agentleFS
Starlight-IntelligenceStarlight-Intelligence/starlight-agent-skills/skills/coding/cosmic-code-lab/SKILL.md

cosmic-code-lab

Skill1 starsChanged 4 months agoMITView on GitHub

Generate a runnable, space-themed coding lab — a problem statement, starter code, hidden tests, and a worked solution — in Python or JavaScript. Use when creating coding exercises, a 'code lab', an interactive tutorial, or a space/astronomy programming challenge.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Cosmic Code Lab

A learning objective → a self-contained, auto-checkable coding lab with a space-science backdrop.

Purpose

Space data makes great programming practice (orbital math, image stats, light travel time, catalog parsing). This skill produces a complete lab — a clear problem, runnable starter code, a hidden test suite, and a reference solution — so an educator or platform can drop it into a course without writing the scaffolding by hand.

When it fires

  • Keyword triggers: code lab, coding challenge, exercise, kata, tutorial, cosmic code
  • File triggers: labs/**, *.lab.md, test_*.py, *.test.js
  • Command triggers: /cosmic-code-lab

Inputs

InputRequiredNotes
objectiveyesThe concept/skill to teach (e.g. "parse a star catalog").
languagenopython (default) or javascript.
levelnointro, intermediate (default), advanced.

Workflow

  1. Frame the problem — a concrete, space-flavored task that isolates the objective. State inputs, outputs, and constraints precisely. ✅ Check: a competent student could implement it from the statement alone.
  2. Write starter code — minimal scaffold with a clearly marked TODO and a stable function signature.
  3. Write hidden tests — a runnable suite (pytest / a tiny JS harness) covering the happy path, an edge case, and an error case. Tests must pass on the solution and fail on the empty starter.
  4. Write the reference solution — clean, idiomatic, commented at decision points.
  5. Add the science note — 2–3 lines on the real astronomy behind the problem, factually correct.
  6. Self-verify — confirm the solution passes the tests and the starter does not.

Output contract

{
  "title": "string",
  "language": "python | javascript",
  "problem_statement": "string",
  "starter_code": "string",
  "tests": "string — runnable test source",
  "solution": "string",
  "science_note": "string"
}

Tools & MCP

  • Tools: Write (lab files), Bash (run the tests to self-verify).
  • MCP dependencies: none required.

Quality bar

  • Solution passes the tests; empty starter fails them.
  • Problem statement is implementable from text alone.
  • Tests cover happy path + at least one edge + one error case.
  • Science note is factually correct.

Example

See examples/example-01.md.


Built on SIP — Starlight Intelligence Protocol Substrate: starlightintelligence.org/protocol v1.1.0 Layers used: [file-contract, attestation, sovereignty] Vertical: starlight-agent-skills · portable capability layer

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.