Menu
SkillsMP a collecté 18 skills depuis Yu-Yang-Li/StarWhisper. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 18 skills collectés sur 18.
Compare the published sparse ZTF/ATLAS early-classification benchmark and lint a light-curve table against the varlen 3-30 / 7-class contract. Use for varlen, sparse light curves, XGBoost vs Transformer vs LSTM, seven merged variability classes, or Early…
Langue du texte source : chinois
Evaluate an observing-policy comparison against the StarWhisper-Explore pre-registered bar and return pass/fail per criterion. Use for 决策边界, survey completeness vs transient follow-up, policy A/B comparison, stable negative result, GOAI Explore, or judging…
Langue du texte source : chinois
Validate an NGSS observing configuration, compute the night exposure budget, and lint a target list before anyone touches hardware. Use for observe_config.json, StarWhisper Telescope, NGSS, NINA, 夜计划, moon distance constraints, exposure count/time/wait, how…
Langue du texte source : chinois
Screen SN Clock explosion-age predictions into a defensible young-supernova shortlist. Use for 超新星时钟, explosion epoch, young SN candidates, H3 age quantiles, within-2-days selection, TNS candidate ranking, or reading snclock prediction tables. Computes ages,…
Langue du texte source : chinois
Write, review, and submit astronomy manuscripts for AAS/MNRAS/A&A/PASP and Chinese NSFC astronomy proposals. Use for papers, referee reports, rebuttals, cover letters, and grant text. Do not retrieve literature or audit citation authenticity.
Langue du texte source : chinois
Record astronomy research preferences, catalogs, claim conservatism, and collaboration boundaries. Use when the user asks to remember subfield habits, writing style, or telescope-safety limits. Never store observatory credentials, FTP, or unpublished target…
Langue du texte source : Plusieurs langues
Design observing campaigns, injection-recovery tests, and agent evaluations before collecting or replaying data. Use for night/field blocking, seeded synthetic nights, shadow-mode hardware runs, sample size, and pre-registered thresholds. Do not default to…
Langue du texte source : Plusieurs langues
Search astronomy papers via NASA ADS and arXiv astro-ph, with optional Giiisp OA as a supplement. Use for ADS, bibcode, ApJ/MNRAS/A&A papers, transients, surveys, or StarWhisper literature. Dry-run without ADS_API_TOKEN; never invent papers.
Langue du texte source : Plusieurs langues
Generate astronomy survey, telescope-decision, and mechanism diagrams from paper text. Use for observing-loop figures and system sketches. Do not invent axis ticks, photometry, or English labels that are not in the source.
Langue du texte source : chinois
Check astronomy citations against NASA ADS/arXiv, AAS/MNRAS reference practice, and whether in-text claims are actually supported. Use for .docx/.pdf citation audits, bibcode resolvability, and context-support mismatches. Do not invent references.
Langue du texte source : anglais
Translate astronomy questions into data contracts over light curves, spectra, FITS, alert streams, or telescope decision logs. Use when the user needs inputs, outputs, sample units, splits, leakage checks, and a non-LLM baseline before modeling.
Langue du texte source : anglais
Build evidence-bounded reviews for transients, surveys, telescope agents, and time-domain methods using NASA ADS and arXiv astro-ph. Use when the user needs keyword decomposition, citation tracing, and explicit observation/simulation/log boundaries.
Langue du texte source : Plusieurs langues
Humanize Chinese astronomy papers, proposals, and talks while keeping bibcodes, filters, MJD, and discovery language conservative. Use when the user wants less template tone without changing facts.
Langue du texte source : chinois
Generate evidence-tracked hypotheses for time-domain astronomy, telescope agents, and survey pipelines. Use when the user starts from keywords, a paper set, or ADS/arXiv astro-ph results and needs testable claims with bibcodes or an explicit speculative flag.
Langue du texte source : anglais
Run confirmatory statistics on light-curve, survey, or agent-evaluation tables after the analysis plan is locked. Use for tests, effect sizes, confidence intervals, selection effects, small-count intervals, and multiple testing across candidates.
Langue du texte source : Plusieurs langues
Audit astronomy theses and papers for ADS-valid citations, coordinate/time/photometric-system consistency, survey selection effects, and over-claimed discoveries. Use for checklist-based, evidence-grounded comments on PDF/DOCX manuscripts.
Langue du texte source : anglais
Build astronomy decks for papers, surveys, and telescope-agent talks. Use when the user wants a PPT from a topic, paper, or notes, with published results kept separate from synthetic Explore numbers. Conservative claims only.
Langue du texte source : anglais
Use this skill when the user wants to run the end-to-end all-sky photo pipeline from a raw all-sky image to a replanned observing sequence, using the packaged run_pipeline.py entrypoint in this shared directory.
Langue du texte source : anglais