Archora Skills is a set of research-focused agent skills for Claude Code and other Agent Skills-compatible tools. It gives you reusable pieces for moving from notes to hypotheses, experiments, drafts, and review.
Builders who want their agent to help with academic research from notes through paper review.
You can turn research notes into hypotheses, drafts, and critique without rebuilding the same workflow each time.
Creates falsifiable research hypotheses from notes and documents.
Designs experimental protocols to test each hypothesis.
Writes an IMRaD-structured paper draft.
Produces matplotlib and Mermaid visualization code.
Detects statistical errors and logical fallacies.
Simulates journal review with an editor-in-chief and three reviewers.
Generates devil’s advocate critiques to stress-test claims.
Surfaces cross-cutting themes and syncs notes into a structured wiki knowledge base.
npx skills add https://github.com/richard-kim-79/archora-skills
"Generate hypotheses from my notes" "Write a paper draft based on this research" "Give me a peer review of this draft" "What are the weaknesses in my argument?"
Academic research agent skills for Claude Code and other Agent Skills-compatible tools.
Built on Archora — a knowledge archive & social network for researchers and educators. Run these same agents in your browser at archora2026.com ✨
npx skills add https://github.com/richard-kim-79/archora-skills
Or manually copy the skills/ directory into your project's .agents/skills/ folder.
| Skill | Description |
|---|---|
| hypothesis | Generate falsifiable research hypotheses from notes and documents |
| validation | Design experimental protocols to test each hypothesis |
| draft | Write an IMRaD-structured paper draft |
| figure | Generate matplotlib / Mermaid visualization code |
| stats | Detect statistical errors and logical fallacies |
| counterargument | Generate devil's advocate critiques |
| peer-review | Simulate journal peer review (EIC + 3 reviewers) |
| synthesis | Surface cross-cutting themes and insights |
| wiki-sync | Sync notes into a structured wiki knowledge base |
Once installed, these skills activate automatically when you ask Claude to perform research tasks:
"Generate hypotheses from my notes"
"Write a paper draft based on this research"
"Give me a peer review of this draft"
"What are the weaknesses in my argument?"
Skills are designed to chain together across a full research pipeline:
┌─────────────┐
│ Raw Notes │ (your Markdown files, PDFs, clippings)
└──────┬──────┘
│
▼
┌─────────────┐ ┌──────────────┐
│ wiki-sync │────▶│ synthesis │ Organize & surface cross-cutting themes
└─────────────┘ └──────────────┘
│
▼
┌─────────────┐
│ hypothesis │ Generate falsifiable research questions
└──────┬──────┘
│
▼
┌──────────────┐ ┌────────┐
│ validation │───▶│ figure │ Design experiments + visualize data
└──────────────┘ └────────┘
│
▼
┌───────┐ ┌───────┐
│ stats │ │ draft │ Validate claims + write IMRaD paper
└───────┘ └───┬───┘
│
▼
┌─────────────────────┐
│ counterargument │ Stress-test before submission
│ peer-review │
└─────────────────────┘
Quick start chain (copy-paste into Claude):
1. "sync my notes into a wiki" — organize notes into wiki
2. "generate hypotheses from my notes" — generate hypotheses
3. "design experiments for each hypothesis" — design experiments
4. "validate my stats" — validate any stats
5. "write the paper draft" — write the draft
6. "peer review this draft" — simulate review
7. "generate counterarguments" — stress-test before submission
Archora is a research platform for academics and educators. Create channels, build wiki knowledge bases, and run AI research agents collaboratively in the browser.
| Web App | Claude Code Skills | |
|---|---|---|
| Best for | Team workflows, shared channels | Local files, personal research |
| Setup | Sign up at archora2026.com | npx skills add |
| Agents | Runs on your wiki & posts | Runs on local Markdown files |
| Collaboration | Multi-user, real-time | Single user |
Both use the same agent logic — pick whichever fits your workflow.
MIT
Sign in to join the discussion.
No comments yet. Be the first to say what this is good for.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.
Public repository for Agent Skills
Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…)
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
A skill to stop your coding agent from burying the answer. ADHD-friendly output.