461 skills found Ā· Page 3 of 16
wanshuiyin / paper-illustration-image2Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation.
wanshuiyin / research-refineTurn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-6-Astra review
wanshuiyin / research-wikiPersistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern
wanshuiyin / experiment-planTurn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problā¦
wanshuiyin / integrity-forensicsRun the Anti-Autoresearch integrity-forensics sweep (span-anchored evidence ledger ā GPT auditors propose findings ā a rules-only reporter that lists every proposal with what the auditor said about it) against a paper via a SHA-pinned thin launcher ā then convert the verdict into a typed policy gateā¦
wanshuiyin / proof-orchestratorManage a stateful, run-directory-based proof project: continuation across runs, run-local source bookkeeping, manual GPT Pro handoff packages when a local attempt stalls, and an optional DeepSeek second opinion as additional evidence only
wanshuiyin / alphaxivQuick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback
wanshuiyin / auto-paper-improvement-loopAutonomously improve a generated paper via GPT-6-Astra xhigh review ā implement fixes ā recompile, for 2 rounds
wanshuiyin / system-profileProfile a target (script, process, GPU, memory, interconnect) for performance analysis
larksuite / lark-openapi-exploreré£ä¹¦/Lark åē OpenAPI ę¢ē“¢ļ¼ä»å®ę¹ęę”£åŗäøęęęŖē» CLI å°č£ ēåē OpenAPI ę„å£ćå½ēØę·ēéę±ę ę³č¢«ē°ę lark-* skill ę lark-cli å·²ę³Øåå½ä»¤ę»”č¶³ļ¼éč¦ę„ę¾å¹¶č°ēØåēé£ä¹¦ OpenAPI ę¶ä½æēØć
AgriciDaniel / claude-obsidianSelf-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal knowledge management (PKM), and an open-source Notion alternative.
Orchestra-Research / huggingface-tokenizersFast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers
Orchestra-Research / nnsight-remote-interpretabilityProvides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution
Orchestra-Research / pyvene-interventionsProvides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework
Orchestra-Research / sparse-autoencoder-trainingProvides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features
Orchestra-Research / transformer-lens-interpretabilityProvides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching
Orchestra-Research / langchainFramework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval.
Orchestra-Research / outlinesGuarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library
Orchestra-Research / implementing-llms-litgptImplements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral)
Orchestra-Research / mamba-architectureState-space model with O(n) complexity vs Transformers' O(nĀ²). 5Ć 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.
Orchestra-Research / nanogptEducational 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).
Orchestra-Research / rwkv-architectureRNN+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.
Orchestra-Research / nemo-curatorGPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16Ć faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS.
Orchestra-Research / openrlhf-trainingHigh-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. 2Ć faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Orchestra-Research / fine-tuning-with-trlFine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training
Orchestra-Research / constitutional-aiAnthropic'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 alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
Orchestra-Research / llamaguardMeta'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.
Orchestra-Research / nemo-guardrailsNVIDIA'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.
Orchestra-Research / ray-trainDistributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling
Orchestra-Research / gptqPost-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4Ć memory reduction with <2% perplexity degradation, or for faster inference (3-4Ć speedup) vs FP16.
