AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Huashu Research Report Builder

Builds institution-grade research reports — industry reports, white papers, annual surveys, consulting decks, and arXiv papers — covering structure, prose, charts, and page-level print QA.

Docs & OfficeAdvanced★ 489⑂ 65AI score 9/10Last updated: Oct 13, 2026

What it does

  • Picks the report archetype first: academic, 16:9 consulting deck (one conclusion per page), survey study, data-research note, arXiv paper, or popular-science long read — chosen from "what will the reader do with it?".
  • Makes you play four roles in order: researcher (define the sample frame, explain mechanisms, position the finding against prior work), editor, information designer, and data-visualization lead.
  • Five hard rules: every number needs a denominator (N); chart titles state the conclusion, not the topic; a self-rebuttal paragraph follows every conclusion; the appendix is a source list capped at 10% of body length; never narrate "how we made this".
  • A fixed build order: archetype + one-sentence thesis → data table → body copy → mechanism & literature positioning → charts → page-by-page self-check.
  • Shipping assets: assets/base.css (A4 and full-bleed layout base), assets/chart.py (8 inline-SVG chart types with negative-value support), assets/render.py (render + auto TOC page numbers + mechanical margin measurement).
  • A human-eye defect checklist: column collisions, negative bars drawn at zero height, clipped labels, orphan paragraphs, long tables missing repeated headers — reviewed page by page, never by sampling.

Who it's for

  • Analysts at consultancies, market-research firms, and corporate strategy teams
  • Marketing/research groups publishing white papers and annual survey reports
  • Researchers who want a disciplined LaTeX/IMRaD pipeline for arXiv submissions
  • Teams fighting consistency and typesetting bugs in 60+ page documents

Examples

  1. "Write a 40-page industry report on 2026 enterprise AI agent adoption" → survey archetype, data table with N/source/definition filled in before any prose, then body, charts, and PDF.
  2. "Turn this into a 16:9 board deck" → switches to the consulting-deck archetype where each page carries exactly one conclusion as its headline.
  3. "QA the exported PDF" → renders every page with pdftoppm, flags glued columns, clipped annotations, and under-margin pages, then fixes the root cause rather than the symptom.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/alchaincyf/huashu-report/HEAD/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the SKILL.m folder from the GitHub repo alchaincyf/huashu-report into my ~/.claude/skills/huashu-report/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/alchaincyf/huashu-report.git ~/.claude/skills/huashu-report

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal (Terminal on macOS/Linux, Git Bash or WSL on Windows).
  2. Create the skills folder if needed: mkdir -p ~/.claude/skills
  3. Clone the repository: git clone https://github.com/alchaincyf/huashu-report.git ~/.claude/skills/huashu-report
  4. Verify with ls ~/.claude/skills/huashu-report — you should see SKILL.md, references/, and assets/.
  5. Install pdftoppm (poppler) for the PDF self-check — macOS: brew install poppler; Ubuntu: sudo apt install poppler-utils.
  6. Make sure Python 3 is available for chart.py and render.py: python3 --version.
  7. Restart Claude Code and ask something like "write an institution-grade industry report from this dataset" to trigger the skill.
  8. Note: the skill checks for new version tags via git ls-remote every 30 days. To disable, set the contents of .last-update-check in the skill folder to off.
View source on GitHub ↗License: MIT