.
Skill Claude Code
Sniffnet is a cross-platform network traffic monitoring tool designed for real-time packet analysis and security monitoring. It provides a visual interface for understanding network behavior, detecting anomalies, and identifying potential security threats.
Skill Claude Code
Big Brother V3.0 is a comprehensive OSINT (Open Source Intelligence) platform for gathering publicly available information during authorized security assessments. It consolidates multiple reconnaissance techniques into a unified framework.
Skill Claude Code
WebExtractor is a web scraping and data extraction tool used during authorized security assessments to identify exposed information on websites. It extracts emails, phone numbers, links, metadata, and other structured data from web pages.
Skill Claude Code
This skill implements the OpenClaw self-learning pattern where the agent continuously learns from interactions, records successful patterns, identifies mistakes, and evolves its own capabilities over time. The key insight: the agent doesn't just follow rules — it creates and refines its own rules based on experience.
Skill Claude Code
Instead of loading all 85+ skills at once (which wastes context), progressively disclose skills based on what the current task needs. This is the "show only what's relevant" pattern.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: