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…
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…
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…
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,…
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.
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 Never store observatory credentials, FTP, or unpublished target…
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…
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.