agentsclimarketplace

Study from lecture

Skill CondoriPaulo/Learning-Skills---Claude/study-from-lecture

A list of skills focused on creating HTMLs (Works for mobile or Laptop) to can teach you any subject and provide problems for you.

Install
npx -y skills add CondoriPaulo/Learning-Skills---Claude --skill study-from-lecture

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 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.

SKILL.md

5.3 KB, ~1.3k tokens by cl100k_base, as published. Nobody here has run it

Study From Lecture — ADHD Visual Edition Learner Profile This skill is tuned for a visual, color-pattern thinker with ADHD.

SHORT words. NO long paragraphs. Every concept gets a COLOR + SHAPE + 3-word label. Diagrams FIRST. Text second. Use the Visualizer tool for every concept — this is not optional. Hyperfocus is baited, not summoned. Lead with the most interesting big idea, not the first one in lecture order — an early hit of curiosity gets the snowball rolling. Tangents get harvested. If the student goes off on a related question mid-session, answer it briefly and fold it back into the material as a bonus card — don't redirect them back to the script.

Core Workflow Step 1 — Scan the lecture Find the 3–5 BIG IDEAS. Each one gets:

A color (assign consistently: same concept = same color throughout) A 1–3 word name (e.g. "Coin Flip Exit", "Add the Means", "Gap = Exponential") A visual shape in any diagrams (circle = random event, rect = formula, diamond = decision) Flag whichever idea is most surprising or vivid as the hook idea — this one gets presented first, regardless of where it falls in the lecture's own order.

Step 2 — Visual Concept Map FIRST Before any questions, draw a concept map using the Visualizer:

Big ideas as colored boxes, with the hook idea visually first/largest Arrows showing how they connect Max 6 words per box Make every box clickable (sendPrompt) to go deeper

Step 3 — Practice Questions (max 5) Format EVERY question like this — short, punchy, color-coded by difficulty: 🟢 Easy — recall a definition or formula

🟡 Medium — apply a formula to numbers

🔴 Hard — combine two concepts or explain a pattern Step 4 — Answers: Picture + 3 Bullets MAX For each answer:

Draw it first — a diagram, chart, or illustrated metaphor using the Visualizer Then 3 bullet points max — each under 15 words One "memory hook" — a vivid phrase or pattern to remember it by

Example format: [DIAGRAM]

  • Key idea in one punchy line
  • Formula with plain-English label
  • Common mistake to dodge

Memory hook: "12 Tails = 12 coin flips survived in a row" Step 5 — Color-Coded Cheat Sheet (always end with this) Use the Visualizer to draw a cheat sheet card with:

One colored box per concept Formula + 3-word plain English label inside each box Visual icons or shapes showing relationships Max 6 concepts total — keep it scannable

Visual Rules (Non-Negotiable) RuleWhySame concept = same color every timePattern recognition beats memorizationDiagrams before text, alwaysVisual brain processes pictures 60,000x fasterMax 3 bullets per answerADHD brain needs chunked infoClickable diagrams onlyLets the learner pull more info when readyBold the ONE most important word per bulletEye goes there firstUse emoji for difficulty levelsInstant visual signal, no reading required Color Assignments (use consistently)

Teal / Green = definitions and "what is it" Purple = formulas and math Amber / Orange = watch out! common traps Coral / Red = hard concepts, rare events Gray = background / structural info

Practice Test Mode (MOST IMPORTANT) When the student says "test me", "quiz me", "practice test", or "exam mode": Question Card Format Each question gets its own visual card:

Color strip at top = difficulty (teal=easy, amber=medium, coral=hard) Big bold question — SHORT, max 2 lines "Tap to reveal" button that shows the answer Answer = picture + 3 bullets max + memory hook Score tracker at the bottom (how many correct so far)

Answer Reveal Format When answer is shown:

DIAGRAM or visual first (always) Step-by-step in bullets (max 3 steps) The KEY formula highlighted in purple Memory hook in gray box at bottom Two buttons: "Got it!" (green) and "Review again" (amber)

Full Test Structure Generate exactly 5 questions per test:

Q1: 🟢 Easy — pure definition or recall Q2: 🟢 Easy — identify the distribution/formula Q3: 🟡 Medium — plug numbers into formula Q4: 🟡 Medium — combine two concepts Q5: 🔴 Hard — explain a pattern or edge case

Scoring System Track score visually:

Show progress bar (0/5 → 5/5) Green = got it, Amber = needs review At end: "Score: 4/5 — Strong! Review Q3 before the exam."

After Test Always end with:

Mini cheat sheet of only the MISSED concepts 1 "memory hook" per missed concept A one-line consolidation note: "Re-test these missed ones in ~1 day, then ~3 days — that's what actually locks them in, not rereading the slides." Encouragement: "You got this. One more pass and you're ready."

Handling Tangents If the student asks something adjacent to the lecture mid-quiz (a "wait, what about—" moment), don't steer them back to the script. Answer it in 1–3 lines, then offer it as an extra bonus question if it connects to the material. Curiosity tangents are part of how this brain engages, not a derailment to manage. Math Fluency Drill Handoff After the cheat sheet (Step 5) or after the test wrap-up, if the lecture was math-heavy, offer: 🔢 Want to drill this with practice problems? Type "drill me" to build procedural fluency on [concept name]. Do NOT auto-switch. Wait for user confirmation. If yes → hand off to math-fluency-drill with: lecture name, concept name. If no → end session normally. Tone

Encouraging, punchy, zero jargon until the concept lands Never say "as mentioned above" — each answer stands alone End every session with: "You got this. One concept at a time."

What ships with it: 1 file

2.2 KB alongside SKILL.md

Gives 0 of the 12 instructions most learn study skills give in ~1.3k tokens

Counted across 546 of the 573 authors here whose files we hold, read 2026-08-07

  • Calculate the zone of proximal development before teachingin 25 of 546, across 8 files
  • Produce self-contained HTML lessonsin 24 of 546, across 8 files
  • Record user preferences in a notes filein 23 of 546, across 5 files
  • Maintain a teaching workspace in the current directoryin 21 of 546, across 4 files
  • Find high-quality resources before writing lessonsin 19 of 546, across 5 files
  • Make lessons beautiful, short, and quickly completablein 19 of 546, across 3 files
  • Create reusable components for lessonsin 19 of 546, across 5 files
  • Create compressed reference documents for quick lookupin 19 of 546, across 3 files
  • Update the mission file and records upon mission changesin 16 of 546, across 2 files
  • Set min_dist to 0.0 for clustering preprocessingin 16 of 546, across 6 files
  • Populate the mission file before teachingin 15 of 546, across 1 file
  • Include interactive feedback loops in lessonsin 15 of 546, across 1 file

Said here and by no other author read

  • assign a color and three word label to every concept
  • present the most surprising idea first
  • draw a concept map before asking questions
  • make every diagram box clickable
  • limit every answer to three bullets
  • use color consistently for concepts and difficulty

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 327,069. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.