Index of the 23 discipline skills (FoR30-FoR52) that mirror the disciplines of the companion ScienceClaw-Eval benchmark: find which discipline skill fits a scientific task (plant panoptic segmentation, protein fitness prediction, hippocampus segmentation,…
Operate ScienceClaw's program-level self-evolution - turn a finished, replay-verified canvas session into a Skill/Operator candidate, gate it on user-registered validation tasks, and leave promotion (and rollback) to the user, with receipts.
Use when segmenting top-down field or UAV RGB images of crops (sugar beet, PhenoBench-style) into soil / crop / weed semantics plus crop-plant and crop-leaf instances (hierarchical panoptic segmentation), from a few labelled images, delivering per-image…
Use when ranking or predicting the fitness effect of single amino-acid substitutions in a protein (deep mutational scanning, ProteinGym-style assays) from labelled variants of the same assay and the wild-type sequence, delivering one score per query variant…
Use when segmenting the hippocampus into anterior and posterior parts in small 3-D T1-weighted brain MRI crops (Medical Segmentation Decathlon Task04) from a set of labelled volumes, delivering one integer label volume per image scored by Dice. Corresponds to…
Use when forecasting day-ahead hourly electricity load of individual buildings (residential and commercial smart-meter data, BuildingsBench-style) from the previous 168 hours and optionally the building's own earlier history, delivering a 24-hour forecast in…
Use when predicting a binary molecular property such as HIV replication inhibition (OGB ogbg-molhiv, MoleculeNet-style activity) from SMILES strings and labelled molecules, delivering one probability-like score per query molecule evaluated by ROC-AUC under a…
Use when forecasting monthly tourism, visitor or other seasonal business and service series (Monash Tourism Monthly, 24-month horizon, period 12) from each series' history, delivering non-negative forecasts per series scored by mean MASE. Corresponds to FoR35…
Use when a task asks to separate stereo music mixtures into four stems (vocals, drums, bass, other) and deliver the estimated stems, optionally with training mixtures plus reference stems, judged by BSSEval-v4 source-to-distortion ratio (SDR, dB), as in…
Use when a task asks for a 24-hour-ahead forecast of a global gridded surface field (2 m temperature on a 64x32 equiangular ERA5 / WeatherBench 2 grid, 6-hourly) from a training record and the four preceding fields of each initialisation, delivered in kelvin…
Use when a task asks to forecast annual country-level economic series several years ahead (for example GDP per capita levels or unemployment rates, horizon 4) for many economies, from a panel of past series and covariate indicators such as growth and…
Use when a task asks to predict whether students answer held-out diagnostic multiple-choice questions correctly, from a large student-by-question correctness matrix and a small per-student budget of adaptively chosen revealed answers (about 10), delivered as…
Use when a task asks for unsupervised anomalous sound detection for one machine type in the first-shot setting (only normal source-domain training clips, no labelled anomalies, unlabeled test clips) and wants one anomaly score per test clip, judged by the…
Use when a task asks for 30-day-ahead probabilistic daily forecasts of dissolved oxygen (mg/L) and water temperature (degC) at freshwater monitoring sites from multi-year daily histories (NEON aquatics, neon4cast ecological forecasting), delivered as a normal…
Use when a task gives hourly ICU records (vitals, labs, demographics, one stay per patient) with sepsis labels and asks for causal hour-by-hour sepsis alarms on new stays, scored by normalized clinical utility (PhysioNet/CinC 2019 early sepsis prediction;…
Use when a task gives noisy OCR text of historical newspapers, periodicals or books (several languages, with metadata and a set of labelled OCR/ground-truth pairs) and asks for corrected transcriptions, one string per unit, scored by character match error…
Use when a task gives a covariate table plus, for each of many simulated observational datasets, a binary treatment vector and an outcome vector, and asks for one average treatment effect on the treated (SATT) per dataset without access to the…
Use when a task gives small culturally specific images with language metadata (Indigenous languages of the Americas) and a few captioned training examples per language, and asks for one caption string in the item's own language per image, scored by mean…
Use when a task gives Python programming problems (a function stub with docstring or a task description, an entry-point name, a few public assert tests) and asks for one complete program per problem that must pass hidden unit tests, scored by execution pass@1…
Use when a task gives a Universal Dependencies treebank (annotated training sentences with upos, head, deprel) and tokenised target sentences, and asks for a dependency tree (head and relation per word) for every target sentence, scored by labeled attachment…
Use when a task asks to locate the clauses of contracts or NDAs (split into candidate spans) that support or contradict fixed natural-language hypotheses, ContractNLI-style: inputs are contract spans, hypotheses and annotated training contracts; the…
Use when a task gives SMT-LIB v2 scripts (quantifier-free nonlinear integer or integer-real arithmetic, QF_NIA / QF_NIRA, SMT-COMP style single-query instances) and asks for the satisfiability verdict of each one (sat, unsat or unknown) as a list in input…
Use when a task gives arguments (conclusion, stance, premise) with a training set labelled for the 20 human-value categories of the ValueEval taxonomy (SemEval-2023 Task 4 / Touche23-ValueEval) and asks for a 0/1 multi-label matrix (arguments by 20 values),…
Use when a task asks to predict a phonon property of inorganic crystals from their structure, for example the frequency of the last peak of the phonon density of states in cm^-1 (Matbench phonons), given structures (lattice, species, fractional coordinates)…
Use when a task gives text transcripts of human behavioural experiments in which every participant response is written as <<KEY>> (Psych-101 / Psych-201 style sessions with a study id and legal response keys) and asks to predict the participant's next choice…
Solve a data-analysis or scientific-computing request as a typed, executable workflow graph on the ScienceClaw canvas, using the scientific tool library and the evolved Skill/Operator program. Use for any task that has input files and a checkable deliverable;…
Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native…
Search and retrieve preprints from arXiv via the Atom API. Use this skill when searching for papers in physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering, or economics by keywords, authors,…
Screen papers for systematic reviews using ASReview active learning. Use when: user has a large set of papers to screen for inclusion/exclusion, wants to prioritize relevant papers, or needs to reduce manual screening workload. NOT for: searching papers (use…
"Astronomical computations via Astropy. Use when: user asks about celestial coordinates, FITS files, or cosmological calculations. NOT for: telescope control or real-time observation planning."
"Bioinformatics operations via Biopython. Use when: user asks about DNA/protein sequences, BLAST, or PDB structures. NOT for: clinical genomics or variant calling pipelines."
Performs biostatistical analyses specialized for clinical and biomedical research including survival analysis, Kaplan-Meier estimation, Cox proportional hazards regression, longitudinal data modeling, and diagnostic test evaluation; trigger when users discuss…
US Census Bureau data via API. Use when: user asks about US demographics, population, housing, or economic data by geography. NOT for: non-US data or real-time statistics.
Query ChEMBL bioactive molecules and drug discovery data. Search compounds by structure/properties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies, for medicinal chemistry.
"Query the ChEMBL REST API for drug-target interactions, bioactivity data, ADMET properties, and approved drug information. Use when the user needs drug mechanism of action, binding affinity data, target information, or pharmacokinetic properties. NOT for…