Daily Research Papers — AI skill for Claude Code
One AI paper per day - summaries and coding-agent skills.
How to install Daily Research Papers
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Ar9av/daily-research-papers and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Daily Research Papers does
One AI paper per day - summaries and coding-agent skills.
Alternatives in AI
- Welcome — AI Research Skills — You now have access to 86 production-ready skills covering the entire AI research lifecycle: literature survey 5.4k ★
- Research Paper Writing Skills — Skill package for ML/CV/NLP paper writing, curated and adapted from Prof 1.5k ★
- Academic Commercialization Agent — Turn any research paper into a commercialization report — 6 AI agents, TRL/MRL scoring, patent landscape, mark 581 ★
README
daily-research-papers
One AI paper per day — plain-English summaries, coding-agent skills, and runnable Python scripts.
Each folder is `YYYY-MM-DD-/` and contains:
paper.md— what the paper says, key numbers, builder takeawayskill.md— how to apply the paper's ideas in a coding agentscripts/— runnable Python implementations of the core ideas
Index
| Date | Paper | Skill | Scripts |
|---|---|---|---|
| 2026-06-15 | MemJack — any unmodified natural image is a jailbreak vector; 71% ASR on 5,000 COCO images; removing memory drops ASR 72→38%; direct refusal is the worst VLM defense | skill | scripts/ |
| 2026-06-14 | Creative Machine — 10 requirements for genuine machine creativity (Designics); R3/R7/R9 unsatisfied by all current AI; ethics must be internal to perception, not a post-generation filter | skill | scripts/ |
| 2026-06-13 | CODE — one poisoned RAG document causes 5–25× reasoning token inflation with no accuracy drop; tri-agent attack: Contradiction Architect + Conflict Weaver + Style Adapter | skill | scripts/ |
| 2026-06-12 | SpatialClaw — persistent Python kernel as action interface for spatial VLM agents; +11.2 pp over prior SOTA, 20 benchmarks, no model-specific tuning | skill | scripts/ |
| 2026-06-11 | SCAIL-2 — end-to-end character animation without pose skeletons; 28-channel mask conditioning + mode-specific RoPE; 93.3% win on multi-character identity isolation | skill | scripts/ |
| 2026-06-10 |
Related Skills
Research Builder
Research and paper-writing skill for Claude Code and Codex: faithful baselines, rigorous experiments, bilingua
Delta Papers
主要ジャーナルとプレプリントサーバーから関心論文を取得し、Claude が日本語で要約・分野動向をまとめて Gmail 配信する Claude Code skill。Daily AI-summarized researc
Engineering Notebook
A Bun CLI that ingests Claude Code and Codex session transcripts, generates LLM-powered daily summaries, and s
AI News
Automated AI news summaries (daily/weekly/monthly/quarterly/yearly) generated by Claude Code remote agents
Chat History Importer
Import AI conversation exports (OpenAI ChatGPT and Anthropic Claude) into your agent's episodic memory. Parses
Academic Writing Skills
AI-powered post-writing toolkit for academic papers — format validation, grammar/style polishing, de-AI editin
Related Agents
Paper Crawler
Collects and classifies research papers from DBLP and OpenAlex APIs for literature surveys
Synthesizer
Research paper synthesis specialist. Compiles evidence from lit scouts into coherent academic papers. Use when
Paper Writer
Scientific writing specialist for research papers — argument structure, claim-evidence chains, narrative arc