paper-2-acfin-web
Skill63 starsChanged 5 months agoMITView on GitHub
Convert accounting and finance papers into dissemination assets — interactive project websites, seminar videos, and conference posters. Use when turning a JAR/JAE/TAR, JF/JFE/RFS, or empirical arch manuscript (LaTeX or PDF) into a Paper2Web homepage, Paper2Video talk, or Paper2Poster for AAA, FARS, MFA, WFA, or journal promotion.
- Reads credentials
- Installs packages
In this repository47 other files it gives its agents.
- install/claude.mdCLAUDE.md
- daskSkill
- econ-visualizationSkill
- geopandasSkill
- matplotlibSkill
- plotlySkill
- polarsSkill
- pymc-bayesian-modelingSkill
- scikit-learnSkill
- seabornSkill
- statistical-analysisSkill
- statsmodelsSkill
- pyfixestSkill
- python-panel-dataSkill
- r-econometricsSkill
- stata-data-cleaningSkill
- stata-regressionSkill
- wrdsSkill
- api-data-fetcherSkill
- citation-managementSkill
- datacommons-clientSkill
- exploratory-data-analysisSkill
- financial-text-nlpSkill
- literature-reviewSkill
- lit-review-assistantSkill
- openalex-apiSkill
- research-ideationSkill
- research-lookupSkill
- sec-edgarSkill
- web-scrapeSkill
- academic-paper-writerSkill
- beamer-presentationSkill
- econ-humanizer-plusSkill
- econ-humanizerSkill
- econ-refereeSkill
- econ-slidesSkill
- econ-writeSkill
- econ-writing-plusSkill
- hypothesis-generationSkill
- latex-econ-modelSkill
- latex-postersSkill
- latex-tablesSkill
- paper-pdfSkill
- peer-reviewSkill
- scholar-evaluationSkill
- scientific-critical-thinkingSkill
- venue-templatesSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 29
Create a seminar deck + video from a finance or accounting empirical paper
- Distinctive: line 36
When extracting or editing generated content, foreground what accounting and finance readers expect:
- Very specific: line 130
After generation, edit the site copy using ac/fin priorities above — especially identification, sample, and magnitude language.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Barrios Skills — John Barrios's curated workflow for economists and accountants. Prioritize reproducible empirical work, clear identification language, and journal-ready output.
Paper2AcFin: Accounting & Finance Paper Dissemination
Adapted from the Paper2All pipeline (paper-2-web), focused on empirical accounting and finance manuscripts — identification, institutional settings, archival data, and regression evidence.
Overview
Transform LaTeX or PDF papers into three outputs:
- Paper2Web — Interactive project homepage (question, design, tables, figures, replication)
- Paper2Video — Seminar-style video with slides and narration
- Paper2Poster — Conference poster (AAA, FARS, MFA, WFA, regional workshops)
Uses the open-source Paper2All toolchain. This skill adds accounting/finance content priorities the generic pipeline does not enforce.
When to use
- Promote a working paper on SSRN, personal site, or lab page
- Build a companion site for a journal submission or revision
- Prepare AAA / FARS / MFA / WFA poster or video materials
- Create a seminar deck + video from a finance or accounting empirical paper
- Batch homepages for a research agenda (e.g., licensing, disclosure, corporate governance series)
Triggers: "paper to website", "conference poster from my LaTeX", "video abstract for my finance paper", "project homepage for my JAR submission", "Paper2Web for accounting paper"
Accounting & finance content priorities
When extracting or editing generated content, foreground what accounting and finance readers expect:
| Section | Emphasize |
| Research question | Policy or market friction; why the setting matters (regulation, reporting, intermediation) |
| Institutional setting | Rule changes, filing regimes, market structure, sample window with dates |
| Data | Compustat, CRSP, TRACE, EDGAR, hand-collected disclosure — source and unit of observation |
| Design | DiD/event study, IV, RDD, matching, panel structure; parallel trends or first stage |
| Results | Economic magnitude (bps, % of assets, $ effects), not only significance |
| Robustness | Alternative samples, windows, definitions, placebo tests |
| Replication | Link to code, data availability statement, WRDS/SEC access notes |
De-emphasize generic "novel contribution" boilerplate; keep coefficient tables, key figures, and a clear identification paragraph on the homepage hero.
Workflow
Need dissemination for an ac/fin paper?
│
├─ Permanent project page / SSRN companion?
│ └─→ Paper2Web (see references/acfin-paper2web.md)
│
├─ Conference poster session?
│ └─→ Paper2Poster — AAA/FARS 4×3 or 4×4 ft (references/acfin-paper2poster.md)
│
├─ Seminar or video abstract?
│ └─→ Paper2Video — 5 min (abstract) or 15–20 min (job talk slice)
│
└─ Full package?
└─→ All three; generate website first (fastest QA)Quick start
1. Install Paper2All
git clone https://github.com/YuhangChen1/Paper2All.git
cd Paper2All
conda create -n paper2all python=3.11
conda activate paper2all
pip install -r requirements.txtSystem deps: LibreOffice, Poppler. See references/installation.md.
2. Configure API keys
# .env in Paper2All root — never commit
OPENAI_API_KEY=your_key_here3. Organize input (LaTeX preferred)
paper_directory/
├── main.tex
├── figures/ # event-study, balance table, main coef plot
├── tables/ # regression tables as standalone if needed
└── bibliography.bib4. Run pipeline
Website only:
python pipeline_all.py \
--input-dir "path/to/paper" \
--output-dir "path/to/output" \
--model-choice 1 \
--generate-websitePoster (typical 48×36 in):
python pipeline_all.py \
--input-dir "path/to/paper" \
--output-dir "path/to/output" \
--model-choice 1 \
--generate-poster \
--poster-width-inches 48 \
--poster-height-inches 36Video (seminar):
python pipeline_light.py \
--model_name_t gpt-4.1 \
--model_name_v gpt-4.1 \
--result_dir "path/to/output" \
--paper_latex_root "path/to/paper"After generation, edit the site copy using ac/fin priorities above — especially identification, sample, and magnitude language. Pair with econ-humanizer or econ-humanizer-plus for prose cleanup.
Post-generation checklist (ac/fin)
- Hero states the policy/market question in one sentence
- Identification strategy visible without scrolling (or in sticky summary)
- Main table and event-study (or parallel trends) figure above the fold
- Data sources named (Compustat, CRSP, EDGAR, etc.)
- Replication / contact / SSRN link in footer
- Poster readable at 4–6 feet; magnitudes on poster, not only stars
- Video opens with setting + design in first 90 seconds
Output layout
output/paper_name/
├── website/ index.html, assets/
├── poster/ poster_final.pdf, .png
└── video/ final_video.mp4, slides/Deploy websites to GitHub Pages, university hosting, or Netlify. Posters: university print shop or poster service. Videos: YouTube (unlisted), seminar sites, SSRN if journal allows.
Pair with other Barrios skills
| Task | Skill |
| Prose on generated pages | econ-humanizer, econ-humanizer-plus |
| Beamer deck before video | beamer-presentation |
| Figures for web/poster | econ-visualization, latex-tables |
| Pull Compustat/CRSP for live tables | wrds skill + wrds-mcp |
References
references/installation.md— Paper2All setupreferences/acfin-paper2web.md— Homepage structure for ac/fin papersreferences/acfin-paper2poster.md— Poster layout and conference sizesreferences/acfin-paper2video.md— Seminar and video-abstract pacingreferences/usage_examples.md— End-to-end ac/fin workflows
Upstream: Paper2All. Generic baseline: skills/optional/research-tools/paper-2-web.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

