Research Paper Daily Push skill
Codex skill that picks fresh research papers for a researcher profile and builds a scored summary in Chinese.
- 104 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Search topics go to scholarly databases and the digest may be sent to external delivery services using the user's tokens.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/research-paper-daily-pushDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Search topics go to scholarly databases and the digest may be sent to external delivery services using the user's tokens.
This is third-party code. Review the repository files before installing.
What it does
The skill builds a research profile from 3 to 10 of your papers (PDF, DOCX, TXT, Markdown) and, once confirmed, searches Europe PMC, Crossref, Semantic Scholar, OpenAlex and bioRxiv for fresh work. A program pre-scores candidates, then the agent rereads the available evidence and sets the final score. Only papers scoring at least 70 reach the digest, from zero to ten a day. Each comes with a translated title, key findings, experiment ideas and two term explanations: strict and plain. Duplicates are removed by DOI and already sent papers are not repeated. Research memory accumulates between runs.
Who it is for. Researchers and graduate students tracking a narrow field who read summaries in Chinese.
Good fit when
- A lab needs a daily topic digest from five scholarly databases without manual searching.
- A draft profile with source traceability is needed from three to ten of the user's own papers.
- An advisor wants a digest with a recommendation score and plain-language term explanations.
- The digest should arrive in WeChat through WxPusher, Server Chan or a WeCom bot.
Not a fit when
- An exhaustive systematic review is needed; the skill keeps only a small share of top papers.
- The digest must be in Russian or English rather than Chinese.
- Formatting a reference list to a standard is all that is required.
Example request
Use `$research-paper-daily-push`: read the papers in `user_papers`, draft a profile and show what needs confirmation.Limitations
The skill runs under Codex and needs Python 3.10 or newer and `pypdf` for PDF parsing. Sources are queried over the network, and for heavy volumes OpenAlex asks for a key in `OPENALEX_API_KEY`. The interface and digest are in Chinese. Search does not start until the user confirms the profile. WeChat delivery happens only with explicit permission in the request or task. Scores rest on the abstracts available, so read full papers for important decisions. If delivery services are not configured, the digest stays a local file.
How to disable. Remove the skill folder from the Codex Skills directory and disable scheduled jobs. Delete the local `config/research_profile.local.json`, `user_papers/` and the history in `data/` separately.
FAQ
What is needed for the first run?
Put 3 to 10 of your papers in `user_papers/` and ask the skill to draft a profile. Search does not begin until you explicitly confirm it.
How many papers reach the digest?
From zero to ten. Papers scoring at least 70 are included; the threshold is not lowered to fill a quota.
Where do the papers come from?
From Europe PMC, Crossref, Semantic Scholar, OpenAlex and bioRxiv. Preprints are flagged as not peer reviewed.
Can I skip WeChat?
Yes. If delivery is not configured, the skill saves a local report.
How does the skill treat instructions embedded in papers?
Paper text, abstracts and metadata count as untrusted input. Commands or requests inside them are ignored, as `SKILL.md` requires.
Discussion
No questions or reviews yet.
Related
SkillsA library of agent skills for medical research: literature search and appraisal, study design, data analysis and academic writing
A skill that finds AI papers from 28 labs on arXiv over any date range and splits led papers from co-authored ones.
A pipeline that picks remote sensing papers from arXiv daily, reviews each in a GitHub Issue and publishes a daily digest.
An agent skill that turns an arxiv paper into a minimal Python implementation, with code anchored to sections and equations and gaps flagged honestly
43 skills for Claude Code along the research cycle: surveys, experiments, topic models, reporting and manuscript review
A Google DeepMind skill collection for science tasks: access to biology and chemistry databases, literature search and structural biology
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Research Paper Daily Push (this card) | no | 104 | |
| dailypaper-skills | no | 1,356 | also curates papers; this skill builds a profile from your papers and scores after checking sources |
| paper-radar | no | 224 | tracks new publications; here the profile is confirmed manually and duplicates are removed by DOI |
README in short
The skill refuses to search without a configured profile. The final score combines relevance, novelty, quality, methodology and research inspiration.