Skip to content
Agentmart
Submit a tool

scientific-report-pdf

Generate a structured scientific PDF report from a JSON description.

Skill by lamm-mit

IndexedApache-2.0★ 250
Write a review

Chalk Labs

Need help deploying scientific-report-pdf?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/lamm-mit-scientific-report-pdf

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Generate a structured scientific PDF report from a JSON description. Accepts a JSON file specifying title, authors, abstract, sections (headings, text, tables, figures), and inline data panels (heatmap, bar, scatter, line). Produces a publication-style A4 PDF using reportlab with no LaTeX dependency. All figures are either loaded from PNG paths or generated on-the-fly from inline data.

Use cases: documents, data, research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/scientific-report-pdf

What's inside

Skill name
scientific-report-pdf
Description
Generate a structured scientific PDF report from a JSON description. Accepts a JSON file specifying title, authors, abstract, sections (headings, text, tables, figures), and inline data panels (heatmap, bar, scatter, line). Produces a publication-style A4 PDF using reportlab with no LaTeX dependency. All figures are either loaded from PNG paths or generated on-the-fly from inline data.
License
Apache-2.0
Metadata
domain: visualization · dependencies: reportlab, matplotlib, pillow
Instructions
115 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (2)

  • SKILL.md
  • scientific_report_pdf.py · scripts/

SKILL.md (first lines)

# scientific-report-pdf

Generates a structured scientific PDF report from a JSON input file. No LaTeX or pandoc required — uses reportlab for pure-Python PDF rendering.

## Usage

```bash
python3 skills/scientific-report-pdf/scripts/scientific_report_pdf.py --input-json report.json
python3 skills/scientific-report-pdf/scripts/scientific_report_pdf.py --input-json report.json --output-dir /tmp/
python3 skills/scientific-report-pdf/scripts/scientific_report_pdf.py --describe-schema
```

## Input JSON Structure

```json
{
  "title": "The Sound of Molecules",
  "authors": ["ReportAgent", "MusicAnalyst"],
  "subtitle": "CS1 Investigation | LAMM Research Platform",
  "abstract": "We present ...",
  "sections": [
    {"type": "heading", "level": 1, "text": "1. Introduction"},
    {"type": "text", "text": "Sonification has been applied to ..."},
    {
      "type": "table",
      "label": "Table 1",
      "caption": "RDKit descriptors for 16 compounds.",
      "headers": ["Compound", "MW", "LogP"],
      "rows": [["aspirin", "180.2", "1.19"], ["ibuprofen", "206.3", "3.72"]]
    },
    {
      "type": "figure",
      "label": "Figure 1",
      "caption": "Era-match heatmap.",
      "path": "/path/to/era_match.png"
    },
    {
      "type": "panel",
      "label": "Figure 2",
      "caption": "Mean similarity by drug class.",
      "panel_type": "bar",
      "figsize": [10, 5],
      "data": {
        "categories": ["NSAID", "Opioid", "Stimulant"],
        "series": [{"name": "Bach", "values": [0.4, 0.7, 0.3], "color": "#c0392b"}],
        "xlabel": "Drug class",
        "ylabel": "Mean cosine similarity",
        "title": "Harmonic Affinity by Drug Class"
      }
    },
    {"type": "pagebreak"},
    {
      "type": "panel",
      "label": "Figure 3",
      "caption": "Cosine similarity heatmap.",
      "panel_type": "heatmap",
      "data": {
        "values": [[0.8, 0.3], [0.2, 0.9]],
        "row_labels": ["aspirin", "fentanyl"],
        "col_labels": ["Bach", "Beethoven"],
        "cmap": "YlOrRd",
        "annotate": true
      }
    }
  ],
  "metadata": {
    "investigation_id": "cs1_sound_of_molecules",
    "platform": "LAMM Infinite",
    "agents": ["SoundAgent1", "MusicAnalyst", "ReportAgent"]
  }
}
```

## Section Types

| type | Required fields | Description |
|------|----------------|-------------|
| `heading` | `level` (1-3), `text` | Section heading |
| `text` | `text` | Paragraph body |
| `table` | `headers`, `rows` | Data table with optional `label`, `caption`, `highlight_col` |
| `figure` | `path` | Embed existing PNG/JPG |
| `panel` | `panel_type`, `data` | Auto-generate matplotlib figure |
| `pagebreak` | — | Force page break |
| `hr` | — | Horizontal rule |

## Panel Types

| panel_type | Required data fields |
|-----------|---------------------|
| `heatmap` | `values` (2D array), `row_labels`, `col_labels` |
| `matrix` | same as heatmap |
| `bar` | `categories`, `series` (list of `{name, values, color}`) |
| `grouped_bar` | same as bar |
| `scatter` | `x`, `y` |
| `line` | `x`, `y` |

## Output

```json
{
  "pdf_path": "/tmp/The_Sound_of_Molecules_20260403_001234.pdf",
  "n_pages": 8,
  "n_figures": 4,
  "size_kb": 512
}
```

## Dependencies

- `reportlab` — PDF generation
- `matplotlib` — auto-generated panel figures
- `pillow` — RGBA→RGB image conversion
- `pypdf` (optional) — page count in output

From lamm-mit/scienceclaw, Apache-2.0.

More from lamm-mit/scienceclaw

Signals

Stars
250
Forks
47
Open issues
1
Last commit (this folder)
Apr 7, 2026 (6 months ago)
Last release
Jun 23, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from lamm-mit

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get scientific-report-pdf running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying scientific-report-pdf?

CallGet help
Cite this page

scientific-report-pdf skill. Agent Mart. https://agentmart.dev/skills/lamm-mit-scientific-report-pdf (last updated 2026-10-24)