Skip to main content
skill CX Codex

llm-research-workflow — Claude Code skill: what it does & setup

llm-research-workflow enforces a structured methodology for extracting, classifying, and validating empirical variables in economics and finance research with LLMs.

no license ★ 240 updated 2026-09-18

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add franklee16/academic-research-skills --skill llm-research-workflow -a claude-code
Open on GitHub

What llm-research-workflow does

The skill integrates an academic methodology drawn from Ferrara (2026, NBER WP 35374) directly into Claude Code sessions. Instead of immediately writing automation scripts, the assistant pauses to evaluate three mandatory prerequisites: tool suitability, data transfer legality, and execution costs. Deterministic lookups or spatial queries get routed toward dedicated libraries and authoritative sources rather than raw generation.

The core loop requires offering multiple alternatives for every variable extraction task, explicitly including at least one deterministic or non-LLM baseline such as keyword rules or supervised algorithms. Claude guides the discussion through method tradeoffs, user comprehension, and mandatory pilot testing on representative subsamples before running full-scale pipelines.

Licensed academic feeds like CRSP, WRDS, or broker archives often forbid bulk uploads to external services. The skill halts blind execution and forces you to consider zero-retention contracts or self-hosted weights like Qwen or Llama.

What it helps with

  • verify whether commercial dataset licenses permit third-party API processing
  • benchmark generative classification against deterministic non-LLM methods
  • structure pilot testing on representative corpora prior to large-scale runs
  • route deterministic queries away from prone-to-hallucination model generation

Example prompts for the agent

  • Can an LLM reliably extract balance sheet indicators from these PDF filings?
  • Help me set up a pipeline to score sentiment in earnings conference calls
  • Classify these historical regulatory notices for an empirical regressions study

How to install llm-research-workflow

1Skills CLI (Vercel)

npx skills add franklee16/academic-research-skills --skill llm-research-workflow -a claude-code

2Manually: put the files in place

~/.claude/skills/llm-research-workflow/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/llm-research-workflow/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about llm-research-workflow

How to install llm-research-workflow in Claude Code?

Run npx skills add franklee16/academic-research-skills --skill llm-research-workflow -a claude-code in your terminal. Alternatively, place the file into ~/.claude/skills/llm-research-workflow/SKILL.md.

What does llm-research-workflow do?

It turns the assistant into an academic reviewer that demands error audits, baseline comparisons, and pilot validation before building research data pipelines.

What tasks does the skill steer away from LLMs?

It intercepts automated literature searches, raw historical price queries, and spatial calculations, routing them instead to statistical databases, geocoding libraries, or verified registries.

Similar skills

All skills for Science and research →

From the same set98

The whole set →
compiledeck compiledeck — a Claude skill that builds and edits LaTeX Beamer decks under hard rules: one point per slide, large type, titles that state the claim. CX Codex +1 ★ 240repo stars glance glance is a Claude Code skill that quickly scans batches of research papers and generates a structured Chinese-language summary PDF with WeasyPrint. CX Codex +1 ★ 240repo stars revision-coordinator The revision-coordinator skill turns manuscript feedback into section-level tasks and routes them to specialized writing skills. Use it when you have a draft and reviewer, colleague, or self-review comments. CX Codex +1 ★ 240repo stars paper-reading-problem-reality-check paper-reading-problem-reality-check puts a single Research Question Card under pressure: is the problem real, is evidence behind it, and would the motivation survive a skeptical reviewer? CX Codex +1 ★ 240repo stars paper-reading-research-question paper-reading-research-question turns an existing field map into testable research questions: candidate angles, an evidence check and question cards. CX Codex +1 ★ 240repo stars diagram-generator diagram-generator is a Claude Code skill that creates and edits draw.io, Mermaid, and Excalidraw diagrams from text descriptions. CX Codex +1 ★ 240repo stars LR LR helps write literature reviews, systematic review sections, and structured syntheses of scholarly sources for a research topic. CX Codex +1 ★ 240repo stars paper-to-social paper-to-social adapts academic papers and preprints into platform-native posts for LinkedIn, X, Xiaohongshu, and Substack. CX Codex +1 ★ 240repo stars

Project sponsors

Companies that keep this analytics open