Complete 10-gate pre-dev workflow for large features (>=2 days). Orchestrates topology discovery, research, PRD, feature map, design validation, TRD, API design, data model,…
Use when you have extracted fragmentation patterns from a collection of MS/MS spectra (using mineMS2) and have partitioned spectra into components via GNPS molecular networking…
Advise on pricing strategy — competitive analysis, willingness-to-pay research, tier design, price increase modeling, discount frameworks, and packaging optimization for startup…
Use when your input is a normalized, centered gene expression matrix with many genes (e.g., 12,000+) and you need to validate whether reducing to a smaller number of principal…
Professional paper research with papercli. Multi-pass search, PDF download and reading, math-aware synthesis, and a detailed referenced markdown findings report.
Mathematical foundations of uncertainty and random phenomena. Covers sample spaces, events, axioms, conditional probability, Bayes' theorem, independence, random variables,…
Run end-to-end product experiments from assumption to decision: translate assumptions into testable hypotheses and experiment briefs, select the right method among qualitative…
Profiles a dataset to surface summary statistics, distributions, missing-value matrix, correlations, outliers, and data-quality issues with severity ratings.
Track and report Claude Code skill usage statistics. Use this whenever the user asks about skill usage, skill stats, skill reports, which skills are used most or least, wants to…
Return memory statistics snapshot from UnityEngine.Profiling.Profiler — reserved, allocated, mono heap, graphics, etc. (in MB).
Ranks and analyzes statement fingerprints using aggregated SQL statistics from crdb_internal.statement_statistics to identify slow, resource-intensive, or error-prone query…
Analyzes transaction fingerprints using aggregated statistics from crdb_internal.transaction_statistics to identify high-retry transactions, contention patterns, and commit…
Estimate AI-assisted and hybrid human+agent development work with research-backed PERT statistics and calibration feedback loops
Structured methodology for constructing and verifying mathematical proofs in statistical research
Run statistically sound comparisons on eval results so prompt and model changes are judged by confidence bounds, not bar-chart vibes.
Test and evaluate AI agents and LLM outputs using code-first evaluation framework with strong typing.
Use when reading, writing, or validating binned and/or unbinned statistical models in the HS3 (HEP Statistics Serialization Standard) JSON format: converting between HistFactory…
Bayesian statistical modeling with PyMC v5+. Use when building probabilistic models, specifying priors, running MCMC inference, diagnosing convergence, or comparing models.
Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization pro — from…
Belief propagation with ordered-statistics post-processing (BP-OSD) for QECTOR. Covers the box-plus kernel phi(x) = -ln(tanh(x/2)), the log-domain sum-product / min-sum / relay…
The strict mathematical ground rules for every QECTOR claim. Encodes the F2 notation, the 16 correctness theorems, the Wilson score interval for LER, the…
Deep web research and HTML report generation. When GLM needs to conduct systematic information gathering and analysis for: (1) Exploring open-ended questions through multi-step…
Use when you have a feature intensity matrix (peak vector) and a corresponding set of QC sample indices from a multi-batch LC/GC-MS experiment, and you need to establish…
Build financial models, backtest trading strategies, and analyze market data. Implements risk metrics, portfolio optimization, and statistical arbitrage.
Expert in quantitative finance, algorithmic trading, and financial data analysis using Python (Pandas/NumPy), statistical modeling, and machine learning.
Expert in quantitative finance, algorithmic trading, and financial data analysis using Python (Pandas/NumPy), statistical modeling, and machine learning.
Define, test, and stress-test a quantitative factor (momentum, value, carry, quality) with explicit universe, signal, weighting, and statistical checks.
Use when you have a peak table matrix with NA values that need to be imputed using cluster statistics, or when a GCIMSDataset object requires filtering by retention time (0–1100…
Use when after installing R or modifying an R environment via conda, package managers, or container images; before running any pipeline step that depends on R packages for…
Use when after training a customized R statistical or machine learning model on annotated training data, you need to persist the trained model object for reuse in downstream…
R statistical modeling with base stats, sandwich, lmtest, car, broom. OLS/WLS/ GLS via lm(), GLMs via glm() (logit, probit, Poisson, negative binomial), robust/clustered SEs via…
Query Radix DLT blockchain data including wallet balances and performance, token prices and market movers, validator staking info, transaction history, network statistics — from…
Use when beginning an LC-MS data analysis pipeline and you need to rapidly inspect instrument metadata, acquisition parameters, or scan statistics from proprietary Thermo .raw…
Audit a rehabilitation recovery tracking system -- evaluate standardized outcome instruments (FIM, Barthel Index, SF-36, DASH, LEFS, PROMIS), functional assessment scoring…
Pulls active listings, comparable sales, market statistics, and property estimates from Redfin via web research.
Amazon Redshift is NOT PostgreSQL; corrects LLM mistakes; covers SQL, metadata, connectivity/auth, storage, query performance, and operations.
Anchors predictions in historical reality by identifying a class of similar past events and using their statistical frequency as a baseline (outside view) before analyzing…
Use when starting a forecast to establish a statistical baseline (base rate) before analyzing specifics.
Calibrate Blender materials, lighting, camera crop, emission/glow, color management, and aura/HUD styling against supplied original/reference images using measurable color,…
Track and analyze regression statistics, trends, hotspots, and health indicators across test suites
Use when when you have trained a regression model on experimental retention times or similar continuous molecular property predictions and need to quantify its generalization…
Detect performance regressions by comparing benchmarks across versions with latency, throughput, and statistical significance analysis
Use when after generating collision cross section predictions on a validation or test set using a trained graph neural network model, and you need to quantify prediction accuracy…
Build and operate the "Regression Sentinel Design for climate adaptation initiatives" capability for climate adaptation initiatives.
Catalog FDA and EMA regulatory precedents by therapeutic area, including expedited pathway statistics, approval basis, endpoint acceptance, advisory committee outcomes, and…
Build trading systems in the style of Renaissance Technologies, the most successful quantitative hedge fund in history.
Use when you have high-dimensional replicate experiment data (metabolomics, proteomics, or genomics) with multiple biological or technical replicates per sample, and you need to…
Optimize the research agent for rate limit handling, API call efficiency, web search integration fixes, and improved streaming UX with granular progress updates and source…
Use when exhibits are the bottleneck for a Research Policy (RP) manuscript — designing tables and figures (regression tables, patent/bibliometric maps, event-study plots, case…
Use when the causal-identification or measurement strategy is the bottleneck for a The Review of Economics and Statistics (REStat) manuscript — a DID / RD / IV / shift-share…
Use when a The Review of Economics and Statistics (REStat) decision letter (R&R or reject-and-resubmit) has arrived and the manuscript needs a response-to-referees letter and a…
Use when assembling the data-and-code replication package for a The Review of Economics and Statistics (REStat) manuscript under the journal's Data and Code Availability Policy —…
Use when the headline estimate of a The Review of Economics and Statistics (REStat) manuscript needs to survive specification, sample, measurement, and inference choices before…
Use when building or revising the exhibits of a The Review of Economics and Statistics (REStat) manuscript so the main result is legible in one table or figure in AEA/REStat house…
Use when deciding how much theory or structure a The Review of Economics and Statistics (REStat) manuscript should carry — right-sizing a model so it interprets or disciplines the…
Use when deciding whether an applied-economics project fits The Review of Economics and Statistics (REStat) rather than AER / AEJ:Applied / J.
Use when deciding which restat-* sub-skill to invoke next, or when sequencing manuscript work from topic selection through rebuttal for a The Review of Economics and Statistics…
Use when revising the prose of a The Review of Economics and Statistics (REStat) manuscript — especially the abstract and introduction — so the applied question and the estimate…
Assesses whether study results are trustworthy by auditing design integrity, sample structure, statistical handling, bias control, validation chain, and claim discipline.
7 seconds. That's how long a recruiter spends on your resume. CellCog makes every second count — #1 on DeepResearch Bench (Feb 2026) to research your target role, ATS…