academic-research-skills
CLAUDE.md76 starsChanged 5 days agoMITView on GitHub
This file guides Claude Code when working in this repository. Read AGENTS.md first — it is the canonical agent entry point: repository layout, development commands, host adapters, and guardrails (dual-marketplace sync, standalone-install constraint, PLAYBOOK pre-reading for browser/anti-scraping skills). Quick reference — run all of these before committing (CI repeats them):
Files
CLAUDE.md
This file guides Claude Code when working in this repository.
Read AGENTS.md first — it is the canonical agent entry point: repository layout, development commands, host adapters, and guardrails (dual-marketplace sync, standalone-install constraint, PLAYBOOK pre-reading for browser/anti-scraping skills).
Quick reference — run all of these before committing (CI repeats them):
python scripts/validate_skills.py # SKILL.md validation
python scripts/validate_plugin_json.py # plugin.json validation
python scripts/check_shared_assets.py # .mcp.json template drift
python scripts/check_marketplace_consistency.py # plugins/ <-> both marketplaces <-> REFERENCE.md
ruff check plugins/ scripts/ && ruff format --check plugins/ scripts/Key facts:
- 16 plugins: 4 platform skills (
cnki-search,sd-search,wos-search,pm-search— one per platform, sub-workflows inreferences/), 11nature-*writing skills, 1scansci-pdfretrieval bridge (paper download, citations, Zotero push via the scansci-pdf MCP server, MIT). - Literature retrieval (download/export/Zotero) belongs to
scansci-pdf; the old*-download/*-export/zotero-cslskills were removed (decision record indocs/PLAYBOOK.md). - New plugins must be registered in BOTH marketplaces (
.claude-plugin/marketplace.jsonand.agents/plugins/marketplace.json) and covered indocs/REFERENCE.md. - Maintenance handbook (failure signatures, platform status, iron rules):
docs/PLAYBOOK.md. Intent-routing manual:docs/REFERENCE.md.
In this repositoryOne other file it gives its agents.
- AGENTS.mdAGENTS.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

