Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/szewowsky/learn-skill/learnnpx skills add Szewowsky/learn-skill --skill learngit clone --depth 1 https://github.com/Szewowsky/learn-skillWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00125 | $0.02289 |
| Opus 5 | $0.00063 | $0.01144 |
| Sonnet 5 | $0.00025 | $0.00458 |
| Haiku 4.5 | $0.00013 | $0.00229 |
Grade A, and why
learn scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Learn — YouTube → NotebookLM → Plan nauki → Questy
Dlaczego ten skill istnieje
Nauka z YouTube to chaos — 50 filmów, zero struktury, nie wiadomo od czego zacząć. Ten skill zamienia ten chaos w grę: szuka filmów, wrzuca do NotebookLM, generuje plan nauki, a potem rozbija go na questy z achievementami i checkboxami. Na końcu feedback loop sprawdza czy faktycznie rozumiesz temat (quiz + Feynman probe), nie tylko czy obejrzałeś filmik.
Wymagania
yt-dlp— szukanie filmów na YouTube (brew install yt-dlp)notebooklmCLI — interakcja z Google NotebookLM (pipx install "notebooklm-py[browser]")- Jednorazowa autoryzacja:
notebooklm login(otwiera przeglądarkę → Google login) - Sprawdzenie auth:
notebooklm auth check
Flow
Krok 0: Konfiguracja output
Sprawdź zmienną środowiskową LEARN_OUTPUT_DIR. Jeśli ustawiona — użyj jej jako katalogu wyjściowego.
Fallback: ./learn-output/ w katalogu projektu.
Utwórz katalog jeśli nie istnieje.
Krok 1: Szukaj filmów na YouTube
Uruchom skrypt bundlowany w skillu:
python3 scripts/youtube_search.py --topic "[TEMAT]" --max-results 10
Skrypt filtruje po: min 1000 views, min 5 min, sortuje po popularności.
WAŻNE: Bash output może być zwinięty w UI — user go nie widzi! Przepisz wyniki jako sformatowaną tabelę markdown w odpowiedzi do usera. Kolumny: #, Tytuł, Views, Czas, Kanał. Zapytaj które filmy dodać — np. "1,2,5" lub "all".
Krok 2: Nowy notebook czy istniejący?
Zapytaj:
- Nowy — stwórz notebook o nazwie tematu
- Istniejący — pokaż listę
Dla nowego:
notebooklm create "[TEMAT]"
Zwraca notebook_id. Ustaw jako aktywny:
notebooklm use [NOTEBOOK_ID]
Dla istniejącego:
notebooklm list
notebooklm use [NOTEBOOK_ID]
Krok 3: Dodaj filmy jako źródła
Dodawaj po jednym z 3-sekundowym delay (rate limiting Google):
notebooklm source add "https://youtube.com/watch?v=VIDEO_ID_1"
sleep 3
notebooklm source add "https://youtube.com/watch?v=VIDEO_ID_2"
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 235 lines · 125 tokens per session scan A 77a747145d2c
learn is a skill published in the GitHub repository Szewowsky/learn-skill (2 stars, last pushed 5mo ago), licensed MIT. It adds 125 tokens to every session and 2,289 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
ljg-learn
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
pedagogy-review
Holistic pedagogical review of a lecture deck (.qmd or .tex). Checks narrative arc, prerequisite assumptions, worked examples, notation clarity, and deck-level pacing. Use when user says "pedagogy review", "does this teach well?", "is the flow right?", "will students follow?", "review the narrative", or before…
night-market-collective-memory
Search and record project memory (Discussions, journal, ADRs). Use before re-investigating anything. Do not use for settled battles; see failure-archaeology.