AI Research Workflow · 3 Skill Sets for Literature Reviews, Paper Reading and Notes
Literature review → close reading → knowledge capture · real Skills surfaced by deep-skill-finder
Copy in one second · your Agent installs it · free, no extra credits
"Searching, reading papers, tidying notes — there goes the whole day"
“Research used to eat a full day just searching, reading papers and tidying notes. There is so much information that I cannot find what matters. I know plenty of AI tools could help, but trying them one by one costs more time than it saves.”
— Xiaohongshu · "AI does a day of research in 3 minutes" (translated from Chinese)
“I open arXiv every day and scan a pile of titles and abstracts. The painful part is not failing to understand them — it is not knowing which one deserves a careful read.”
— Xiaohongshu · arXiv close-reading tool thread (translated from Chinese)
“You may have a few core reference papers and want to write something comparable, yet you have no idea where to start or how to find your novel contribution.”
— Xiaohongshu · research-architect workflow update (translated from Chinese)
These real voices scattered across Xiaohongshu, Zhihu and X all point to the same thing: the Skills exist — people just do not know which Skill fits which stage. Testing them one at a time is slower than doing the work yourself.
Lazy route · recommended
Install deep-skill-finder once, let your Agent find Skills itself
Research runs through three stages: sweep the literature systematically, read paper by paper to extract methods and findings, then turn what you read into a reusable knowledge base. MEYO has Skills for every stage, but you do not have to hunt them down one by one — once deep-skill-finder is installed, handing your Agent a task like "review this field for me" makes it run a semantic search over the MEYO Skill library, recommend the matching Skills together with their install counts, and wait for your confirmation before installing. You say what you want to research; let the Agent pick the tools.
Copy the command → paste it to Claude Code, Codex, Cursor, WorkBuddy and the like · your Agent installs it automatically:
Please install the deep-skill-finder skill: download the archive from https://www.meyo.life/skill-finder, unpack it into the local skill directory and enable it.
Or scroll on for the per-scenario Skills. To learn more about deep-skill-finder →
meyo.life/skill
3 research scenarios · top 2 Skills in each
Below are the actual results deep-skill-finder returned from the MEYO Skill library for these three scenarios; install counts are real community data. Install them all, or pick one or two by name.
Run a literature review
What work already exists in this field?
2 Skills, 2 approaches · pick the one that fits your field · or install both and compare
Best for: you want a stable note-taking convention
A structured Markdown knowledge base protocol covering adding, organising and searching notes and projects, plus logging external sources and distilling concepts
Best for: notes already piled up · you need to reclassify them
Scans a Markdown vault, builds a semantic folder hierarchy, moves notes into place and generates MOC.md indexes at the root and in every topic folder
460 installs
💬 Join the deep-skill-finder Discord Community
Swap AI research workflow notes with other deep-skill-finder users · get help with setup
FAQ
Q: Will deep-skill-finder interrupt my research flow by searching on its own?
A: No. Your Agent only searches MEYO when you hand it an explicit task, and once it finds candidates it asks you to confirm before installing anything. Ordinary questions or sentence rewrites will not trigger it.
Q: Are these 6 Skills free? Will they burn extra API credits?
A: All 6 Skills across the 3 scenarios are free and open source. A Skill itself consumes no credits — you only pay your normal API usage when the Agent runs one. They often use fewer tokens than a long hand-written prompt, because the instruction structure is already optimised inside the Skill.
Q: I am not in CS — my field is social science, medicine or business. Will these work?
A: Yes. The literature Skills query OpenAlex, CrossRef, PubMed and Semantic Scholar, which are cross-disciplinary and not tied to one field. paper2diagram and extract-methods operate on the PDF itself, so they are field-agnostic too.
Q: Are the references reliable? Will they hallucinate citations like some AI tools?
A: These Skills pull metadata from real scholarly APIs (OpenAlex, CrossRef, PubMed and similar) rather than asking the model to recall citations from memory, so fabricated entries should not appear. Even so, spot-check a few DOIs before you cite them.
Q: I use Codex or Cursor instead of Claude Code. Can I still install these?
A: Yes. These Skills are agent-neutral, so Claude Code, Codex, Cursor and WorkBuddy all work, and the installation is identical — download the archive from MEYO and unpack it into your Agent's Skill directory.
Q: Can I skip deep-skill-finder and install just one Skill by hand?
A: Absolutely. Every Skill above has a Copy command button on the right — paste it to your Agent and it installs on its own. deep-skill-finder simply lets the Agent find Skills for you later; it is not a prerequisite.