Fetch papers from HuggingFace Daily Papers feed and generate a digest with analysis.
powershell
# Windows PowerShell
$env:HF_TOKEN = "hf_xxxxxxxxxxxxx"
# macOS / Linux / Git Bash
export HF_TOKEN="hf_xxxxxxxxxxxxx"
The script reads
HF_TOKENfromos.environ. If not set, it exits with a clear error message.
bash
cd <skill-path>/scripts && python hf_papers.py [date YYYY-MM-DD]
hf_results.json (saved in the working directory)Read hf_results.json. Fields:
FieldDescriptionpaperIdarXiv IDtitlePaper titlevotesCommunity upvotessubmittedBySubmitter nameorganizationResearch institutionsummaryFull abstract (cleaned, up to 2000 chars)aiSummaryAI-generated summary (200-300 chars, from HF blue box)githubRepoGitHub repo URL if availablekeywordsAI-extracted keywords (up to 10)linkHF paper pagearxivLinkarXiv abstract page
Scoring reference (10-point scale, intuition-based):
DimensionWeightBonus signalsInnovation0-3New benchmark/dataset, novel direction, first-of-its-kindPracticality0-3Has GitHub code, clear real-world application, big tech/academiaTechnical depth0-2Summary >200 chars, contains RL/MCTS/evolutionary methodsInterestingness0-2Provocative thesis, cross-discipline, counterintuitive
High vote count (>10) is a bonus — reflects community heat.
text
📄 HF Daily Papers · [date] N papers total
## 🔴 Must Read (score 8-10)
[Title | ID | Organization
Xiaolongxia comment: ...]
## 🟡 Worth Noting (score 6-7)
[Compact list + one-line evaluation]
## 🟢 Skim If Interested
[Ultra brief list]
## 🦞 Summary
Top 3 + today's main theme observations
Commentary guidelines: