Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g — from…
Manages the project's testable hypotheses — surfacing new ones, refining existing ones, updating status, reviewing the full set, and assessing hypothesis state based on evidence…
Write testable product hypotheses with clear success metrics, baselines, targets, and timeframes. Produces a structured hypothesis statement, supporting evidence, a validation…
Когда не знаешь почему что-то происходит — выдвигает 4-6 конкурирующих объяснений и систематически убивает ложные через kill-тесты и confidence scores.
Structured code debugging through hypothesis formation and falsification planning. Use when diagnosing bugs, unexpected behaviour, or system failures where the root cause is…
Manages hypothesis lifecycle, enforces validation criteria, time budgets, and confidence scoring rules.
Investigate build failures, test errors, runtime crashes, or unexpected behavior through systematic minimal reproduction, multi-hypothesis testing, and evidence-based…
Frame work as falsifiable hypotheses, test the cheapest first, and update on evidence rather than defending the plan.
Identify, structure, and catalog testable hypotheses from pilot signals and strategic inputs. Use when transforming unstructured idea lists or pilot objectives into a for — from…
Identify, structure, and catalog testable hypotheses from pilot signals and strategic inputs. Use when transforming unstructured idea lists or pilot objectives into a for — from…
Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propo — from…
Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propo — from…
Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propo — from…
Generate testable hypotheses. Formulate from observations, design experiments, explore competing explanations, develop predictions, propose mechanisms, for scientific inq — from…
Generate testable hypotheses. Formulate from observations, design experiments, explore competing explanations, develop predictions, propose mechanisms, for scientific inq — from…
Resolve organizational friction and "disagree and commit" scenarios by decomposing high-level mandates into testable assumptions.
Evaluate, propose, or critique a scientific hypothesis or testable claim using the lab's type-aware gating pipeline.
Custom Hypothesis strategy patterns for property-based testing. Activated when designing test data generators or property tests.
Тестируемая гипотеза — We believe / Will result in / We'll know when [metric] reaches [threshold]
Guide selection and interpretation of statistical hypothesis tests. Use when: (1) Choosing appropriate test for research data, (2) Checking assumptions before analysis, (3)…
Property-based testing with Hypothesis for discovering edge cases and validating invariants. Use when implementing comprehensive test coverage, testing complex logic with many…
Take any claim and design + execute a complete research protocol to test it. Apply scientific method automatically: design study, gather data, run analysis, provide verdict with…
Retrieve and update company hypotheses in Primr. Use when the user asks what is already known, wants to validate a claim, or wants to persist a research finding.
Track and manage research hypotheses with confidence levels. Use when the user asks about prior research, wants to validate claims, or queries what is known about a company.
Use when when you have completed DESeq2 differential expression analysis on RNA-seq count data and obtained p-values for each gene, use IHW if you want to improve power to detect…
Comprehensive guide to writing testable product hypotheses that drive learning and prevent building the wrong things
Applies "what if" thinking to explore alternative scenarios, test assumptions, understand causal relationships, and prepare for uncertainty.
Structures responses so the answer or first action comes first, steps are numbered and bounded, and every unfinished task ends with one concrete next step.
Overview of `workflows/catheter_navigation/` (fluorosim DRR, XPBD physics, vasculature digital twin).
Launch the interactive Slang fluoroscopy viewport with XPBD catheter physics. Use when asked to open the viewport, teleop a catheter, or demo fluoro navigation.
Overview of `workflows/agentic/` (IsaacLab-Arena + GR00T/openpi). Use when the user asks what i4h workflow is, what's supported, or where to start.
Use when matching the argument of an ICALP (EATCS) theory paper to its claim — choosing the proof strategy for an upper or lower bound, deciding when supporting computation…
Use when designing or auditing ICASSP experiments across signal-processing modalities — matching the metric to the task law (WER, SI-SDR, PESQ/STOI, EER/minDCF, PSNR/SSIM, BER,…
Use when revising an ICASSP paper into the IEEE two-column four-page house style — leading with the signal-processing contribution and mechanism, naming the task-matched metric on…
Research, drafting, and analysis involving the International Criminal Court (Rome Statute system). Enforces a verification-first methodology — every case-law, decision, f — from…
Use when designing the experimental program for an ICCV paper against the early-March deadline, covering benchmark-drift audits across the two-year gap, baseline fairness in the…
Use when reasoning about ICCV's review pipeline and where authors have leverage, covering the March-to-June OpenReview timeline, the every-author-reviews contract and its 2025…
Use when auditing an ICCV submission in the weeks before the early-March deadline, covering OpenReview registration and profile completeness, the single same-day…
Use when planning or auditing ICCV supplementary material under the same-day paper-plus-supplement deadline, covering what moves out of the 8-page body, parallel production of…
Use when designing or auditing IEEE ICDE experiments for a data-engineering paper: workload realism, tuned baselines, scale curves over single points, throughput and tail-latency…
Use when auditing an IEEE ICDE research-track submission for round choice, Microsoft CMT setup, conflict declarations, the IEEE 12-page format, single-blind requirements,…
Use when preparing IEEE ICDE supplemental material for the CMT submission: what belongs in the 12-page body versus the supplement, the runnable artifact package (README,…
Use when deciding whether a project is a strong IEEE ICDE fit, routing among the three database venues from ICDE's seat (SIGMOD's quarterly rounds vs PVLDB's monthly deadlines vs…
Use when planning an IEEE ICDE project timeline around the two-round-per-edition calendar, choosing between the June and November research deadlines, budgeting for a possible…
Use when designing or auditing the empirical evaluation for an ICDM (IEEE International Conference on Data Mining) paper - mining-task definition, strong and fairly-tuned…
Use when strengthening reproducibility for an ICDM (IEEE International Conference on Data Mining) paper - seeds, configs, compute and data reporting, and an anonymized…
Use when auditing an ICDM (IEEE International Conference on Data Mining) submission for readiness, covering Research-vs-Applied track choice and its anonymity regime, the…
Use when deciding whether a project is a strong ICDM (IEEE International Conference on Data Mining) fit, choosing among its Research, Applied, and Blue Sky tracks, and comparing…
Use when deciding what counts as evidence for an ICDT (International Conference on Database Theory) result — matching-bound complexity analysis as the primary evidence, worked…
Automatically score growth experiments using the ICE framework (Impact × Confidence × Ease). Use when the user creates a new experiment, mentions scoring or prioritization, or…
Use when designing or auditing ICLR experiments, including baselines, ablations, scaling laws, robustness, statistics, benchmarks, human evaluation, and compute reporting.
Use when stress-testing ICML experimental evidence before submission or rebuttal, including strong tuned baselines, mechanism-isolating ablations, seed variance and confidence…
Use when deciding whether a manuscript fits ICML, choosing the main research track versus the ICML Position Papers track or another venue (NeurIPS, ICLR, AISTATS, UAI, COLT,…
Use when designing or auditing the experimental section of an ICRA paper — real-robot versus simulation-only evidence, trial counts and success-rate reporting, task distributions…
Use when drafting an ICSE author response or executing a Major Revision, covering criterion-targeted replies to research-track reviews, the September response window, the…
Use when converting an accepted ICSE research-track paper into its final published form, covering the extra camera-ready page, de-anonymization order, finalizing the Data…
Use when designing or auditing the evaluation of an ICSE research-track paper, covering subject and benchmark selection, baseline fairness, statistical tests and effect sizes as…
Use when building the related-work and positioning sections of an ICSE research-track paper, covering the literature lanes SE reviewers check, searching ACM DL, IEEE Xplore and…
Use when building the verifiability story of an ICSE research-track paper, covering the open-science policy's sharing-by-default expectation, the Data Availability section,…
Use when reasoning about how an ICSE research-track submission is evaluated, covering double-anonymous PC review, the four posted criteria, the Accept / Major Revision / Reject…