llm-replication-disclosure — Claude Code skill: install
llm-replication-disclosure is a Claude Code skill that checks replication materials for LLM-assisted research and helps draft disclosure text before submission or a data-editor response.
no license ★ 240 updated 2026-09-18
npx skills add franklee16/academic-research-skills --skill llm-replication-disclosure -a claude-codeWhat llm-replication-disclosure does
This skill reviews whether an LLM-assisted study records the model identifier, call settings, prompts, validation evidence, data handling, and relevant code. It can also help draft methods or appendix text and assemble a replication package with a README and manifests.
It supports three workflows: auditing an existing project, drafting disclosure material, and staging a package from files already on disk. Templates are stored in references/templates.md, and original files should be copied before any reorganization. Missing archived raw model responses are a fatal gap because later results cannot be checked from the package alone.
What it helps with
- audit a replication package before submission
- locate missing prompts, model versions, or raw outputs
- draft a disclosure statement for LLM-assisted research
- assemble a README and manifests from project files
Example prompts for the agent
- Audit this project for the items required in an LLM replication package and list the gaps.
- Draft the methods and appendix wording for how LLMs were used in this study.
- Stage a replication package from the existing files without changing the originals.
How to install llm-replication-disclosure
1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill llm-replication-disclosure -a claude-code2Manually: put the files in place
~/.claude/skills/llm-replication-disclosure/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/llm-replication-disclosure/
1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill llm-replication-disclosure -a codex2Manually: put the files in place
.agents/skills/llm-replication-disclosure/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill llm-replication-disclosure -a cursor2Manually: put the files in place
.cursor/skills/llm-replication-disclosure/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install franklee16/academic-research-skills output-tools/llm-replication-disclosure/SKILL.md2Manually: put the files in place
.github/skills/llm-replication-disclosure/SKILL.md1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill llm-replication-disclosure -a gemini-cli2Platform CLI
gemini skills install https://github.com/franklee16/academic-research-skills --path output-tools/llm-replication-disclosureManually: put the files in place
.devin/skills/llm-replication-disclosure/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-replication-disclosure
How do I install llm-replication-disclosure in Claude Code?
Run npx skills add franklee16/academic-research-skills --skill llm-replication-disclosure -a claude-code, then open ~/.claude/skills/llm-replication-disclosure/SKILL.md.
What does llm-replication-disclosure do?
It audits LLM-assisted research materials, identifies gaps in the replication package, and helps write disclosure text for a paper, appendix, or data editor.
Why do archived raw model responses matter?
They let downstream results be checked from the package even when a later model run produces different output. Their absence is treated as a fatal gap.