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,...
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or...
Provides comprehensive IBM Mainframe administration, development, and modernization guidance including z/OS operations, JCL scripting, COBOL/PL/I programming, CICS/IMS configuration, DB2...
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform
Refactor CLAUDE.md files to follow progressive disclosure principles. Use when CLAUDE.md is too long or disorganized.
|
Guides comprehensive requirements gathering and analysis including stakeholder interviews, user story creation, use case documentation, acceptance criteria, requirements prioritization, and...
Agentic MCP - Three-layer progressive disclosure for MCP servers with Socket daemon. Use when the user needs to interact with MCP servers, query available tools, call MCP tools, or manage the MCP...
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF,...
Comprehensive guide for using Local Skills MCP - creating skills in the right locations, understanding skill directories, setup, and configuration. Use when creating new skills, deciding where to...
智能变更日志生成器 - 自动分析Git提交历史，生成符合规范的CHANGELOG.md。支持语义化版本管理、多种输出格式、增量更新和GitHub/GitLab集成。
Jeffrey Emanuel's multi-agent implementation workflow using NTM, Agent Mail, Beads, and BV. The execution phase that follows planning and bead creation. Includes exact prompts used.
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when...
Creates high-quality technical documentation including API documentation, user guides, tutorials, architecture documents, README files, release notes, and technical specifications. Produces clear,...
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 -...
Create interactive, production-ready UI mockups and prototypes using NuxtJS 4 (Vue) or Next.js (React), TypeScript, and TailwindCSS v4. Use when building web mockups, prototypes, landing pages,...
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities....
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+...
Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple sources. Use when the user needs thorough investigation, market...