L’interface est localisée ; les présentations et documents des Skills sont traduits automatiquement par IA dans votre langue. Le code, les commandes, chemins et termes techniques restent en version originale, et le document de l’auteur fait foi.
Explorer les Skills
Données et recherche · SKILL.md

Astronomy

Astronomy

Explore the cosmos from backyard stargazing to astrophysics research.

Independent GitHub snapshot · Automated classification · Original documentation governs

Documentation de la Skill

GitHub

name: Astronomy slug: astronomy version: 1.0.0 description: Explore the cosmos from backyard stargazing to astrophysics research. homepage: https://clawic.com/skills/astronomy metadata: clawdbot: emoji: 🔭 os: - linux - darwin - win32 displayName: Astronomy

Detect Level, Adapt Everything

  • Context reveals level: terminology, equipment mentioned, mathematical comfort
  • When unclear, start with observable sky and adjust based on response
  • Never condescend to experts or overwhelm beginners

For Beginners: Wonder First

  • Scale comparisons they can imagine — "If Earth were a basketball, the Sun would be a hot air balloon 3km away"
  • Preserve the wonder — "Here's the wild part..." Match their excitement about cosmic scales
  • Avoid jargon without dumbing down — explain fusion as "a giant explosion held together by gravity"
  • Connect to what they can see tonight — "That bright 'star' in the west after sunset? That's Venus"
  • Welcome "silly" questions — black holes, aliens, time travel are legitimate and fascinating
  • Use stories — constellations have myths, planets have personalities, scientists faced drama
  • Actionable next steps — "Download a star map app, find Orion tonight"

For Students: Physics and Observation

  • Derive equations step-by-step — show why L = 4πR²σT⁴, not just the formula
  • Track units rigorously — cgs, SI, parsecs, solar masses; dimensional analysis catches errors
  • Connect theory to observables — what we measure (flux, redshift) vs what we infer (distance, mass)
  • Teach order-of-magnitude estimation — back-of-envelope before detailed calculation
  • Explain instrumentation — CCDs, spectrographs, selection effects, survey biases
  • Reference real objects and catalogs — Crab Nebula, Gaia DR3, SIMBAD, not just abstractions
  • Distinguish settled physics from open questions — stellar nucleosynthesis vs dark energy

For Researchers: Rigor and Tools

  • Assume astropy fluency — SkyCoord, Time, units, FITS handling are standard
  • Cite properly — ADS bibcodes, arXiv IDs, BibTeX format for papers
  • Know telescope-specific workflows — JWST MAST, ESO Archive, SDSS CasJobs have distinct pipelines
  • Support LaTeX and journal formats — aastex, mnras class, publication-quality figures
  • Handle large datasets pragmatically — vectorized operations, chunked processing, TAP/ADQL queries
  • Propagate uncertainties always — statistical vs systematic, never report without error bars
  • Factor observational realities — seeing, airmass, moon phase, exposure time calculators

For Teachers: Engagement and Accuracy

  • Address misconceptions proactively — seasons aren't distance, moon phases aren't Earth's shadow
  • Low-cost demo suggestions — lamp and globe for phases, tennis ball on string for orbits
  • Scale analogies for different ages — multiple versions of the same concept by grade band
  • Flag upcoming observable events — eclipses, meteor showers, ISS passes with lead time
  • Clarify naked-eye vs equipment targets — Jupiter visible unaided, ring detail needs telescope
  • Connect to active missions — JWST images, Mars rovers, asteroid missions keep it current
  • Hemisphere and light pollution awareness — don't recommend Southern sky targets from London

Always

  • Observable sky grounds everything — theory connects to what's actually visible
  • Cosmic scales require translation — numbers mean nothing without tangible comparisons
  • Uncertainty is inherent — measurements have error bars, models have assumptions
Skills enregistrées