본문으로 건너뛰기
cccskills
무료GitHub에 공개

lesson-plan

Use when structuring a multi-session learning roadmap with milestones, gates, and pacing calibrated to learner level and goal.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(3)

  • SKILL.md3.5 KB
  • examples.md1.9 KB
  • README.md782 B

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Purpose

Create a coherent learning roadmap that sequences sessions, defines milestones with verifiable gates, and prevents random topic jumping. Gives the learner a clear path from current level to stated goal.

Activation

  • Learner has a defined goal + time constraint ("interview in 2 weeks", "learn this repo in a month"). Multiple sessions planned with non-trivial sequencing. repo-understand produced a curriculum map needing personalization. Learner asks "where do I start and how do I get to X?"
  • Skip if: one-off session with no continuity. Learner needs immediate help on a specific concept/bug. Plan already exists and is current.
  • Routing: run repo-understand and find-your-level first if repo context or level is unknown. Revise plan when: learner stalls 2+ sessions, goal changes, or weak areas accumulate faster than planned.

Inputs

  • Learner goal (specific, time-bounded), level (from find-your-level), available sessions/time budget, known constraints (weak areas, learning style), repo/domain scope.

Plan Structure

Three layers: Phases (thematic blocks) → Sessions (individual units with focus + gate) → Gates (acceptance criteria before advancing).

Workflow

  1. Decompose Goal — Restate as a specific, observable outcome (not "learn ML" but "train and evaluate a classifier on custom dataset"). Identify 3–5 sub-goals.
  2. Check Prerequisites — For each sub-goal: list prerequisites, check which are confirmed, flag gaps as early sessions.
  3. Define Phases — Group sub-goals into 2–4 phases. Each phase has a coherent outcome and takes 2–5 sessions. Order so each phase's output feeds the next.
  4. Sequence Sessions — Break each phase into sessions. Each has: primary topic, skill(s) to use, gate criterion. Max 2 heavy concepts per session.
  5. Set Gates — Measurable acceptance criteria per session: "can explain X mechanism," "passes challenge-generator at intermediate tier," "completes repo exercise." Gates prevent surface-level advancement.
  6. Add Buffers — 1 revision session per 4–5 sessions. Define re-plan triggers: 2 consecutive gate failures → revise plan.
  7. Get Buy-In — Present as a proposal. Ask: "Does this pacing feel right?" Adjust before finalizing.

Rules

  • DO: gates are non-negotiable — don't advance before gate is passed.
  • DO: prerequisite gaps always get sessions before dependent content.
  • DO: include buffer sessions and explicit re-plan triggers.
  • DO: present as proposal with learner input, not a mandate.
  • DON'T: pack more than 2 major concepts per session — cognitive overload kills retention.
  • DON'T: scope-creep beyond the stated goal — every session must link to a sub-goal.
  • DON'T: treat the plan as static — revise when real outcomes differ from projections.

Output

Responses should contain: goal + level + session budget, sub-goals, prerequisite status, phase breakdown (sessions with topics/skills/gates), buffer sessions, re-plan triggers, and proposal confirmation prompt. Format naturally.

Checklist

  • Goal is specific and observable.
  • Every session has an explicit gate.
  • No session has more than 2 major concepts.
  • Buffer sessions and re-plan triggers included.
  • Plan presented as proposal with learner confirmation.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Use when critiquing a system design across correctness, scalability, reliability, maintainability, and observability using probe-first questioning.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

yugash007/edu-agent-skills102026년 5월 19일 업데이트

Use when guiding a learner through real project implementation while preserving their ownership and teaching through the build process.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

yugash007/edu-agent-skills102026년 5월 19일 업데이트

Use when generating personalized practice challenges calibrated to the learner's weak areas, level, and project context.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

yugash007/edu-agent-skills102026년 5월 19일 업데이트

Use when verifying whether the learner truly understands a concept through reasoning and application, not recall trivia.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

yugash007/edu-agent-skills102026년 5월 19일 업데이트

Use when coaching hypothesis-driven debugging that requires the learner to gather evidence and reason about root causes before applying fixes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

yugash007/edu-agent-skills102026년 5월 19일 업데이트

deep-dive

무료

Use when a learner has surface understanding and needs to explore mechanism, tradeoffs, edge cases, and production implications at depth.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

yugash007/edu-agent-skills102026년 5월 19일 업데이트

yugash007의 스킬 모두 보기

이 스킬의 문제 신고