Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Turn a research paper into teaching materials — a lecture outline, the 3-5 results worth presenting (with intuition), a slide skeleton ready for `/create-lecture`, discussion questions, and a problem-set brief. Reads the paper end-to-end and pitches to a stated audience level. Use when user says "turn this paper into a lecture", "teach from this paper", "build slides from this PDF", "make teaching materials from X", "I'm presenting this paper to my class".
.claude/skills/pedrohcgs-teach-from-paper/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 81% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 464% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 565% | 0% |
| case-08 | ✓→✗ | ▼ Worse | 101% | 0% |
Convert one research paper into a ready-to-build teaching package: a lecture outline, a shortlist of teachable results with the intuition spelled out, a slide skeleton, discussion questions, and an exercise brief. The deliverable is an outline and a brief — not a finished deck; the slide skeleton is shaped to hand straight to /create-lecture, and the exercise brief to /scaffold-exercises.
.tex, .md) and a slot to teach it — a lecture, a reading group, a job-market practice talk./create-lecture to do the drafting.Not for: literature surveys across many papers (use /lit-review); refereeing the paper's correctness (use /review-paper); drafting the actual Beamer slides (use /create-lecture).
$0 — path to the paper.| Format | How to read it | | --- | --- | | .tex, .qmd, .md, .txt | Read directly with the Read tool. | | .pdf | TMP=$(mktemp -t paper).txt && pdftotext "$0" "$TMP" (poppler-utils), then Read/Grep "$TMP". |
If extraction fails or the tool is missing, ask the user for a plain-text version and stop. The full paper goes in the context window (1M) — read it end-to-end before extracting; do not skim the abstract and guess.
Read the paper start to finish. Then resolve the audience level and time budget — from --level / --minutes if given, otherwise ask once. Echo a Pre-Flight Report before extracting:
markdown## Pre-Flight Report **Paper:** [title, authors, year] **One-line thesis:** [the paper's central claim in your words] **Audience level:** undergrad | phd | seminar (drives notation depth + which proofs survive) **Time budget:** N minutes (~N/2 slides) **Prerequisites assumed:** [concepts students must already have] **Running example candidate:** [the paper's application that can thread the lecture]
Get a nod on level + thesis, then proceed. Level governs everything downstream: undergrad keeps intuition and drops proofs; phd keeps the identifying assumptions and one key derivation; seminar foregrounds the contribution-vs-literature framing.
Produce a motivation → setup → key result → method → takeaways arc, then a slide skeleton matching the time budget (~2 min/slide). Each skeleton entry is a title + one-line content note + figure/diagram placeholder — enough for /create-lecture to draft from, no prose. Honor the project's pedagogy invariants in shape: motivation before formalism, a worked example near each definition, a transition slide at each act break.
/scaffold-exercises, which fleshes out problems, data, and answer keys. Skip if --no-exercises.Write to quality_reports/teach_from_paper_[sanitized-title].md:
markdown# Teaching Package: [Paper Title] **Audience:** [level] · **Budget:** [N min] · **Date:** [YYYY-MM-DD] ## 1. Lecture Outline Motivation → Setup → Key Result → Method → Takeaways (one line each) ## 2. Results Worth Presenting ### R1 — [name] - **Statement:** … · **Intuition:** … · **Breaks when:** … [R2..R5] ## 3. Slide Skeleton (→ /create-lecture) | # | Title | Content note | Figure/diagram | ## 4. Discussion Questions 1. [comprehension] … 5. [critique] … ## 5. Exercise Brief (→ /scaffold-exercises) - **E1:** [prompt] — drills [skill] — answer shape: [form]
/create-lecture [Topic]. Exercise brief ready — run /scaffold-exercises."--level — undergrad | phd | seminar. Sets notation depth, which proofs survive, and question difficulty. Asked interactively if omitted.--minutes — target lecture length; the slide count is roughly --minutes/2.--no-exercises — skip Phase 3's exercise brief (keep discussion questions)./create-lecture — consumes the Phase 2 slide skeleton to draft the actual Beamer deck. See .claude/skills/create-lecture/SKILL.md./review-paper — referee the paper's correctness before teaching it if you're unsure the result holds. See .claude/skills/review-paper/SKILL.md./lit-review — for situating the paper among many, rather than teaching one deeply. See .claude/skills/lit-review/SKILL.md./scaffold-exercises (a downstream skill that fleshes out problem sets); this skill stops at the brief./create-lecture. The slide skeleton is an outline, not Beamer./scaffold-exercises./review-paper if the result's validity is in doubt.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-13 | fail→pass | 10,334 | 4,310 | -58% | 1 | 1 | 0% | 1,633 | 2,464 | +51% | 0 | 0 | — |
case-01 | fail→fail | 29,969 | 5,715 | -81% | 1 | 1 | 0% | 6,213 | 1,973 | -68% | 0 | 0 | — |
case-02 | fail→fail | 33,279 | 4,225 | -87% | 1 | 1 | 0% | 6,222 | 1,918 | -69% | 0 | 0 | — |
case-03 | fail→fail | 33,449 | 5,514 | -84% | 1 | 1 | 0% | 6,215 | 2,036 | -67% | 0 | 0 | — |
case-08 | pass→fail | 6,544 | 4,269 | -35% | 1 | 1 | 0% | 1,191 | 2,399 | +101% | 0 | 0 | — |
case-04 | pass→pass | 5,912 | 7,584 | +28% | 1 | 1 | 0% | 1,264 | 3,084 | +144% | 0 | 0 | — |
case-05 | pass→fail | 16,884 | 7,079 | -58% | 1 | 1 | 0% | 2,893 | 2,121 | -27% | 0 | 0 | — |
case-06 | pass→fail | 14,049 | 5,369 | -62% | 1 | 1 | 0% | 2,511 | 2,528 | +1% | 0 | 0 | — |
case-07 | pass→pass | 12,224 | 6,788 | -44% | 1 | 1 | 0% | 2,112 | 2,776 | +31% | 0 | 0 | — |
case-09 | pass→fail | 6,539 | 1,534 | -77% | 1 | 1 | 0% | 1,037 | 1,942 | +87% | 0 | 0 | — |
case-10 | pass→pass | 11,219 | 5,013 | -55% | 1 | 1 | 0% | 1,766 | 2,521 | +43% | 0 | 0 | — |
case-11 | pass→pass | 6,178 | 4,985 | -19% | 1 | 1 | 0% | 1,130 | 2,505 | +122% | 0 | 0 | — |
case-12 | fail→pass | 9,223 | 6,378 | -31% | 1 | 1 | 0% | 1,476 | 2,673 | +81% | 0 | 0 | — |
case-14 | pass→pass | 9,438 | 6,130 | -35% | 1 | 1 | 0% | 1,422 | 2,798 | +97% | 0 | 0 | — |
case-15 | fail→fail | 16,709 | 6,292 | -62% | 1 | 1 | 0% | 2,802 | 2,027 | -28% | 0 | 0 | — |
case-16 | pass→pass | 10,357 | 3,342 | -68% | 1 | 1 | 0% | 1,631 | 2,239 | +37% | 0 | 0 | — |
case-17 | fail→fail | 7,165 | 2,493 | -65% | 1 | 1 | 0% | 1,226 | 2,124 | +73% | 0 | 0 | — |
case-18 | pass→pass | 5,865 | 5,385 | -8% | 1 | 1 | 0% | 1,037 | 2,605 | +151% | 0 | 0 | — |
case-19 | fail→pass | 44,323 | 3,151 | -93% | 1 | 1 | 0% | 393 | 2,215 | +464% | 0 | 0 | — |
case-20 | fail→pass | 3,217 | 10,452 | +225% | 1 | 1 | 0% | 523 | 3,480 | +565% | 0 | 0 | — |
case-21 | fail→fail | 30,285 | 6,577 | -78% | 1 | 1 | 0% | 6,184 | 2,069 | -67% | 0 | 0 | — |
case-22 | fail→fail | 29,413 | 6,018 | -80% | 1 | 1 | 0% | 6,197 | 2,088 | -66% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 14 counted toward the lift figure. The other 8 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of 0 percentage points is the difference between those two pass rates over the 14 comparable cases. 5 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.