agentleFS
Sign inStart free
liknenSliknenS/language-learning-skills/skills/study-planner/SKILL.md

study-planner

Skill0 starsChanged 24 days agoMITView on GitHub

Study planner for a foreign language - sets a goal (target level and deadline) and agrees a realistic weekly plan - minutes of own speech, quizzes, conversations, lessons - then compares the plan with what was done. Use this skill whenever a language learner asks for a study plan or schedule, names a target level or date ("B2 by June"), asks how much to practise or whether they are on track. Also for "составь план занятий", "склади план навчання", "plan nauki".

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write it down in one sentence and confirm it.

    line 14
  2. Distinctive:

    Weekly targets: Use a few countable things: minutes of own speech, quizzes or review sessions, conversations, lessons.

    line 16
  3. Very specific:

    Start with today() and profile() if not done this session.

    line 25
  4. Very specific:

    Keep the goal and the plan in a file if you can write files (plan.md: goal, weekly targets, a log line per week), otherwise give the …

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Study planner

A plan is a few numbers per week that the learner agrees to and that can be checked.

Steps

  1. Goal. Current level (self-assessed is fine), target level, deadline, what for (work, exam, relocation). Write it down in one sentence and confirm it.
  2. Budget. How many days a week and minutes a day the learner really has. Plan for the bad week, not the good one.
  3. Weekly targets. Use a few countable things: minutes of own speech, quizzes or review sessions, conversations, lessons. Add one focus per week ("past tense", "phrases for the bank").
  4. Check honestly. At the start of each session compare last week's plan with what happened. Behind: cut the plan or move the deadline together with the learner, don't just add more.
  5. Rough pace. Moving one CEFR level usually takes months of regular practice, more at higher levels. Say "about" and avoid exact promises.

If Talkfirst MCP is connected

  • Start with today() and profile() if not done this session; read docs("plan") and docs("pace").
  • Goal: profile_update with level, target_level, deadline, purpose, only when the learner asks (changing the level or the target restarts the pace estimate).
  • Plan: plan() returns this week and past weeks with fact counted by the server (speech_min, quizzes, dialogues, lessons). plan_set(weeks) replaces the plan from the current week on, up to 12 weeks ahead, each week starting on a Monday. Agree the numbers with the learner first.
  • Pace: talk about it only from the pace field of today() / plan() (minutes a week the goal needs, the current average, status such as on_track or behind, estimated dates), never from your own guess.
  • Standing agreements ("explain in English, correct only meaning-changing mistakes") go to notes_set; the next chat reads them with notes().

Without it

Keep the goal and the plan in a file if you can write files (plan.md: goal, weekly targets, a log line per week), otherwise give the learner a short block to paste at the start of the next chat. Ask for the week's numbers yourself at check-in; they are self-reported.

Plan and fact counted by the server, visible in every new chat: connect Talkfirst (free plan, MCP connector for Claude and ChatGPT).

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.

Check your setup, free