Draft
Academic research agent skills for Claude Code and other Agent Skills-compatible tools. Hypothesis generation, experiment design, paper drafting, peer review simulation, and more.
npx -y skills add richard-kim-79/archora-skills --skill draftAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
What its author says it does
Copied from the file, not written here
Writes a complete IMRaD-structured academic paper draft (Abstract, Introduction, Related Work, Methods, Results, Discussion, Conclusion, References) from the user's notes, documents, and wiki content. Use when the user asks to write a paper, create a manuscript, generate a draft, or produce academic writing. Do NOT use for short summaries — only for full paper-length output.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.7 KB, as published. Nobody here has run it
Paper Draft Generation
Generate a complete IMRaD-structured academic paper draft from research notes and documents.
IMRaD Structure
| Section | Purpose | Length |
|---|---|---|
| Abstract | Background, objective, methods, findings, conclusions | 250–300 words |
| Introduction | Problem, motivation, gap, contribution | 400–600 words |
| Related Work | Prior literature organized by theme | 500–800 words |
| Methods | How the research was/will be conducted | 400–600 words |
| Results | What was found (or projected findings) | 300–500 words |
| Discussion | Interpretation, implications, limitations | 400–600 words |
| Conclusion | Summary, contributions, future work | 200–300 words |
| References | All cited sources | As needed |
Workflow
- Gather content — read all provided notes, wiki pages, and documents
- Identify the core contribution — what is new and why does it matter?
- Map citations — track which sources support which claims
- Draft section by section — follow IMRaD order
- Add inline citations — use
[Author, Year]or[Source Title]format - Flag gaps — mark sections needing real data with
> ⚠️ [PROJECTED — add empirical data]
Citation format
Use the actual title or author of notes/documents you read:
Predictive coding theory proposes... [Rao & Ballard, 1999]
At the end, add a References section listing all cited sources.
Handling missing data
When the research doesn't have empirical results yet, write projected results based on the hypotheses — but clearly mark them:
> ⚠️ **Projected Results** — Replace with actual experimental data before submission.
Based on the experimental design, we expect...
Quality checklist
- Abstract covers all 5 components (background, objective, methods, findings, conclusions)
- Introduction ends with a clear statement of contribution
- Every major claim has an inline citation
- Methods section is specific enough to reproduce
- Discussion addresses alternative interpretations
- Limitations section is honest, not defensive