paper2html

Name: paper2html
Author: QuZhan51496

288stars10forks

How to install paper2html?

quzhan51496/paper2anything/paper2html

$npx -y skills add QuZhan51496/paper2anything --skill paper2html

Installs into the current project.

Summary

Convert an academic paper PDF into a publish-ready, self-contained single-page project homepage (a self-contained index.html) — the kind of paper landing page researchers host on GitHub Pages. Triggers when the user says "turn a paper into a project page/webpage", "paper2html

Files · 1

View on GitHub

SKILL.md

1	# paper2html — Paper to single-page project homepage (you-led, coordinated)
2
3	Turn a paper PDF into a self-contained, publish-ready single-page project website — the kind of paper
4	homepage researchers commonly build on GitHub Pages.
5	You are the lead author: this file is the recipe, not a fully automated script — there is no `main.py`,
6	no renderer. The mechanical steps (parse / extract / QA) call the small tools under `scripts/`; **understanding
7	the paper, designing the page, and writing `index.html` are done by you** (read the material and figures with
8	Read, write `index.html` with Write), confirming with the user at key points via `AskUserQuestion`.
9
10	```text
11	PDF
12	→ parse + extract (parse_pdf.py: MinerU → clean.md + manifest.json + images/, gate 1)
13	→ you understand it + set the design (read manifest + clean.md + look at figures) → pick a design language [confirm design direction]
14	→ you hand-author the page (per the references/ design-language and authoring rules) → index.html [optional confirm]
15	→ QA validation (validate.py: missing figures/broken links/content fidelity, gate 2) → fix per report, loop
16	→ single-page project homepage index.html (+ images/, deployable as-is)
17	```
18
19	## How you run this skill
20
21	1. Step by step: run scripts for the mechanical steps via `Bash` (absolute paths, no cd needed); do the design and authoring yourself with `Read`/`Write`.
22	2. Compute `WORKDIR` inline at the top of each Bash block (each Bash call is a separate shell and does not share variables):
23	```bash
24	WORKDIR="$(dirname "$pdf_path")/.paper2anything/html/$(basename "${pdf_path%.*}")"
25	```
26	`$pdf_path` is the paper PDF the user gave (reset it in each block). The scripts live in `${SKILL_DIR}/scripts` — `SKILL_DIR`
27	is this skill's directory (see "Base directory for this skill: …" injected at the top of this skill); each Bash block is a
28	separate shell, so in the blocks that use it `export SKILL_DIR=<that directory>` once at the top (set it inline each time, like `WORKDIR`).
29	3. Pause at decision points with `AskUserQuestion`: after understanding the paper, confirm the design direction (design language / primary color / emphasis); after the draft is done, you may confirm again.
30	4. Faithful to the manifest, you fill the gaps: use only the real material in `manifest.json`, don't fabricate numbers/authors/links; fields the manifest left empty
31	(authors/abstract/links etc.) you complete from the full text of `clean.md` — you are the lead author, deterministic extraction is only scaffolding.
32
33	---
34
35	## Step 0: Environment and credentials
36
37	> Unified environment: all `python` commands run in paper2anything's unified conda environment (top-level `environment.yml`),
38	> prefixed with `conda run -n paper2anything --no-capture-output`.
39
40	Credentials are centralized in the package-root `.env` (copied from `.env.example`, already gitignored); export it once per new shell:
41
42	```bash
43	set -a; source <paper2anything package root>/.env; set +a
44	```
45
46	This skill only needs `MINERU_API_TOKEN` (to parse the PDF). Page design and authoring are done by you, calling no LLM API,
47	so no OPENAI/LLM key is needed.
48
49	Dependency self-check:
50
51	```bash
52	conda run -n paper2anything --no-capture-output python -c "import requests, rich, dotenv, playwright, PIL" 2>&1
53	# render_check.py (Step 4 render self-check) needs the chromium engine; install it once before the first run:
54	# conda run -n paper2anything --no-capture-output python -m playwright install chromium
55	```
56
57	---
58
59	## Step 1: Parse + deterministic extraction (script, gate 1)
60
61	```bash
62	pdf_path="/path/to/paper.pdf" # ← the user's paper PDF
63	WORKDIR="$(dirname "$pdf_path")/.paper2anything/html/$(basename "${pdf_path%.*}")"
64	conda run -n paper2anything --no-capture-output \
65	python "${SKILL_DIR}/scripts/parse_pdf.py" "$pdf_path" --workdir "$WORKDIR"
66	```
67
68	Outputs (under `$WORKDIR`):
69	- `clean.md` — normalized full-text markdown (for you to read through)
70	- `manifest.json` — deterministically extracted facts: title/authors/affiliations/abstract/links/claim

People who liked this also viewed

6 picks

Type

paper2html

288stars10forks

View on GitHub

How to install paper2html?

quzhan51496/paper2anything/paper2html

$npx -y skills add QuZhan51496/paper2anything --skill paper2html

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# paper2html — Paper to single-page project homepage (you-led, coordinated)
2
3	Turn a paper PDF into a self-contained, publish-ready single-page project website — the kind of paper
4	homepage researchers commonly build on GitHub Pages.
5	You are the lead author: this file is the recipe, not a fully automated script — there is no `main.py`,
6	no renderer. The mechanical steps (parse / extract / QA) call the small tools under `scripts/`; **understanding
7	the paper, designing the page, and writing `index.html` are done by you** (read the material and figures with
8	Read, write `index.html` with Write), confirming with the user at key points via `AskUserQuestion`.
9
10	```text
11	PDF
12	→ parse + extract (parse_pdf.py: MinerU → clean.md + manifest.json + images/, gate 1)
13	→ you understand it + set the design (read manifest + clean.md + look at figures) → pick a design language [confirm design direction]
14	→ you hand-author the page (per the references/ design-language and authoring rules) → index.html [optional confirm]
15	→ QA validation (validate.py: missing figures/broken links/content fidelity, gate 2) → fix per report, loop
16	→ single-page project homepage index.html (+ images/, deployable as-is)
17	```
18
19	## How you run this skill
20
21	1. Step by step: run scripts for the mechanical steps via `Bash` (absolute paths, no cd needed); do the design and authoring yourself with `Read`/`Write`.
22	2. Compute `WORKDIR` inline at the top of each Bash block (each Bash call is a separate shell and does not share variables):
23	```bash
24	WORKDIR="$(dirname "$pdf_path")/.paper2anything/html/$(basename "${pdf_path%.*}")"
25	```
26	`$pdf_path` is the paper PDF the user gave (reset it in each block). The scripts live in `${SKILL_DIR}/scripts` — `SKILL_DIR`
27	is this skill's directory (see "Base directory for this skill: …" injected at the top of this skill); each Bash block is a
28	separate shell, so in the blocks that use it `export SKILL_DIR=<that directory>` once at the top (set it inline each time, like `WORKDIR`).
29	3. Pause at decision points with `AskUserQuestion`: after understanding the paper, confirm the design direction (design language / primary color / emphasis); after the draft is done, you may confirm again.
30	4. Faithful to the manifest, you fill the gaps: use only the real material in `manifest.json`, don't fabricate numbers/authors/links; fields the manifest left empty
31	(authors/abstract/links etc.) you complete from the full text of `clean.md` — you are the lead author, deterministic extraction is only scaffolding.
32
33	---
34
35	## Step 0: Environment and credentials
36
37	> Unified environment: all `python` commands run in paper2anything's unified conda environment (top-level `environment.yml`),
38	> prefixed with `conda run -n paper2anything --no-capture-output`.
39
40	Credentials are centralized in the package-root `.env` (copied from `.env.example`, already gitignored); export it once per new shell:
41
42	```bash
43	set -a; source <paper2anything package root>/.env; set +a
44	```
45
46	This skill only needs `MINERU_API_TOKEN` (to parse the PDF). Page design and authoring are done by you, calling no LLM API,
47	so no OPENAI/LLM key is needed.
48
49	Dependency self-check:
50
51	```bash
52	conda run -n paper2anything --no-capture-output python -c "import requests, rich, dotenv, playwright, PIL" 2>&1
53	# render_check.py (Step 4 render self-check) needs the chromium engine; install it once before the first run:
54	# conda run -n paper2anything --no-capture-output python -m playwright install chromium
55	```
56
57	---
58
59	## Step 1: Parse + deterministic extraction (script, gate 1)
60
61	```bash
62	pdf_path="/path/to/paper.pdf" # ← the user's paper PDF
63	WORKDIR="$(dirname "$pdf_path")/.paper2anything/html/$(basename "${pdf_path%.*}")"
64	conda run -n paper2anything --no-capture-output \
65	python "${SKILL_DIR}/scripts/parse_pdf.py" "$pdf_path" --workdir "$WORKDIR"
66	```
67
68	Outputs (under `$WORKDIR`):
69	- `clean.md` — normalized full-text markdown (for you to read through)
70	- `manifest.json` — deterministically extracted facts: title/authors/affiliations/abstract/links/claim

People who liked this also viewed

6 picks

Type