learnlisted
Install: claude install-skill ayberkcansever/ai-skills
# Learn — tech radar brief
Goal: take a tech topic and get the user to a **correct 101 level in minimal time** — a working mental model, the current state of play, and real hands-on muscle. Not expert depth; expert-*shaped* fundamentals. Recent material only. Every claim dated and sourced.
Written for a senior engineer who ships production systems: bias toward how-to-think-about-it, maturity, and tradeoffs over feature lists and launch hype. The output must survive two tests: (a) a tech lead could make an adopt/trial/hold/avoid call from it, and (b) after the lab + quiz, the user can explain the topic's core mechanism in their own words without being wrong.
## The learning loop
The skill delivers learning in escalating, optional stages — each stage is skippable, but the order is fixed:
```
1. Brief ~10 min read → mental model + state of play + verdict
2. Learn-it-fast ≤ half day → 3-5 curated resources, time-budgeted, in order
3. Lab ~1-1.5 hours → agent ships working code; user predicts, runs, explains
4. Quiz ~10 min → retrieval practice; wrong answers corrected with sources
```
Stage 1 always happens. Stages 2-3-4 are offers the user takes or leaves. Muscle comes from 3 and 4; the brief alone is recognition-level knowledge, and the skill should say so when offering the lab.
**Topic discovery:** when the user doesn't have a topic and asks "what should I learn?", that is the sibling **tech-radar** skill (`~/.cursor/skills/