By yunhaom94
Human-in-the-loop research ideation, planning, and literature review workflow for researchers.
npx claudepluginhub yunhaom94/agent-research-flowUse when the user shares a CS research thought — rough fragments, shorthand, keywords with a question mark, a selected line from a notes document, or a terse prompt about a paper/idea/direction — and wants collaborative development rather than a direct answer.
Use when the user asks to find related work, search literature, survey prior art, or check whether someone has already done X for a research topic or problem statement.
Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.
Use when the caller needs the full text of a single academic paper as a Markdown file — given a paper identifier (URL, DOI, arXiv ID, Semantic Scholar ID, title, or local PDF path) and a destination path, this skill locates the PDF, downloads it, and converts it to Markdown. Does NOT resolve bibliographic metadata and does NOT modify any literature index — callers handle those concerns themselves.
A Claude plugin and workspace for automating academic research workflows.
develop-idea).literature-search).zotero-manage). (Not yet implemented)Use develop-idea skill to initalize a project workspace. The process revolves around references/Ideas.md as the main workspace, where human and the AI agent collabrativly build and expand a research idea.
To load this repository as a local plugin in Claude Code, run:
git clone <this-repo-url>
claude --plugin <path-to-this-directory>
You need to set up the API key for Semantic Scholar search as an environment variable. For example, under <project_root>/.claude/settings.local.json:
"env": {
"S2_API_KEY": <your-semantic-scholar-api-key>
},
}
Team-oriented workflow plugin with role agents, 27 specialist agents, ECC-inspired commands, layered rules, and hooks skeleton.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
Complete collection of battle-tested Claude Code configs agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
AI-supervised issue tracker for coding workflows. Manage tasks, discover work, and maintain context with simple CLI commands.