lzh-phd GitHub avatar

topic-feasibility-screener

lzh-phd

A Codex skill that screens empirical research topics from CSV or Stata datasets by combining dataset profiling, literature search, transparent theory/data scoring, and second-pass validation into an interactive HTML dashboard.

Stars

481

7-day growth

No data

Forks

7

Open issues

0

License

MIT

Last updated

2026-07-04

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It explicitly separates topics with no theoretical footing from those that have bridge evidence (a potential frontier gap), a distinction often overlooked by keyword-only tools, and it provides a visual, evidence-grounded dashboard for early-stage thesis and paper development in accounting, finance, economics, and related fields.

Who it is for

  • PhD students and early-career researchers in accounting, finance, economics, and management
  • Academic researchers exploring new empirical topics from existing datasets
  • Research method instructors demonstrating systematic topic screening
  • Data analysts in business schools or research institutes working with CSV or Stata data

Use cases

  • Screening multiple candidate research topics from a single dataset for a dissertation
  • Evaluating whether a rough idea has both theoretical and empirical feasibility before investing time in full analysis
  • Generating and prioritizing topic ideas using variable profiles and nearby datasets
  • Producing a transparent audit trail for advisors or reviewers to assess topic selection

Strengths

  • Provides transparent 0-100 scores for multiple feasibility dimensions (empirical, theory support, theory gap, etc.)
  • Handles bridge evidence intelligently—does not penalize direct-evidence gaps when adjacent literatures are supportive
  • Outputs an interactive HTML dashboard plus mandatory self-audit CSV for trust verification
  • Integrates real literature search with diagnostics (query family, status, hit counts, error messages) and evidence classification into direct, bridge, background, weak

Considerations

  • Screening significance must not be interpreted as causal proof; final causal identification requires manual judgment
  • Relies on the Codex environment and requires the skill folder to be copied into a specific directory
  • Limited to CSV and Stata .dta datasets; other formats like Excel or SQL are not mentioned

README quick start

使用边界

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482