NousResearch
- 195 skills
- 0 followers
- 11 hours ago last updated
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Claude Code Orchestration · nousresearchOrchestrate Claude Code (Anthropic CLI) as a subagent. Two modes — print mode (one-shot, fast) and PTY/tmux mode (interactive, multi-turn). Use when delegating a coding task to a fresh Claude Code session with restricted tools.
- ▌ Writing Plans · nousresearchWrite implementation plans that make coding obvious — exact file paths, full code examples, step-by-step commands, expected output. Use before any feature with 3+ files or when delegating to subagents.
- ▌ Kanban Dispatcher · nousresearchSQLite task board for structured multi-agent parallelization. Workers claim tasks, send heartbeats, request approval gates, and spawn child tasks. Use when orchestrating 3+ parallel agents on a complex project with dependencies.
- ▌ Hermes S6 Container Supervision · nousresearchModify or debug s6 services in the Hermes Docker image.
- ▌ Sparse Autoencoder Training · nousresearch bundleTrain sparse autoencoders to interpret model features.
- ▌ Audiocraft Audio Generation · nousresearch bundleAudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
- ▌ Baoyu Article Illustrator · nousresearch bundleArticle illustrations: type × style × palette consistency.
- ▌ Optimizing Attention Flash · nousresearch bundleSpeed up long-sequence transformer training and inference.
- ▌ MCP OAUTH Remote Gateway · nousresearch bundleManual OAuth for remote MCP servers on headless gateways.
- ▌
- ▌ Kanban Video Orchestrator · nousresearch bundlePlan and run multi-agent video production pipelines.
- ▌ Memento Flashcards · nousresearch bundle>- Spaced-repetition flashcard system. Create cards from facts or text, chat with flashcards using free-text answers graded by the agent, generate quizzes from YouTube transcripts, review due cards with adaptive scheduling, and export/import decks as CSV.
- ▌ Cloudflare Temporary Deploy · nousresearch bundleDeploy a Worker live, no account, via wrangler --temporary.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Huggingface Tokenizers · nousresearch bundleFast BPE/WordPiece tokenization and custom vocab training.
- ▌
- ▌
- ▌ Neuroskill Bci · nousresearch bundle> Connect to a running NeuroSkill instance and incorporate the user's real-time cognitive and emotional state (focus, relaxation, mood, cognitive load, drowsiness, heart rate, HRV, sleep staging, and 40+ derived EXG scores) into responses. Requires a BCI wearable (Muse 2/S or OpenBCI) and the NeuroSkill desktop app running locally.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Segment Anything Model · nousresearch bundleSAM: zero-shot image segmentation via points, boxes, masks.
- ▌
- ▌
- ▌ Weights And Biases · nousresearch bundleW&B: log ML experiments, sweeps, model registry, dashboards.
- ▌
- ▌
- ▌ Oss Forensics · nousresearch bundle| Supply chain investigation, evidence recovery, and forensic analysis for GitHub repositories. Covers deleted commit recovery, force-push detection, IOC extraction, multi-source evidence collection, hypothesis formation/validation, and structured forensic reporting. Inspired by RAPTOR's 1800+ line OSS Forensics system.
- ▌
- ▌ Serving Llms Vllm · nousresearch bundlevLLM: high-throughput LLM serving, OpenAI API, quantization.
- ▌
- ▌
- ▌ Architecture Diagram · nousresearch bundleDark-themed SVG architecture/cloud/infra diagrams as HTML.
- ▌
- ▌
- ▌
- ▌ Drug Discovery · nousresearch bundle> Pharmaceutical research assistant for drug discovery workflows. Search bioactive compounds on ChEMBL, calculate drug-likeness (Lipinski Ro5, QED, TPSA, synthetic accessibility), look up drug-drug interactions via OpenFDA, interpret ADMET profiles, and assist with lead optimization. Use for medicinal chemistry questions, molecule property analysis, clinical pharmacology, and open-science drug research.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Popular Web Designs · nousresearch bundle54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
- ▌
- ▌ Web Pentest · nousresearch bundle| Authorized web application penetration testing — reconnaissance, vulnerability analysis, proof-based exploitation, and professional reporting. Adapts Shannon's "No Exploit, No Report" methodology with hard guardrails for scope, authorization, and aux-client leakage. Active testing against running applications you own or have written authorization to test.
- ▌
- ▌
- ▌ One Three One Rule · nousresearch> Structured decision-making framework for technical proposals and trade-off analysis. When the user faces a choice between multiple approaches (architecture decisions, tool selection, refactoring strategies, migration paths), this skill produces a 1-3-1 format: one clear problem statement, three distinct options with pros/cons, and one concrete recommendation with definition of done and implementation plan. Use when the user asks for a "1-3-1", says "give me options", or needs help choosing between competing approaches.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌