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
npx skills add franklee16/academic-research-skills --skill llm-research-workflow -a claude-codeWhat 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-code2Manually: put the files in place
~/.claude/skills/llm-research-workflow/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/llm-research-workflow/
1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill llm-research-workflow -a codex2Manually: put the files in place
.agents/skills/llm-research-workflow/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill llm-research-workflow -a cursor2Manually: put the files in place
.cursor/skills/llm-research-workflow/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install franklee16/academic-research-skills research-workflow/llm-research-workflow/SKILL.md2Manually: put the files in place
.github/skills/llm-research-workflow/SKILL.md1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill llm-research-workflow -a gemini-cli2Platform CLI
gemini skills install https://github.com/franklee16/academic-research-skills --path research-workflow/llm-research-workflowManually: put the files in place
.devin/skills/llm-research-workflow/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
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.