AlpacaLabsLLC/skills-for-architects / skills/learn
learn
UnverifiedGuided, hands-on course teaching architects how to use Codex or Claude Code — six short modules, each built around an exercise on a bundled sandbox project (a fictional Brooklyn art museum expansion). Resumable across sessions via PROGRESS.md. Use when the user runs $learn or /as:learn, says they're new to AI-assisted project work, or asks how to learn it.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 3.6 KB |
| SKILL.md | skill md | 23.3 KB |
| host-contract.json | config | 1.5 KB |
| sandbox/art-museum/IMG_4032.txt | markdown | 1.2 KB |
| sandbox/art-museum/RE_ RE_ RE_ quick question.txt | markdown | 1.4 KB |
| sandbox/art-museum/Scan_001.txt | markdown | 1.4 KB |
| sandbox/art-museum/notes final FINAL (2).txt | markdown | 680 B |
| sandbox/art-museum/program_v2_FINAL_final.csv | other | 658 B |
| sandbox/art-museum/site-visit-jun12.txt | markdown | 1.2 KB |
| templates/office-CLAUDE.md | markdown | 2.3 KB |
host-contract.json
View on GitHub{
"path": "skills/learn/SKILL.md",
"responsibility": "Guided, hands-on course teaching architects how to use Codex or Claude Code \u2014 six short modules, each built around an exercise on a bundled sandbox project (a fictional Brooklyn art museum expansion). Resumable across sessions via PROGRESS.md. Use when the user runs $learn or /as:learn, says they're new to AI-assisted project work, or asks how to learn it.",
"inputs": "Supplied task and selected source scope; exact destination only for requested persistence or application work. Load project context only when the task needs project records.",
"owned_records": [
"practice-folder/PROGRESS.md",
"practice-exercise-artifacts"
],
"non_owned_records": [
"PROJECT.md",
"STUDIO.md",
"TASKS.csv",
"TIME.csv",
"proposals/",
"agreement/",
"INVOICES.csv",
"ffe/items-and-schedules",
"product-library.csv",
"epd-library.csv",
"ffe/jobs/input-manifests"
],
"delegation": "inherit-scope-target-permissions-and-evidence",
"modes": [
{
"mode": "answer"
},
{
"mode": "file-read"
},
{
"mode": "file-output",
"when": "Only the requested course progress and exercise files within the chosen practice scope; no project register ownership.",
"required": [
"file.read",
"file.write"
],
"optional": [
"process.run"
]
},
{
"mode": "delegate"
}
],
"execution": {
"model": "harness-native",
"contract": "skills/learn/SKILL.md",
"operations": []
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |