Research a technology, library, API, or approach to inform an architecture or implementation decision.
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit
A local text formatting organizer for biomedical/academic writing; use it when you need to clean whitespace/line endings while preserving Markdown structures or when normalizing…
textstat is a Python package that calculates readability statistics for text content, including Flesch Reading Ease, Gunning Fog Index, SMOG Index, Coleman-Liau Index, and…
Thermodynamics from the zeroth law through statistical mechanics. Covers temperature and thermal equilibrium, heat transfer mechanisms (conduction, convection, radiation), the…
Combined research, decision, and codification workflow. Use when: (1) Exploring a question before committing (2) Making a decision that needs documentation (3) User says research,…
Analysis of Competing Hypotheses. Operationalizes Richards Heuer's CIA-tradition technique for systematically narrowing among multiple hypotheses against evidence.
Abductive reasoning about causes. Takes a phenomenon, separates observations from interpretations, then spawns diagnosticians applying different reasoning lenses (technical,…
Apply Karpathy framing — AI agent 架構 / skill as code / auto-research / 學習工作流 / human-vs-agent split / 教育設計.
First-person rigor patterns for non-trivial work — type/dimension check, decompose, bound-then-refine, sanity at limits, falsifiability.
Apply parsimony principle to prefer simpler explanations with fewer assumptions. Use for hypothesis selection in debugging, architecture decisions, and choosing between competing…
Multi-source research on concepts and ideas. Combines web search, documentation lookup, and codebase analysis into structured findings.
Hypothesis → Prediction → Test → Revise with explicit falsification. Use for debugging, feature experimentation, performance investigation, and A/B testing design.
Test ideas through hypothetical scenarios when empirical testing is impractical. Use for architecture evaluation, edge case analysis, ethics considerations, and strategy…
Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems where simple prompting…
Comprehensive guide for developing MailExtensions for Mozilla Thunderbird, including Manifest V2/V3 configuration, all messenger.* APIs, UI actions, Experiment APIs, and ATN…
Analyzes time-series data for patterns, trends, seasonality, and anomalies, with forecasting using statistical and machine learning methods.
Plan and control time-step policies for transient simulations — couple CFL and physics-based stability limits with adaptive stepping, ramp initial transients through sharp…
Optimizes manuscript titles and abstracts for information density, factual accuracy, and submission fit in biomedical research writing.
Fast and accurate code statistics tool written in Rust. Counts lines of code, comments, and blanks across 200+ languages, with output in JSON, YAML, or CBOR for programmatic…
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms.
Use when converting medical text between academic and patient-friendly tones, translating medical jargon for patients, adapting research papers for public audiences, or rewriting…
Use when planning a topic cluster (hub + spokes) for a new content area. The agent researches the space, identifies the hub topic, maps the spokes, and produces a specific content…
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
PyTorch Geometric (PyG) for graph neural networks: node/graph classification, link prediction with GCN, GAT, GraphSAGE, GIN.
PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning.
PyTorch-native Graph Neural Network framework for molecules and proteins. Suitable for building custom GNN architectures for drug discovery, protein modeling, or knowledge graph…
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms.
Interactive guided tour of the Claude Memory Kit aimed at marketers, content creators, and agency operators — not developers.
Identify which processes, connections, and remote hosts are actually using bandwidth before you chase the wrong incident hypothesis.
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "V/TO", "quarterly rocks", "Level 10…
Multi-agent trading analysis for a stock ticker. Runs technical, news, fundamentals, and macro analysts in parallel, then an adversarial bull/bear debate, then Research Manager,…
Diagnose why website traffic changed. Use when the user asks "why did traffic drop/spike", investigates an anomaly, or wants to separate tracking regressions from real behaviour…
Research the Israeli traffic statute behind a specific offense — find the regulation/section, number of points, fine tier, applicable appeal route (legacy vs.
Run a quick training experiment locally (CPU or MPS). Use when the user wants to test a model change, debug training code, run a smoke test, or validate a new architecture before…
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching.
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching.
วางแผนทริปครบวงจร — destination research, day-by-day itinerary, budget calculator, packing list, visa info (ไทย+ต่างประเทศ)
Systematically gather comprehensive travel itinerary requirements through structured discovery questions, MCP-powered research (Perplexity, Exa), and expert detail gathering.
Run a command or prompt on a recurring interval, like a lab rat on a wheel. Use when the user wants to poll, repeat a task periodically, set up a recurring check, or keep a…
Trending audio and sound finder for Instagram Reels and TikTok — research currently trending sounds, match them to your niche, and suggest how to use them in your content.
(Industry standard: Meta-Learning System / Automated Autoresearch) Primary Use Case: Continuous, self-improving orchestration of an agentic system over multiple sessions.
Skill untuk riset, terjemahan, dan eksplorasi 100,000+ kitab klasik Islam dari Turath.io. Gunakan skill ini saat user meminta riset literatur Islam, menerjemahkan teks Arab,…
Use AutoResearchClaw when an agent should turn a raw research topic into literature review, experiment planning, draft writing, and verification artifacts instead of improvising…
Generates complete two-sample Mendelian randomization research designs from a user-provided outcome, exposure or exposure family, and robustness direction.
Generates complete two-sample Mendelian randomization (MR) research designs from a user-provided research direction.
Query UCSC Genome Browser REST API for DNA sequences, tracks, gene models, and conservation across 100+ assemblies.
Iteratively improve frontend UI quality through automated grade-fix-verify cycles inspired by Karpathy's autoresearch pattern.
Use when working with Ultramemory hybrid memory system, storing/retrieving information, managing multi-agent memory operations, web research with Tavily, or scheduling automated…
Think-Driven Interactive Discovery - Deep research with step-file architecture for high-density output
Reviews umbrella reviews and second-order meta-analyses. Use when synthesizing existing systematic reviews/meta-analyses, assessing primary-study overlap, duplicate evidence,…
Unity Physics skill for collision detection, rigidbody dynamics, raycasting, and physics configuration.
Unreal Engine Chaos physics skill for destruction, vehicle simulation, and cloth physics.
Generates user-facing usage statistics, activity summaries, and personalized insights dashboards (weekly recaps, year-in-review, Spotify Wrapped-style).
Use when the user wants browser automation, page inspection, or web research and you need to choose between public-web tools, the live browser session, or a separate browser…
Use when researching what someone has been working on, getting up to speed on a colleague's recent activity, or preparing for a 1:1.
Design and improve product user onboarding (first-time user experience) to drive activation and early retention.
Plan, conduct, and synthesize user research. Trigger with "user research plan", "interview guide", "usability test", "survey design", "research questions", or when the user needs…
Plan and execute user research — interviews, surveys, usability tests. Use when you need primary evidence to inform a product decision.
Specialized skill for synthesizing qualitative user research into actionable insights. Analyzes interview transcripts, extracts patterns and themes, identifies pain points,…