learn-in-30-days
Skill1 starsChanged 33 days agoMITView on GitHub
Turn any skill or subject the user wants to learn into a realistic 30-day plan with daily tasks, weekly projects, free-resource types for each step, and weekly self-tests, sized to the hours per day the user actually has. Use when a user asks how to learn a topic, wants a roadmap or study plan, or says teach me X in 30 days or make me a learning plan.
In this repository11 other files it gives its agents.
- assignment-researcherSkill
- client-brief-analyzerSkill
- fyp-project-managerSkill
- interview-grillerSkill
- portfolio-case-studySkill
- pricing-calculatorSkill
- professional-emailSkill
- project-scope-plannerSkill
- proposal-writerSkill
- resume-builderSkill
- study-any-topicSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Put the self-test at the end of each week (questions or a task done without help) and a rest or light day each week.
- Distinctive: line 18
Add the if-you-fall-behind rule: drop the optional tasks marked optional, never the weekly project or test.
- Distinctive: line 22
Never plan more hours than the user stated.
- Distinctive: line 32
If you fall behind - what to drop, what never to drop
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
Learn Anything in 30 Days
When to use this skill
- Learning a new skill for a job, freelancing, or exams
- A roadmap is needed that fits real daily hours
- Previous self-study failed because the plan was unrealistic
Workflow
- Set the contract first: the exact skill, the user current level (true zero, some basics, intermediate), target outcome in one sentence (hold a conversation, build a portfolio project, pass the exam), and real hours per day. Plans are built from these numbers only.
- Divide 30 days into 4 weekly stages: Week 1 Foundations (core concepts, small daily wins), Week 2 Guided Practice (following structured material, replicating examples), Week 3 Independent Practice (original small tasks without tutorials), Week 4 Project and Test (one portfolio-sized output and a timed self-test).
- Each day gets ONE main task completable in the stated hours, with the resource type to use (official docs section, one video lesson, textbook chapter, exercise set) - specific enough to start without deciding anything.
- Put the self-test at the end of each week (questions or a task done without help) and a rest or light day each week. A plan with no rest day is a plan to quit in week 2.
- Add the if-you-fall-behind rule: drop the optional tasks marked optional, never the weekly project or test. Show what Week 1 looks like in full; summarise weeks 2-4 by day themes if the user wants the short version.
- End with the tracking method: a simple daily checkbox list and the weekly question - could I do this week test without help? If no, repeat the week, which is progress, not failure.
Rules - never break these
- Never plan more hours than the user stated. A 1-hour-a-day plan that survives beats a heroic 6-hour plan that dies on day 4.
- Resource types and official sources only unless a specific resource is verified - never invent course names, links, or book titles.
- The target outcome decides the content. Exam plans drill past-paper style questions; portfolio plans build artefacts. Never give both the same plan.
- 30 days creates a foundation and proof of work, not mastery - say this honestly in the plan intro.
Output format
- Your contract - skill, level, target outcome, hours per day
- 4 weekly stages - theme + outcome of each week
- Day-by-day plan - one main task per day, resource type, optional tasks marked
- Weekly self-tests - the exact test for each week
- If you fall behind - what to drop, what never to drop
Example
User: I want to learn Python for freelancing, I know zero, I have 1.5 hours a day, in 30 days I want one small project done.
Good output (excerpt): Week 4 project scoped to the contract: a file-organiser script the user can demo to clients - not build a web app. Day 1 task: install Python and write a program that renames one file; small, finished, motivating. Daily load never exceeds the stated 1.5 hours.
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
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.

