language-learning
/language-learning
Prowadzi osobę uczącą się języka planem pod poziom CEFR, opartym na zrozumiałym wejściu, powtórkach rozłożonych w czasie i wczesnej praktyce mówienia, z minimum dziennym, szablonem sesji i tygodniowym grafikiem.
- Autor
- SkillMedev ↗
- Repozytorium
- skills ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 13.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 1
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 13.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Prowadzi osobę uczącą się języka planem pod poziom CEFR, opartym na zrozumiałym wejściu, powtórkach rozłożonych w czasie i wczesnej praktyce mówienia, z minimum dziennym, szablonem sesji i tygodniowym grafikiem.
Wyzwalacze z opisu
Oryginalny opis (EN)
Coaches a language learner with a CEFR-targeted plan built on comprehensible input, spaced repetition, and early speaking practice, including daily minimums, a session template, and a weekly schedule. Use when someone says "help me learn Spanish", "I keep forgetting vocabulary", "how do I get from A2 to B1", or "design my daily language routine". Do NOT use for general exam or academic study techniques - use study-system instead.
Jak działa
- Inputs to collect
- Operating procedure
- Worked artifact: weekly schedule (A2 Spanish, 30 min/day, conversational B1 goal)
- Deliverable
- Do NOT
- Quality bar
Podgląd SKILL.md
--- name: language-learning description: Coaches a language learner with a CEFR-targeted plan built on comprehensible input, spaced repetition, and early speaking practice, including daily minimums, a session template, and a weekly schedule. Use when someone says "help me learn Spanish", "I keep forgetting vocabulary", "how do I get from A2 to B1", or "design my daily language routine". Do NOT use for general exam or academic study techniques - use study-system instead. metadata: title: "Language Learning" --- # Language Learning Languages are acquired through massive comprehensible input - material just above the learner's current level - plus consistent retrieval, not through grammar study alone. The costly failure this skill prevents is the intermediate plateau built from wrong-level habits: content so hard it burns motivation, flashcard decks that grow faster than they can be reviewed, and speaking postponed "until ready," which is a day that never arrives on its own. ## Inputs to collect 1. Target language. No default. 2. Current level on the CEFR scale (A1 beginner → C2 mastery). If unknown, estimate from a 2-minute probe - ask the learner to describe their day in the target language - and label the estimate a guess. 3. Goal: travel, conversation, work, or exam, plus the target CEFR level. Default: conversational B1. 4. Time budget per day. Default: 30 minutes. Below 20 minutes daily, reset expectations before planning (see thresholds). 5. Speaking access: tutor, exchange partner, or neither. Shapes Step 4. ## Operating procedure ### Step 1: Set the level target and honest timeline Anchor expectations with real hour counts: each CEFR level jump takes roughly 100-200 hours of engaged study at the lower levels (A1→A2, A2→B1), more at B2 and above, and distant languages (for an English speaker: Japanese, Arabic, Mandarin) take 2-4x the hours of close ones (Spanish, French). At 30 minutes daily, A2→B1 is a 9-18 month project, not a summer. State this up front; unstated fantasy timelines are the top cause of quitting at month two. ### Step 2: Select input at 80-90% comprehension Choose reading and listening material where the learner understands roughly 80-90% without a dictionary - enough context to infer the rest. Below 80% comprehension, input stops being acquirable and becomes decoding, which kills the habit; at 98-100%, nothing new is being acquired. Practical calibration: if the learner must look up more than 2-3 words per sentence, the material is too hard - step down (graded readers, learner podcasts, children's content) without shame; level of material is a tool, not a rank. Translate sparingly; prefer inferring from context. ### Step 3: Run spaced repetition within a hard cap - Prioritize high-frequency vocabulary first: the top 1,000 words of most languages cover roughly 80% of everyday speech. Frequency lists beat thematic lists (colors, animals) for time-to-conversation. - Add 10-20 new cards per day maximum. Every new card creates future reviews; beyond 20/day, review debt compounds until the learner faces 300 dues and quits. - If daily reviews exceed about 30% of the total time budget, stop adding new cards until reviews shrink. - Prefer sentence cards over isolated words - words are recalled the way they were encoded, and conversation needs them in context. ### Step 4: Apply the speaking-early rule Produce output from week one, even imperfectly - self-talk, shadowing audio, writing three sentences about the day. By A2, add live conversation at least 2 sessions per week (tutor or exchange partner, 25-30 minutes each). Speaking is a distinct skill that input alone does not build, and the longer it is postponed the higher the anxiety wall grows. Correct errors gently: restate the natural form, have the learner repeat it once, and move on - drilling one error for five minutes trades flow for fear. ### Step 5: Shape every session the same way For a 30-minute session: 5 minutes reviewing due cards (retrieval first, while fresh); 15 minutes of new comprehensible input featuring a couple of target structures; 7 minutes of active production - prompt the learner to build sentences with today's material, correcting kindly; 3 minutes capturing 3-5 new items into the review deck. Scale segments proportionally for longer sessions. ### Step 6: Protect the streak Daily small reps beat rare long sessions - 20-30 minutes every day outperforms a 3-hour Saturday, because spaced exposure is the mechanism, not total hours in one sitting. The floor on a bad day is 5 minutes of reviews; keeping the chain alive matters more than any single session. Use the target language for instructions and chat as much as the learner's level allows. ## Worked artifact: weekly schedule (A2 Spanish, 30 min/day, conversational B1 goal) ``` Mon 5' Anki reviews | 15' learner podcast ep (listen 2x) | 7' retell episode aloud | 3' capture 4 cards Tue 5' reviews | 15' graded reader chapter | 7' write 5 sentences using new verbs | 3' capture Wed 5' reviews | 25' TUTOR SESSION (conversation; tutor notes 3 recurring errors) Thu 5' reviews | 15' re-read Tue chapter aloud (shadow pacing) | 7' self-talk: describe your day | 3' capture Fri 5' reviews | 15' podcast (new ep) | 7' summarize it in 4 spoken sentences | 3' capture Sat 5' reviews | 25' EXCHANGE PARTNER (12' Spanish / 12' English swap) Sun 10' reviews only (rest day floor) - weekly check: comprehension still ~85%? review debt under 10 min? New cards: 10-15/day from encountered material, never from random lists. ``` ## Deliverable Produce a learning plan containing: current and target CEFR level with an honest hour-based timeline, 2-3 named input sources calibrated to 80-90% comprehension, spaced-repetition settings (new-card cap, frequency-first policy, sentence-card rule), a speaking schedule meeting the week-one output rule and the 2x/week conversation minimum from A2, the daily session template, and the filled weekly schedule. ## Do NOT - Do not assign native-speed content to an A1-A2 learner because it is "authentic" - below 80% comprehension it teaches frustration, not language. - Do not let new cards outrun reviews; a 300-card backlog ends more language journeys than any grammar point. - Do not postpone speaking until "ready" - readiness is produced by speaking, not a precondition for it. - Do not spend the bulk of study time on explicit grammar rules; grammar explains what input has already made familiar, a few minutes at a time. - Do not plan around motivation peaks. Plan the minimum-viable daily session, and let good days be a bonus. ## Quality bar - The plan states hours-to-goal arithmetic that matches the daily time budget - no silent fantasy timelines. - Input sources are named and level-checked, not "watch shows in the language." - New-card cap and review-debt rule are explicit numbers. - Speaking appears in week one, and at least twice weekly from A2. - A bad-day floor (5 minutes of reviews) is written into the plan.
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · SkillMedev/skills | 100 | MIT |
| aj-geddes/unicorn-team | 100 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki a06aadfb98bf (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100fluent-setup
Prowadzi jednorazowy onboarding tworzący profil nauki języka: imię, języki, poziom CEFR, termin, minuty dziennie i cele; obsługuje też aktualizacje i reset profilu. - 100language-tutor
Działa jak spersonalizowany korepetytor języka obcego: ocenia poziom, prowadzi stopniowaną rozmowę, uczy słownictwa i gramatyki w kontekście, delikatnie poprawia błędy i buduje plan powtórek do celu. - 100study-system
Zamienia sylabus lub listę tematów w plan nauki: fiszki z rosnącymi odstępami, aktywne przypominanie, technika Feynmana, tygodniowe sesje z przeplotem i dziennik błędów. - 100study-plan
Buduje lub aktualizuje długoterminowy plan przygotowania do egzaminu prawniczego bar, z fazami, wagą przedmiotów według słabych stron i dziennym harmonogramem opartym na historii sesji. - 100deliberate-practice-spaced-repetition-code
Pomaga utrwalać algorytmy i interfejsy API metodą powtórek rozłożonych w czasie, na przykład w Anki. - 100study-planner
Układa plan nauki oparty na rozłożonych sesjach i samosprawdzaniu, zamiast na zakuwaniu i wielokrotnym czytaniu.