Research
920 skills.
Browse
ara-compilerorchestra-researchCompiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical layer (configs, code stubs), exploration graph, and grounded evidence. Use when ingesting a paper or codebase into a structured, machine-executable knowledge package, building an ARA from scratch, or converting research outputs into a falsifiable, agent-traversable form.ara-research-managerorchestra-researchRecords research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.ara-rigor-reviewerorchestra-researchPerforms ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance, falsifiability, scope calibration, argument coherence, exploration integrity, methodological rigor) and producing a constructive, severity-ranked report with a Strong Accept-to-Reject recommendation. Use after Level 1 structural validation passes, when an ARA needs an objective epistemic critique before publication or release.autoresearchorchestra-researchOrchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experimenblip-2-vision-languageorchestra-researchVision-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.brainstorming-research-ideasorchestra-researchGuides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.constitutional-aiorchestra-researchAnthropic'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.creative-thinking-for-researchorchestra-researchApplies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.deepspeedorchestra-researchExpert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attentionevaluating-cosmos-policyorchestra-researchEvaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.experiment-tracking-swanlaborchestra-researchProvides 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.knowledge-distillationorchestra-researchCompress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.llavaorchestra-researchLarge 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 chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.miles-rl-trainingorchestra-researchProvides 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.ml-training-recipesorchestra-researchmlfloworchestra-researchTrack ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platformmodel-pruningorchestra-researchReduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.nanogptorchestra-researchEducational 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).openrlhf-trainingorchestra-researchHigh-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. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.presenting-conference-talksorchestra-researchGenerates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.rwkv-architectureorchestra-researchRNN+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.sentencepieceorchestra-researchLanguage-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, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.sparse-autoencoder-trainingorchestra-researchProvides 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.tensorboardorchestra-researchVisualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkittransformer-lens-interpretabilityorchestra-researchProvides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.verl-rl-trainingorchestra-researchProvides 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.weights-and-biasesorchestra-researchTrack ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platformloogle-searchparcadeiSearch Mathlib for lemmas by type signature patternperplexity-searchparcadeiAI-powered web search, research, and reasoning via Perplexitypint-computeparcadeiUnit-aware computation with Pint - convert units, dimensional analysis, unit arithmeticproveparcadeiFormal theorem proving with research, testing, and verification phasesrepo-research-analystparcadeiAnalyze repository structure, patterns, conventions, and documentation for understanding a new codebaseresearch-agentparcadeiResearch agent for external documentation, best practices, and library APIs via MCP toolsresearch-externalparcadeiExternal research workflow for docs, web, APIs - NOT codebase explorationbriesearchpaulnsorensenResearches cited evidence from documentation, current web sources, repositories, local code, and Git hosting. Use when the user asks to research, compare, investigate, verify facts, find guidance, assess maintenance, or gather evidence before implementation.data-science-expertpersonamanagmentlayerExpert-level data science, analytics, visualization, and statistical modeling. Use when the user mentions analytics, visualization, statistics, pandas, or NumPy, or when the task involves Data Analysis, Machine Learning, Data Visualization, or Feature Engineering.statistics-mathpluginagentmarketplaceStatistics, probability, linear algebra, and mathematical foundations for data sciencePandas Data AnalysispluginagentmarketplaceMaster data manipulation, analysis, and visualization with Pandas, NumPy, and Matplotlibacademic-writingpoemsweYou must use this when producing any research prose — literature reviews, syntheses, analyses, methodology descriptions, discussion sections, abstracts, or any written output intended for an academic audience.google-trends-researchpostplusaiResearch Google Trends keyword momentum, regional interest, and related queries. Use search-interest evidence without treating it as sales or total demand.tiktok-researchpostplusaiResearch public TikTok videos, comments, creators, profiles, related videos, and paid ad examples for audience evidence and creative benchmarks.youtube-researchpostplusaiResearch public YouTube channels, video metrics, and comment samples; obtain downloadable video records when requested. Use for content and audience evidence.paper2codeprathamlearnstocodeConverts an arxiv paper into a minimal, citation-anchored Python implementation. Trigger when user runs /paper2code with an arxiv URL or paper ID, says "implement this paper", or pastes an arxiv link asking for implementation. Flags all ambiguities honestly. Never invents implementation details not stated in the paper.academic-research-skills-codexreason-machinesAI-assisted academic research workflows for literature review, paper writing, peer review, and research pipelinescodex-autoresearch-loopreason-machinesSelf-directed iterative research skill for Codex that continuously cycles through modify, verify, retain or discard, and repeat until a measurable goal is reached.taiwan-equity-research-coveragereason-machinesStructured equity research database for 1,735 Taiwan-listed companies with wikilink knowledge graph, supply chain mapping, and financial data tools.tribev2-brain-encodingreason-machinesUse TRIBE v2, Meta's multimodal foundation model for predicting fMRI brain responses to video, audio, and text stimuliwildworld-datasetreason-machinesWildWorld large-scale action-conditioned world modeling dataset with 108M+ frames from a photorealistic ARPG game, featuring per-frame annotations, 450+ actions, and explicit state information for generative world modeling research.financial-deep-researchrebyteai-templateConduct enterprise-grade financial research with multi-source synthesis, regulatory compliance tracking, and verified market analysis. Use when user needs comprehensive financial analysis requiring 10+ sources, verified claims, market comparisons, or investment research. Triggers include "financial research", "market analysis", "investment analysis", "due diligence", "financial deep dive", "compare stocks/funds", or "analyze [company/sector]". Do NOT use for simple stock quotes, basic company loindustry-researchrkreddypComprehensive industry research skill providing methodologies, frameworks, and best practices for analyzing industry trends, key companies, market dynamics, and industry-specific developments across consumer, tech, healthcare, and finance sectors