Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival.
This skill should be used when working with single-cell omics data analysis using scvi-tools, including scRNA-seq, scATAC-seq, CITE-seq, spatial transcriptomics, and othe — from…
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature — from…
Process-based discrete-event simulation framework in Python. Use this skill when building simulations of systems with processes, queues, resources, and time-based events — from…
Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for…
Use this skill when working with symbolic mathematics in Python. This skill should be used for symbolic computation tasks including solving equations algebraically, perfo — from…
Use this skill when working with scientific research tools and workflows across bioinformatics, cheminformatics, genomics, structural biology, proteomics, and drug discov — from…
Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM.
This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions.
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data.
Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival.
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature — from…
Cross-reference experimental designs and statistical validity across primary sources, covering effect-size verification, p-value and power analysis, methodology critique, and…
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).
Systematic framework for evaluating scholarly and research work based on the ScholarEval methodology.
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks.
Maintain scikitplot.impute, especially ANNImputer, its experimental public gate, approximate-neighbor backend dispatch, index access/persistence policy, sklearn compatibility…
Edit and tighten scientific or technical prose at the sentence and paragraph level, using the method taught in Stanford's Writing in the Sciences.
The super-loop that closes the research→backlog loop — it chains the outward CRAWLERS (the daily `idea-scout` arXiv/GitHub feed, the industry scans, the RESEARCH/CONCEPT corpus)…
Market research powered by live web data. Use this skill when the user wants to understand a market, category, or customer segment — including consumer sentiment, demand and trend…
Seaborn Statistical Visualization workflow skill. Use this skill when the user needs Seaborn is a Python visualization library for creating publication-quality statistical…
Use this skill whenever you need to know where something lives in a codebase or what else a change touches — before any code change, when you're new to a repo, when a request…
DEFAULT search tool for ALL search/lookup needs. Multi-source search and deduplication layer with intent-aware scoring.
This skill should be used when performing web research beyond a simple single search -- looking into topics, comparing options, investigating questions, finding recommendations,…
Use this skill when the user wants to design or operate a budgeted economic agent with its own operational identity, AgentMail address, agent-wallet treasury, infrastructure…
Autonomous skill generator that learns new technologies from the web. Use when, users want to learn about a new library/framework/tool, need to create a skill for an unfamiliar…
GitHub CLI primitives for the senpai research workflow — label swaps, send-back, close, mark-review, issue checks, PR queries.
Turn an investment agent into a supply-chain bottleneck hunter. Use this skill for source-backed investment research, live market/theme scans, AI/semi/technology value-chain…
This skill analyses user session recordings and usability tests to identify research-backed design insights.
Statistical analysis of trading sessions — London, New York, Tokyo, and their overlaps. Use this skill whenever the user asks about "best time to trade", "session analysis",…
Use when after computing pairwise similarity scores across a collection of preprocessed mass spectra using matchms similarity measures (Cosine-related, molecular…
Designs complete single-cell research plans from a user-provided biomedical direction. Always use this skill whenever a user wants to design, scope, or structure a single — from…
MANDATORY META-SKILL: Governs how the AI agent interacts with ALL other skills. Enforces disciplined skill reading, smart selection, complete execution, speed, and quality.
This skill provides comprehensive guidance and tools for conducting pharmacoeconomic evaluations including cost-effectiveness analysis (CEA), cost-utility analysis (CUA),…
Decision criteria for when to extract content into skills vs keep inline, and when to amplify terse instructions via research.
Search the web for real-time information using the Skywork web search API. Use this skill whenever the user needs up-to-date information from the internet — for example,…
Deep multi-round PR code review for the slax-reader-client Kotlin Multiplatform Compose project. Runs visible-quality triage (performance, idiomaticity, elegance), researches…
Creates an L2 slice in the abap_wiki knowledge base: a business process on which to build functional documentation.
Use when you have an ArchR project with clustered single-cell ATAC-seq cells and want to reconstruct developmental or cellular transition trajectories.
Use when when you have SMILES structures of small organic molecules and need to predict CCS values for metabolite annotation in untargeted mass spectrometry workflows.
Use when deciding whether and how experiments belong in a SODA (ACM-SIAM Symposium on Discrete Algorithms) paper — SODA's scope includes experimental validation but theorems carry…
Use this skill when presenting information from external sources, citing research, or answering factual questions. Assess source credibility and recency before relying on it.
No Inference / Source-Locked Verification. Forces Claude to answer ONLY from user-provided materials and/or online sources actually accessed — no inference, no assumptions, no…
This skill should be used when the user asks to 'verify sources', 'check citations', 'fact-check footnotes', 'verify quotes', 'source check', 'are my cites real', 'check for…
Guidance for writing SPARQL queries against RDF/Turtle datasets, particularly for university or academic data.
Use when after identifying candidate parent–adduct mass-difference pairs (via massdiff, histogram binning, and adductMatch), apply this skill to discriminate true molecular…
Identify statistically significant clusters of events across both space and time. Use this skill whenever the user mentions spatiotemporal, cluster analysis, hotspot, getis ord,…
This skill should be used when the user asks to "spawn an agent team", "run agents in parallel", "multi-agent review", "build an agent team", "fan out work to agents", or asks for…
Research and shortlist target speakers for B2B marketing events — webinars, fireside chats, customer panels, podcast guests, virtual summits, conference sessions, and roadshow…
This skill should be used when the user asks to "create a policy spec", "write a spec", "spec-first policy", "docs/specs/rego", "SPEC.md", "policy specification", "spec template",…
Research devcontainer spec, official CLI, and VS Code extension behavior before making design decisions.
Enforces Millrace research-loop spec quality for GoalSpec and incident fix_spec artifacts using verifiable requirements, ambiguity bans, and deterministic traceability.
Spec-driven development orchestrator that turns vague, top-of-mind feature requests into production-grade specifications before any code is written.
Research an interviewer online before a meeting using parallel TinyFish agents and return a structured prep report.
Apply causal inference methods — counterfactual framework, instrumental variables, propensity score matching, and difference-in-differences — to estimate causal effects from…
Conduct Exploratory Data Analysis (EDA) using descriptive statistics, visualizations, and data quality checks.
Conduct statistical hypothesis testing including null/alternative hypothesis formulation, p-values, Type I/II errors, and test statistic selection.
Use when after identifying differentially methylated bases (q-value < 0.01, methylation difference > 25%) using calculateDiffMeth(), use this skill to determine what fraction of…
Sample-size and statistical power calculations for planning studies. Use whenever someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis,…
Comprehensive stock market analysis skill covering A-share (China), Hong Kong, and US equities. Priority use cases: stock analysis and buy/sell/hold recommendations by ticker…