Study plan builder
The largest community-driven library of Agent Skills (SKILL.md + scripts/references/examples) for Claude, Codex, Gemini CLI, Cursor and friends.
npx -y skills add JayRHa/AgentSkills --skill study-plan-builderAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Builds a realistic, personalized learning roadmap for a skill or subject — with milestones, curated resource types, active practice, spaced review, and progress checkpoints — fit to the learner's deadline and weekly time budget. Use this skill when the user asks to "make a study plan", "create a learning roadmap", "help me learn X in N weeks", "plan how to study for an exam", "build a curriculum", or wants a structured path to master a topic. Grounded in learning-science principles (spacing, retrieval, interleaving).
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
4.5 KB, as published. Nobody here has run it
Study Plan Builder
Overview
Produce a week-by-week learning plan that someone can actually follow. Work backward from the goal and deadline, sequence topics by dependency, and bake in active practice and spaced review rather than passive reading. Apply the evidence-based methods in references/learning-science.md.
Keywords: study plan, learning roadmap, curriculum, syllabus, exam prep, skill acquisition, spaced repetition, interleaving, milestones, schedule, time budget, deliberate practice.
Workflow
- Define the goal concretely. Turn "learn Python" into an observable outcome ("build and deploy a small Flask API", "pass the PCEP exam"). A measurable goal sets the scope.
- Establish constraints. Capture: deadline, hours/week available, current level, and preferred resource types. If unknown, assume ~5 hrs/week and beginner, and say so.
- Decompose into topics and order them by dependency (fundamentals before applications). Group into milestones — each a meaningful, demonstrable capability.
- Allocate time across the calendar working backward from the deadline; leave ~15% buffer for slippage and review. Don't overschedule.
- Design each week with the mix in
references/learning-science.md: input (read/watch) → active practice (exercises/projects) → retrieval (recall, flashcards, self-quiz). Practice should dominate over passive input. - Schedule spaced review of earlier material at expanding intervals, and interleave related topics rather than blocking one at a time.
- Add checkpoints. Every milestone ends with a concrete deliverable or self-test that proves mastery before moving on.
- Render the plan using
templates/study-plan.md. Include resources (by type, not a rigid single source), weekly goals, practice tasks, and review items. - Add an adjustment rule — what to do if behind (cut scope, not review) or ahead (deepen/project).
Decision Framework
| Situation | Plan choice |
|---|---|
| Hard deadline (exam) | Work backward from date; front-load content, back-load practice tests |
| Open-ended skill | Project-driven milestones; learn just-in-time for each project |
| Very limited time | Ruthless scope cut to the 20% that delivers 80%; daily micro-sessions |
| Building a habit | Short, consistent daily blocks beat rare long ones |
| Prerequisite gaps | Insert a "foundations" milestone before the main track |
Worked Example (excerpt)
Goal: "Comfortable writing SQL queries for analytics in 6 weeks, 5 hrs/week."
- M1 (wk 1–2): Foundations — SELECT, WHERE, ORDER BY, basic functions. Deliverable: answer 20 single-table questions on a sample DB.
- M2 (wk 3–4): Joins & aggregation — JOINs, GROUP BY, HAVING, subqueries. Deliverable: a 10-query report on a 3-table schema. Review: re-test M1 questions (spaced).
- M3 (wk 5): Window functions & CTEs. Deliverable: rewrite 3 subquery reports using window functions.
- M4 (wk 6): Capstone + review. Deliverable: end-to-end analysis from a raw dataset; mixed-topic self-quiz (interleaved).
See templates/study-plan.md for the full structure.
Best Practices
- Goal first, measurable. No plan without a concrete target.
- Practice > passive input. Schedule more doing than reading/watching.
- Space and interleave earlier topics; don't cram or block.
- Checkpoints with deliverables gate progression.
- Build in buffer (~15%) and a rule for falling behind (cut scope, keep review).
- Resource types, not dogma — suggest a book/course/docs/practice mix and let the learner pick.
Common Pitfalls
- Passive plans ("read chapters 1–10") with no practice or retrieval.
- Overscheduling with zero buffer — one bad week derails everything.
- No spaced review, so early material is forgotten by the exam.
- Vague goals that can't tell you when you're done.
- Blocking one topic for weeks instead of interleaving for durable learning.
- Ignoring prerequisites, causing a wall mid-plan.