Paper Reader, Heilmeier Catechism

Trust Score 90/100

Read an academic paper and produce a compact Heilmeier-style analysis that combines summary and critique for fast expert review.

triggers:read this papersummarize this paperreview paperheilmeieranalyze this paper

GitHub SKILL.md

What it does

This skill ingests an academic paper from a PDF, arXiv link, DOI, or pasted text and produces a single inline modified Heilmeier's Catechism analysis that combines structured summary with critique. The output is a concise, sectioned response covering objective, problem context, technical approach, impact, risks, costs, and experimental results.

When to use it

Use when a user asks to read, summarize, review, or critically assess an academic research paper in STEM fields. Trigger on PDF uploads, arXiv links, DOIs, or pasted paper text. Do not use for non-academic blog posts or news articles.

What's included

Scripts: none bundled, this is an instruction skill for agent behavior.
References: none required, the skill relies on the paper content and optional web fetches for citation when requested.
Instructions: stepwise protocol to acquire the paper, prioritize sections when long, and answer seven Heilmeier questions with strict rules for opinions and citations.

Compatible agents

Designed for general-purpose assistant agents with web_fetch and PDF reading capabilities, for example agents using web_fetch, PDF parsers, and models that support inline markdown output.

Audit Summary

A well-crafted prompt-only skill that guides an agent through reading an academic paper and producing a modified Heilmeier's Catechism analysis. No scripts included — it's purely a structured prompt with detailed formatting and attribution rules. The SKILL.md is exceptionally well-written with clear step-by-step instructions, explicit opinion/citation rules per question, and strong guardrails against hallucination. Security is clean: no shell commands, no network calls beyond standard web_fetch, no data exfiltration risks. The single minor deduction is for the instruction to use web_fetch on arXiv links, which is standard and low-risk.

Watch Out

Pure prompt skill — no automation beyond what the host agent provides
Requires an agent capable of reading PDFs or fetching web content

Notes

Excellent example of a prompt-only skill. Clear triggers, detailed formatting rules, explicit boundaries on opinions vs paper content. The attribution and citation rules are thoughtful and address real LLM failure modes. No security concerns whatsoever.

Information

Repository: paper-reader-heilmeier
Stars: 50

Trust Score

Overall90

Security95

Code Quality82

Architecture88

Usefulness72

Related Skills

Markdrop

Convert PDFs to structured Markdown or interactive HTML and generate AI-powered descriptions for images and tables using multiple LLM providers.

Chinese Software Copyright Application

Generate complete Chinese software copyright application materials (application form, code documentation, user manual, design docs) and export them to PDF from

arxiv2md

Convert arXiv papers into clean, LLM-ready Markdown via a REST API or CLI for fast reading, summarization, and downstream processing.

Doc Cleaner

Convert PDF, DOCX, XLSX and text files into clean, structured Markdown with CJK and table support; supports offline or AI-enhanced modes.

AI News Daily

Generate a structured, bilingual daily briefing of the latest AI industry news, model updates, papers, and open-source tools with in-depth technical analysis an

Research Information Lookup

Find and synthesize current research and academic papers with automatic backend routing (Parallel Chat API or Perplexity) and structured citations.

Office & Design Toolkit

Comprehensive toolkit for processing and producing DOCX, PPTX, XLSX and PDF files plus design guidance and quality checks for professional office documents and

arXiv Paper Search & Download

Search arXiv, fetch paper metadata, download PDFs, and produce concise summaries for academic papers (ID or query).

Back to Skills