paper2poster

Name: paper2poster
Author: QuZhan51496

288stars10forks

How to install paper2poster?

quzhan51496/paper2anything/paper2poster

$npx -y skills add QuZhan51496/paper2anything --skill paper2poster

Installs into the current project.

Summary

Convert academic papers (PDF) into conference posters (HTML/PNG). You are the conductor: you decide what each section needs — an original paper figure or text — write the outline, hand-author the poster HTML, and iterate on the render using your own visual read and a blind-reader

Files · 1

View on GitHub

SKILL.md

1	# Paper2Poster — Conference Poster Skill (You as Conductor)
2
3	Convert a paper PDF into an academic conference poster (HTML/PNG) by walking a small set of CLI scripts. You are the conductor: this file is the recipe, not an orchestrator. There is no `run_pipeline.py` — at each step you run one Bash command, read the intermediate artifact, and ask the user for confirmation at the decision points below.
4
5	```text
6	PDF
7	→ parse_pdf.py (MinerU → content.md + figures/)
8	→ intake QA (you ask size/venue/authors/visual policy)
9	→ auto_outline.py (digest.json + assets[])
10	→ choose visuals (you read parsed/figures/ + captions: which sections use an original figure, which use text)
11	→ outline.json (you write from content.md; user confirms)
12	→ poster.html (you hand-author the poster: original figures where they help, text elsewhere)
13	→ render + score (Playwright PNG → deterministic geometry check + your own visual read + blind-reader content quiz)
14	→ iterate on poster.html (edit + re-render + re-score until it reads like a real poster)
15	→ poster.png
16	```
17
18	`problem_context`, `method_main`, and `result_evidence` are a useful reading-order spine to think about — what's the paper about, how does it work, what's the evidence. For each, decide what carries it best: an original paper figure if one reads well at poster scale, or text (a worded explanation, a labelled box, a short list) if no figure fits. There is no figure quota — use as many or as few original figures as the content calls for, down to zero. A text-only section, or a text-only poster, is a legitimate outcome when the figures don't earn their place.
19
20	---
21
22	## How you run this skill
23
24	This skill only works if you execute it as a sequence of small Bash + Read + AskUserQuestion turns. Do not try to short-circuit it.
25
26	1. Run one step at a time with the `Bash` tool, exactly as written below. Use absolute paths under `${SKILL_DIR}` (the directory this skill lives in — e.g. `<…>/paper2anything/paper2poster`; set it once per shell with `export SKILL_DIR=<…>/paper2anything/paper2poster`).
27	2. Read the intermediate artifact before moving on:
28	- after Step 3: the figures you considered, viewed in `parsed/figures/` (and their captions in `digest.json`), and which sections you decided to carry with text instead,
29	- after Step 5: your rendered `poster.png`, plus your visual read and the blind-reader quiz result.
30	3. Pause for the user at the decision points with `AskUserQuestion`:
31	- After Step 2 — intake: size, venue, author block, visual policy.
32	- After Step 3 — is your per-section visual plan (which sections use an original figure, which use text) acceptable?
33	- After Step 4 — is the outline structure acceptable?
34	- After Step 8 — accept the poster, or revise/restyle it?
35	4. Let the content decide whether a section gets a figure. Use an original paper figure where one genuinely helps; carry a section with text when no figure earns its place. Don't pad the poster with weak figures to hit a count, and don't strip a figure that's doing real work. A text-only section — or a text-only poster — is fine.
36	5. Score every render, then iterate (Steps 5–7). After each render, run the deterministic geometry check and look at the PNG yourself (your visual read — hierarchy/density/balance/readability); run the blind-reader content quiz (Step 7) at milestones rather than on every micro-edit (it spawns a subagent, so it costs more than reading a PNG). Let what they surface drive the next edit; don't ship the first render unscored. The geometry check is two-sided: not just "no overflow" but also a fill ratio ≥ 0.95 — a poster that fits but leaves large whitespace (or shrinks text to do so) fails and must be iterated. Verify this gate yourself; how you reach it is your judgment.
37	6. Don't overwrite a good render — keep scored candidates. Iteration is not always monotonic: an edit aimed at one issue can regress overall quality, and the version you had three edits ago may have read better. Before a non-trivial restyle or structural change, save the current render as a numbered candidate (e.g. copy `poster.html`/`poster.png` to `poster_candN.html`/`poster_candN.png`) and record its scores. Pick the final from the best-scoring candidate, not just the latest edit. Never let a higher-scoring intermediate

People who liked this also viewed

6 picks

Type

paper2poster

288stars10forks

View on GitHub

How to install paper2poster?

quzhan51496/paper2anything/paper2poster

$npx -y skills add QuZhan51496/paper2anything --skill paper2poster

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Paper2Poster — Conference Poster Skill (You as Conductor)
2
3	Convert a paper PDF into an academic conference poster (HTML/PNG) by walking a small set of CLI scripts. You are the conductor: this file is the recipe, not an orchestrator. There is no `run_pipeline.py` — at each step you run one Bash command, read the intermediate artifact, and ask the user for confirmation at the decision points below.
4
5	```text
6	PDF
7	→ parse_pdf.py (MinerU → content.md + figures/)
8	→ intake QA (you ask size/venue/authors/visual policy)
9	→ auto_outline.py (digest.json + assets[])
10	→ choose visuals (you read parsed/figures/ + captions: which sections use an original figure, which use text)
11	→ outline.json (you write from content.md; user confirms)
12	→ poster.html (you hand-author the poster: original figures where they help, text elsewhere)
13	→ render + score (Playwright PNG → deterministic geometry check + your own visual read + blind-reader content quiz)
14	→ iterate on poster.html (edit + re-render + re-score until it reads like a real poster)
15	→ poster.png
16	```
17
18	`problem_context`, `method_main`, and `result_evidence` are a useful reading-order spine to think about — what's the paper about, how does it work, what's the evidence. For each, decide what carries it best: an original paper figure if one reads well at poster scale, or text (a worded explanation, a labelled box, a short list) if no figure fits. There is no figure quota — use as many or as few original figures as the content calls for, down to zero. A text-only section, or a text-only poster, is a legitimate outcome when the figures don't earn their place.
19
20	---
21
22	## How you run this skill
23
24	This skill only works if you execute it as a sequence of small Bash + Read + AskUserQuestion turns. Do not try to short-circuit it.
25
26	1. Run one step at a time with the `Bash` tool, exactly as written below. Use absolute paths under `${SKILL_DIR}` (the directory this skill lives in — e.g. `<…>/paper2anything/paper2poster`; set it once per shell with `export SKILL_DIR=<…>/paper2anything/paper2poster`).
27	2. Read the intermediate artifact before moving on:
28	- after Step 3: the figures you considered, viewed in `parsed/figures/` (and their captions in `digest.json`), and which sections you decided to carry with text instead,
29	- after Step 5: your rendered `poster.png`, plus your visual read and the blind-reader quiz result.
30	3. Pause for the user at the decision points with `AskUserQuestion`:
31	- After Step 2 — intake: size, venue, author block, visual policy.
32	- After Step 3 — is your per-section visual plan (which sections use an original figure, which use text) acceptable?
33	- After Step 4 — is the outline structure acceptable?
34	- After Step 8 — accept the poster, or revise/restyle it?
35	4. Let the content decide whether a section gets a figure. Use an original paper figure where one genuinely helps; carry a section with text when no figure earns its place. Don't pad the poster with weak figures to hit a count, and don't strip a figure that's doing real work. A text-only section — or a text-only poster — is fine.
36	5. Score every render, then iterate (Steps 5–7). After each render, run the deterministic geometry check and look at the PNG yourself (your visual read — hierarchy/density/balance/readability); run the blind-reader content quiz (Step 7) at milestones rather than on every micro-edit (it spawns a subagent, so it costs more than reading a PNG). Let what they surface drive the next edit; don't ship the first render unscored. The geometry check is two-sided: not just "no overflow" but also a fill ratio ≥ 0.95 — a poster that fits but leaves large whitespace (or shrinks text to do so) fails and must be iterated. Verify this gate yourself; how you reach it is your judgment.
37	6. Don't overwrite a good render — keep scored candidates. Iteration is not always monotonic: an edit aimed at one issue can regress overall quality, and the version you had three edits ago may have read better. Before a non-trivial restyle or structural change, save the current render as a numbered candidate (e.g. copy `poster.html`/`poster.png` to `poster_candN.html`/`poster_candN.png`) and record its scores. Pick the final from the best-scoring candidate, not just the latest edit. Never let a higher-scoring intermediate

People who liked this also viewed

6 picks

Type