Data journalism workflows for analysis, visualization, and storytelling. Use when analyzing datasets, creating charts and maps, cleaning messy data, calculating statistics, or building data-driven...
Research and plan implementation approach using parallel subagent exploration. Creates TDD-compliant implementation plans in doc/plans/ by investigating codebase, analyzing trade-offs, and...
Multi-conversation methodology for iterative stateful work with context accumulation. Use when users request work that spans multiple sessions (research, debugging, refactoring, feature...
Multi-conversation methodology for iterative stateful work with context accumulation. Use when users request work that spans multiple sessions (research, debugging, refactoring, feature...
Analyzes and transforms prompts using 7 research-backed frameworks (CO-STAR, RISEN, RISE-IE, RISE-IX, TIDD-EC, RTF, Chain of Thought, Chain of Density). Provides framework recommendations, asks...
Optimize markdown files for LLM consumption by adding YAML front-matter with metadata and TOC, normalizing heading hierarchy, removing noise and redundancy, converting verbose prose to structured...
Use when the user has a document (PDF, markdown, book notes, research paper, methodology guide) containing theoretical knowledge or frameworks and wants to convert it into an actionable, reusable...
Research top-performing Xiaohongshu (ε°ηΊ’δΉ¦ / XHS) image posts, analyze titles/content/comments for patterns and emotional resonance, enrich background via Firecrawl MCP, then write and publish an...
When the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price...
Guide safe refactoring with research-backed discipline and small-change rigor. Produce refactoring approach, step sequence, and risk assessment. Use when modifying existing code, improving...
Analyze audience demographics, engagement patterns, and follower behavior across Instagram, YouTube, and LinkedIn using anysite MCP server. Understand who engages with content, track audience...
World-class color theory expertise combining the scientific precision of Josef Albers' "Interaction of Color," the systematic thinking of color systems from Pantone and RAL, and the perceptual...
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...
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,...
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety...
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...
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....
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or...
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...
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...