Browse Skills

collaborating-with-claude.md

63

1 export collaborating-with-claude

2 from "renocrypt/latex-arxiv-SKILL"

3 Use the Claude Code CLI to consult Claude and delegate coding tasks for prototyping, debugging, and code review. Supports multi-turn sessions via SESSION_ID. Optimized for low-token, file/line-based handoff.

2026-01-15

memory-processor.md

62

1 export memory-processor

2 from "severity1/claude-code-auto-memory"

3 Process file changes and update CLAUDE.md memory sections. Use when the memory-updater agent needs to analyze dirty files, update AUTO-MANAGED sections, verify content removal, or detect stale commands. Invoked after file edits to keep project memory in sync.

2026-01-15

nemo-guardrails.md

62

1 export nemo-guardrails

2 from "zechenzhangAGI/AI-research-SKILLs"

3 NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

2026-01-16

serving-llms-vllm.md

62

1 export serving-llms-vllm

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

2026-01-16

mamba-architecture.md

62

1 export mamba-architecture

2 from "zechenzhangAGI/AI-research-SKILLs"

3 State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.

2026-01-16

powershell-windows.md

62

1 export powershell-windows

2 from "xenitV1/claude-code-maestro"

3 PowerShell Windows patterns. Critical pitfalls, operator syntax, error handling.

2026-01-15

rwkv-architecture.md

62

1 export rwkv-architecture

2 from "zechenzhangAGI/AI-research-SKILLs"

3 RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

2026-01-16

code-review-checklist.md

62

1 export code-review-checklist

2 from "xenitV1/claude-code-maestro"

3 Code review guidelines covering code quality, security, and best practices.

2026-01-15

multiplayer.md

62

1 export multiplayer

2 from "xenitV1/claude-code-maestro"

3 Multiplayer game development principles. Architecture, networking, synchronization.

2026-01-15

artifacts-builder.md

62

1 export artifacts-builder

2 from "xenitV1/claude-code-maestro"

3 React/Tailwind component construction patterns for building reusable UI components.

2026-01-15

llamaguard.md

62

1 export llamaguard

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

2026-01-16

documentation-templates.md

62

1 export documentation-templates

2 from "xenitV1/claude-code-maestro"

3 Documentation templates and structure guidelines. README, API docs, code comments, and AI-friendly documentation.

2026-01-15

openrlhf-training.md

62

1 export openrlhf-training

2 from "zechenzhangAGI/AI-research-SKILLs"

3 High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

2026-01-16

condition-based-waiting.md

62

1 export condition-based-waiting

2 from "mneves75/dnschat"

3 Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

2026-01-13

behavioral-modes.md

62

1 export behavioral-modes

2 from "xenitV1/claude-code-maestro"

3 AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

2026-01-15

codebase-analyzer.md

62

1 export codebase-analyzer

2 from "severity1/claude-code-auto-memory"

3 This skill should be used when the user asks to "initialize auto-memory", "create CLAUDE.md", "set up project memory", or runs the /auto-memory:init command. Analyzes codebase structure and generates CLAUDE.md files using the exact template format with AUTO-MANAGED markers.

2026-01-15

sentencepiece.md

62

1 export sentencepiece

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.

2026-01-16

llamaindex.md

62

1 export llamaindex

2 from "zechenzhangAGI/AI-research-SKILLs"

3 Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.

2026-01-16

nemo-curator.md

62

1 export nemo-curator

2 from "zechenzhangAGI/AI-research-SKILLs"

3 GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

2026-01-16

mobile-typography.md

62

1 export mobile-typography

2 from "xenitV1/claude-code-maestro"

3 Mobile typography system for React Native and Flutter. Type scales, font weights, line heights, responsive typography, and dark mode support.

2026-01-15

game-development.md

62

1 export game-development

2 from "xenitV1/claude-code-maestro"

3 Game development orchestrator. Routes to platform-specific skills based on project needs.

2026-01-15

frontend-design.md

62

1 export frontend-design

2 from "xenitV1/claude-code-maestro"

3 Design thinking and decision-making for web UI. Use when designing components, layouts, color schemes, typography, or creating aesthetic interfaces. Teaches principles, not fixed values.

2026-01-15

systematic-debugging.md

62

1 export systematic-debugging

2 from "xenitV1/claude-code-maestro"

3 4-phase systematic debugging methodology with root cause analysis and evidence-based verification. Use when debugging complex issues.

2026-01-15

mobile-ux-patterns.md

62

1 export mobile-ux-patterns

2 from "xenitV1/claude-code-maestro"

3 Mobile UX patterns for touch gestures, haptic feedback, accessibility, and platform-native interactions. Essential for building truly mobile-friendly apps.

2026-01-15