majiayu000
@majiayu000
Public Skills
content-research-writer
by majiayu000
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
content-research-writer
by majiayu000
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
serving-llms-vllm
by majiayu000
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.
chroma
by majiayu000
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.
rwkv-architecture
by majiayu000
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.
simpo-training
by majiayu000
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
blip-2-vision-language
by majiayu000
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.
axolotl
by majiayu000
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
hqq-quantization
by majiayu000
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.
clip
by majiayu000
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.
peft-fine-tuning
by majiayu000
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.
verl-rl-training
by majiayu000
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
gptq
by majiayu000
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
mamba-architecture
by majiayu000
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.
slime-rl-training
by majiayu000
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
faiss
by majiayu000
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
miles-rl-training
by majiayu000
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
fine-tuning-serving-openpi
by majiayu000
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.
pyvene-interventions
by majiayu000
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.
unsloth
by majiayu000
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
nnsight-remote-interpretability
by majiayu000
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
experiment-tracking-swanlab
by majiayu000
Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.
whisper
by majiayu000
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 ASR.
sparse-autoencoder-training
by majiayu000
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.
nanogpt
by majiayu000
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
Testing Workflow
by majiayu000
The most comprehensive Claude Code skills registry Web Search: https://skills-registry-web.vercel.app
Testing Workflow
by majiayu000
The most comprehensive Claude Code skills registry Web Search: https://skills-registry-web.vercel.app
AgentOps State Discipline
by majiayu000
The most comprehensive Claude Code skills registry Web Search: https://skills-registry-web.vercel.app
Spec Management workflow
by majiayu000
The most comprehensive Claude Code skills registry Web Search: https://skills-registry-web.vercel.app
sse-resilience
by majiayu000
Redis-backed SSE stream management with stream registry, heartbeat monitoring, completion store for terminal events, and automatic orphan cleanup via background guardian process.
External Project Reality Auditor
by majiayu000
The most comprehensive Claude Code skills registry Web Search: https://skills-registry-web.vercel.app
Docker Review Skill
by majiayu000
The most comprehensive Claude Code skills registry Web Search: https://skills-registry-web.vercel.app
wolf-scripts-agents
by majiayu000
Agent coordination, orchestration, and multi-agent workflow management scripts
wolf-scripts-agents
by majiayu000
Agent coordination, orchestration, and multi-agent workflow management scripts
claude-skill-registry
by majiayu000
The most comprehensive Claude Code skills registry Web Search: https://skills-registry-web.vercel.app
sse-resilience
by majiayu000
Redis-backed SSE stream management with stream registry, heartbeat monitoring, completion store for terminal events, and automatic orphan cleanup via background guardian process.
AgentOps State Discipline
by majiayu000
The most comprehensive Claude Code skills registry Web Search: https://skills-registry-web.vercel.app
Article Verification Workflow
by majiayu000
The most comprehensive Claude Code skills registry Web Search: https://skills-registry-web.vercel.app
state-directory-manager
by majiayu000
Manage persistent state directories for bash scripts
state-directory-manager
by majiayu000
Manage persistent state directories for bash scripts
Spec Management workflow
by majiayu000
The most comprehensive Claude Code skills registry Web Search: https://skills-registry-web.vercel.app
Meta Dispatcher & Task Orchestrator
by majiayu000
PRD 驱动的任务调度与技能管理专家。接收完整 PRD/需求文档，负责拆解业务、选择技术栈、路由到合适的专业 Skill，并维护从方案到落地的全流程。
ceo-advisor
by majiayu000
Executive leadership guidance for strategic decision-making, organizational development, and stakeholder management. Includes strategy analyzer, financial scenario modeling, board governance frameworks, and investor relations playbooks. Use when planning strategy, preparing board presentations, managing investors, developing organizational culture, making executive decisions, or when user mentions CEO, strategic planning, board meetings, investor updates, organizational leadership, or executive strategy.
cto-advisor
by majiayu000
Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Includes tech debt analyzer, team scaling calculator, engineering metrics frameworks, technology evaluation tools, and ADR templates. Use when assessing technical debt, scaling engineering teams, evaluating technologies, making architecture decisions, establishing engineering metrics, or when user mentions CTO, tech debt, technical debt, team scaling, architecture decisions, technology evaluation, engineering metrics, DORA metrics, or technology strategy.
doc-updates
by majiayu000
Build Your Google ADK Skill
by majiayu000
"Create your Google Agent Development Kit skill in one prompt, then learn to improve it throughout the chapter"
Build Your LiveKit Agents Skill
by majiayu000
"Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter"
doc-updates
by majiayu000
adb-skill-generator
by majiayu000
Meta-tool for rapid adb-* skill creation from templates
agent-hierarchy-diagram
by majiayu000
"Generate visual hierarchy diagrams of agent system showing levels and delegation. Use for documentation or onboarding."
model-selection
by majiayu000
Automatically applies when choosing LLM models and providers. Ensures proper model comparison, provider selection, cost optimization, fallback patterns, and multi-model strategies.
model-selection
by majiayu000
Automatically applies when choosing LLM models and providers. Ensures proper model comparison, provider selection, cost optimization, fallback patterns, and multi-model strategies.
claude-ecosystem-promoter
by majiayu000
Marketing and promotion specialist for Claude ecosystem technology - MCP servers, skills, plugins, and agents. Expert in community engagement, registry submissions, content marketing, and developer relations. Activate on 'promote MCP', 'share skill', 'market plugin', 'launch agent', 'developer marketing', 'MCP registry'. NOT for creating MCPs/skills (use agent-creator), general marketing (use content-marketer), or SEO optimization (use seo-visibility-expert).
diff-analysis
by majiayu000
Methodology for categorizing changes, assessing risks, and creating summaries from any changeset. Triggers: diff analysis, changeset review, risk assessment, change categorization, semantic analysis, release preparation, change summary, git diff Use when: analyzing specific changesets, assessing risk of changes, preparing release notes, categorizing changes by type and impact DO NOT use when: quick context catchup - use catchup instead. DO NOT use when: full PR review - use review-core with pensive skills. Use this skill for systematic change analysis with risk scoring.
flow-nexus-neural
by majiayu000
Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus
diff-analysis
by majiayu000
Methodology for categorizing changes, assessing risks, and creating summaries from any changeset. Triggers: diff analysis, changeset review, risk assessment, change categorization, semantic analysis, release preparation, change summary, git diff Use when: analyzing specific changesets, assessing risk of changes, preparing release notes, categorizing changes by type and impact DO NOT use when: quick context catchup - use catchup instead. DO NOT use when: full PR review - use review-core with pensive skills. Use this skill for systematic change analysis with risk scoring.
Build Your Pipecat Skill
by majiayu000
"Create your Pipecat skill from official documentation, then learn to improve it throughout the chapter"
adb-skill-generator
by majiayu000
Meta-tool for rapid adb-* skill creation from templates
agent-hierarchy-diagram
by majiayu000
"Generate visual hierarchy diagrams of agent system showing levels and delegation. Use for documentation or onboarding."
Build Your Google ADK Skill
by majiayu000
"Create your Google Agent Development Kit skill in one prompt, then learn to improve it throughout the chapter"
flow-nexus-neural
by majiayu000
Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus
deduplication
by majiayu000
Event deduplication with canonical selection, reputation scoring, and hash-based grouping for multi-source data aggregation. Handles both ID-based and content-based deduplication.
Build Your Pipecat Skill
by majiayu000
"Create your Pipecat skill from official documentation, then learn to improve it throughout the chapter"
ceo-advisor
by majiayu000
Executive leadership guidance for strategic decision-making, organizational development, and stakeholder management. Includes strategy analyzer, financial scenario modeling, board governance frameworks, and investor relations playbooks. Use when planning strategy, preparing board presentations, managing investors, developing organizational culture, making executive decisions, or when user mentions CEO, strategic planning, board meetings, investor updates, organizational leadership, or executive strategy.
Shows you the largest objects in your repo's pack file.
by majiayu000
```
prompt-architect
by majiayu000
"Create and enhance prompts, system instructions, and principle files. Capabilities: transform verbose prompts, add patterns/heuristics, optimize token usage, structure CLAUDE.md principles, improve agent/persona definitions, apply prompt engineering techniques (CoT, few-shot, ReAct). Actions: create, enhance, optimize, refactor, compress prompts. Keywords: prompt engineering, system prompt, CLAUDE.md, principle files, instruction optimization, agent prompt, persona prompt, token efficiency, prompt structure, workflow prompts, rules, constraints, few-shot, chain-of-thought, soul, tensions, dialectic. Use when: creating new prompts, enhancing principle files, improving system instructions, optimizing CLAUDE.md, restructuring verbose prompts, adding patterns to workflows, defining agent behaviors."
planning
by majiayu000
"Universal planning for technical and non-technical projects. Domains: software implementation, business, personal, creative, academic, events. Capabilities: feature planning, system architecture, goal setting, milestone planning, requirement breakdown, trade-off analysis, resource allocation, risk assessment. Actions: plan, architect, design, evaluate, breakdown, structure projects. Keywords: implementation plan, technical design, architecture, roadmap, project plan, strategy, goal setting, milestones, timeline, action plan, SMART goals, sprint planning, task breakdown, OKRs. Use when: planning features, designing architecture, creating roadmaps, setting goals, organizing projects, breaking down requirements."
claude-ecosystem
by majiayu000
"Claude Code ecosystem expertise. Modules: CLI tool (setup, slash commands, MCP servers, hooks, plugins, CI/CD), extensibility (agents, skills, output styles creation), CLAUDE.md (project instructions, optimization). Actions: configure, troubleshoot, create, deploy, integrate, optimize Claude Code. Keywords: Claude Code, Anthropic, CLI tool, slash command, MCP server, Agent Skill, hook, plugin, CI/CD, enterprise, CLAUDE.md, agentic coding, agent, skill, output-style, SKILL.md, subagent, Task tool, project instructions, token optimization. Use when: learning Claude Code features, configuring settings, creating skills/agents/hooks, setting up MCP servers, troubleshooting issues, CI/CD integration, initializing or optimizing CLAUDE.md files."
sequential-thinking
by majiayu000
"Structured reflective problem-solving methodology. Process: decompose, analyze, hypothesize, verify, revise. Capabilities: complex problem decomposition, adaptive planning, course correction, hypothesis verification, multi-step analysis. Actions: decompose, analyze, plan, revise, verify solutions step-by-step. Keywords: sequential thinking, problem decomposition, multi-step analysis, hypothesis verification, adaptive planning, course correction, reflective thinking, step-by-step, thought sequence, dynamic adjustment, unclear scope, complex problem, structured analysis. Use when: decomposing complex problems, planning with revision capability, analyzing unclear scope, verifying hypotheses, needing course correction, solving multi-step problems."
research
by majiayu000
"Technical research methodology with YAGNI/KISS/DRY principles. Phases: scope definition, information gathering, analysis, synthesis, recommendation. Capabilities: technology evaluation, architecture analysis, best practices research, trade-off assessment, solution design. Actions: research, analyze, evaluate, compare, recommend technical solutions. Keywords: research, technology evaluation, best practices, architecture analysis, trade-offs, scalability, security, maintainability, YAGNI, KISS, DRY, technical analysis, solution design, competitive analysis, feasibility study. Use when: researching technologies, evaluating architectures, analyzing best practices, comparing solutions, assessing technical trade-offs, planning scalable/secure systems."
Universal Single-Cell Annotator
by majiayu000
The most comprehensive Claude Code skills registry Web Search: https://skills-registry-web.vercel.app
00-samples-policy
by majiayu000
samples ë©íë°ì´í°ê° package.jsonì ìì
00-meta-chain-flow-150
by majiayu000
"[00] META. Orchestrate skills into dynamic chains for complex tasks. Analyzes the task, discovers available skills, builds an optimal chain, explains why each skill is needed, and executes step-by-step with user confirmation. Use for any complex task requiring multiple thinking/research/analysis steps. Triggers on \"plan this\", \"how to approach\", \"what's the strategy\", \"build a plan\", or any multi-step problem requiring skill orchestration."
DSA Skills
by majiayu000
Dynamic Programming 0/10
atlassian-cli
by majiayu000
Use when working with Jira or Confluence from command line, including authentication, searching issues with JQL, bulk operations, sprint reports, or creating/updating work items using acli
clark-county-pleadings
by majiayu000
Create, edit, and convert legal pleadings for Clark County District Court and Justice Court, Nevada. Handles specialized .doc/.docx format with line numbering (1-28), proper caption formatting, document codes (District Court), criminal/civil motion templates, and PDF conversion. Use for drafting motions to suppress, discovery requests, continuances, oppositions, and other court documents for both Nevada District and Justice Courts.
confluence-server
by majiayu000
This skill enables interaction with Confluence Server/Data Center REST API for documentation retrieval and knowledge management. Use when the user wants to read pages, search content, list spaces, or retrieve documentation from Confluence Server.
Litdb Expert Skill
by majiayu000
Expert assistant for using litdb - a literature and document database for scientific research
claude-skill-registry
by majiayu000
```
bg-remover
by majiayu000
Remove backgrounds from images using FAL.ai's BiRefNet model. Use when users ask to remove background, make transparent PNG, extract subject from image, or create cutouts. Trigger phrases include "remove background", "transparent background", "cut out", "extract subject", or any background removal request.
buildkite
by majiayu000
Use this skill when working with Buildkite CI/CD pipelines, agents, builds, test analytics, or package registries. Covers pipeline configuration, YAML syntax, agent setup, build steps, plugins, and API usage.
codex-delegator
by majiayu000
Automatically delegate complex, logic-intensive tasks to OpenAI Codex CLI via codex exec --full-auto. Claude Code uses this skill to invoke Codex for complex backend logic, intricate algorithms, or persistent bugs. Enables seamless AI-to-AI collaboration where Claude Code analyzes and Codex executes.
golang-web
by majiayu000
Modern Go Web application architecture guide. Use when creating new Go web projects, APIs, or microservices. Covers project structure, tech stack selection, and best practices based on Go standards.
web-asset-generator
by majiayu000
Generate web assets including favicons, app icons (PWA), and social media meta images (Open Graph) for Facebook, Twitter, WhatsApp, and LinkedIn. Use when users need icons, favicons, social sharing images, or Open Graph images from logos or text slogans. Handles image resizing, text-to-image generation, and provides proper HTML meta tags.
codex-agent
by majiayu000
MANDATORY for code review - must use Codex CLI for all code reviews, then apply fixes based on Codex feedback. Also use for cross-verification, debugging, and getting alternative implementations.
api-design
by majiayu000
REST/GraphQL/gRPC API design best practices. Use when designing APIs, defining contracts, handling versioning. Covers OpenAPI 3.2, GraphQL Federation, gRPC streaming.