Menu
SkillsMP has collected 34 skills from tangxiangru/AutoR. Open a skill to review its source and details.
Showing 34 of 34 collected skills.
Use when writing results and discussion, and when a task or a reviewer asks why an effect happens rather than whether it does. Covers the difference between reporting an effect and accounting for it, and what a mechanism claim needs behind it.
Use when the supplied data looks synthetic, degraded, incomplete or wrong, and whenever you are tempted to reframe the study around what you found about the inputs, the harness or the evaluation. Covers what to do with a real data problem without losing the…
Use when planning figures, at study design and again before writing. Covers the figures a paper in this field is expected to contain, why an original figure does not substitute for a standard one, and how to decide what to draw first.
Use when deciding how to aggregate results, at analysis and figure planning. Covers why a pooled number hides the result, which strata a study is expected to report, and when an aggregate is the right answer.
Use when the research task is in astronomy — observational astronomy, surveys, photometry and astrophysical inference — at study design, analysis or writing. Astronomy: the error budget and fit bookkeeping are the audit trail
Use when the research task is in astronomy — observational astronomy, surveys, photometry and astrophysical inference — at study design, analysis or writing. Astronomy: the figure is the unit of result, and nothing is reported pooled
Use when the research task is in chemistry — molecular simulation, docking, reaction energetics and chemical ML — at study design, analysis or writing. Anchor to the incumbent program, report in the canonical unit, convert error into a threshold success rate
Use when the research task is in chemistry — molecular simulation, docking, reaction energetics and chemical ML — at study design, analysis or writing. Print the named-entity ranked list and the property-versus-coordinate curve -- chemistry's two…
Use at study design and again before writing, to check that every deliverable the task statement names has been produced. Covers how to enumerate what was asked for, why partial coverage scores worse than it feels, and what to do when a named deliverable is…
Use when the research task is in earth — weather, climate, hydrology and geoscience data analysis — at study design, analysis or writing. Earth: the supplied archive is an input, never the comparison set
Use when the research task is in earth — weather, climate, hydrology and geoscience data analysis — at study design, analysis or writing. Earth: report the stratified lattice, and show the field it came from
Use when the research task is in energy — batteries, electrochemistry, energy-system modelling and identification — at study design, analysis or writing. Run the default recipe with its conventional diagnostics, and give each claim its own plain panel
Use when the research task is in energy — batteries, electrochemistry, energy-system modelling and identification — at study design, analysis or writing. Counterfactual pair, nested closure, native resolution: the accounting an energy study is graded on
Use whenever a number, a comparison or a claim is about to enter a stage summary or the report — at analysis and writing, and any time you are tempted to state a value you have not computed in this run. Covers where a number must come from, what to do when…
Use when the research task is in information — machine learning, retrieval, multimodal and agent evaluation — at study design, analysis or writing. Show every stage's intermediate object and re-run the demos on the original's own inputs
Use when the research task is in information — machine learning, retrieval, multimodal and agent evaluation — at study design, analysis or writing. Reproduce the whole (variant x backbone x dataset x metric) grid, reduced-N where you must
Use when the research task is in life — structural biology, protein/ligand modelling, sequence and assay work — at study design, analysis or writing. A life-science method result is a head-to-head, a cost table, and an orthogonal truth set
Use when the research task is in life — structural biology, protein/ligand modelling, sequence and assay work — at study design, analysis or writing. Fill every slot of the life-science results skeleton, including the parts you cannot compute
Use when the research task is in material — atomistic simulation, interatomic potentials and materials property prediction — at study design, analysis or writing. Run the protocol as specified as the foreground result, and leave every stage's default…
Use when the research task is in material — atomistic simulation, interatomic potentials and materials property prediction — at study design, analysis or writing. Extract the landmark scalar, report it in the property's physical unit, and anchor it to a…
Use when the research task is in math — optimisation, algorithms, solvers and formal or symbolic reasoning — at study design, analysis or writing. Draw the field's plain two-curve figure against the algorithm's own cost counter, before any richer diagnostic
Use when the research task is in math — optimisation, algorithms, solvers and formal or symbolic reasoning — at study design, analysis or writing. Run every named baseline as a real arm at equal effort, and sweep the knob you claim credit for
Use when the research task is in neuroscience — neural recording, decoding and brain-model comparison — at study design, analysis or writing. Two-sided comparator ladder, the negative-control representation panel, and per-unit predictions
Use when the research task is in neuroscience — neural recording, decoding and brain-model comparison — at study design, analysis or writing. Report per-group and per-class detection metrics, and sweep the modality's own degradations
Use when the research task is in physics — condensed matter, many-body theory, simulation and physical modelling — at study design, analysis or writing. Physics: exclude a named model, and treat the fit protocol as part of the result
Use when the research task is in physics — condensed matter, many-body theory, simulation and physical modelling — at study design, analysis or writing. Physics: measure it twice, propagate it, and generate it
Use when a run is finished and the report is written, after the report is written, to record one reusable lesson for the next run in this field. Covers what counts as a lesson worth passing on, what must never be passed on, and how to write it.
Use when the task is to reproduce, replicate or re-implement a published study, at design time and when reporting results. Covers what a reproduction must report, how to compare against the source study's numbers, and why the reproduction comes before any…
Use when adding, verifying or cleaning citations and BibTeX entries in Stage 07 (Writing), when a reference cannot be resolved cleanly from DBLP or CrossRef, when checking that a cited paper actually supports the claim attributed to it, or when filling…
Use when a LaTeX build fails or produces a broken PDF in Stage 07 (Writing) — undefined control sequences, missing style packages, unresolved citations or references, float placement blowing the page budget, or a build_log.txt full of errors you need to…
Use when drafting, structuring or revising the manuscript or report in Stage 07 (Writing) — shaping the contribution into one story, writing the abstract and introduction, fixing prose that reads generic or templated, ordering sentences for clarity, or…
Use in Stage 08 (Dissemination) when assembling the release or submission bundle — auditing whether the run's code, data, results and figures are actually reproducible by someone else, writing the readiness checklist and threats-to-validity notes, or deciding…
Use when turning measured results into a table or figure for the paper — building a LaTeX or markdown results table from workspace/results/*.json, deciding what uncertainty to report, choosing which baselines and ablations belong in the main table, or writing…
Use when the target venue's submission requirements matter — checking a draft against NeurIPS, ICML or ICLR expectations, deciding which required sections (checklist, broader impact, reproducibility, LLM disclosure) the paper needs, or running the Stage 08…