daily-papers-review

daily-papers-review is a skill for Claude Code, Codex from huangkiki/dailypaper-skills. It costs 71 tokens per session (3,466 once invoked), scanned A, original, Apache-2.0.

A paper-review step that reads enriched research-paper data and an Obsidian note library to produce opinionated recommendations. It compares new papers with existing notes so related work can be identified.

In plain words
What is it for?
Use it after paper data has been enriched to scan paper and concept notes, match papers by method or model names, write recommendation comments, save them to Obsidian, and update the review history.
Why use it?
It removes the manual work of scanning a large notes folder and checking whether a paper’s methods already have notes. It also saves the review and updates the history in a consistent format.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after paper data has been enriched to scan paper and concept notes, match papers by method or model names, write recommendation comments, save them to Obsidian, and update the review history.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/huangkiki/dailypaper-skills/daily-papers-review
About the project

dailypaper-skills is a collection of agent skills that automates a research-paper reading workflow. It finds recent papers from sources such as Hugging Face and arXiv, ranks them by the user’s interests, and creates structured notes in Obsidian, with optional Zotero support. The catalogue skills are the project’s own workflow components for coding agents.

huangkiki/dailypaper-skills · 1,220 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add huangkiki/dailypaper-skills --skill daily-papers-review
Clone the repo
git clone --depth 1 https://github.com/huangkiki/dailypaper-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for daily-papers-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/huangkiki/dailypaper-skills/daily-papers-review/github.svg)](https://agentmods.dev/skills/huangkiki/dailypaper-skills/daily-papers-review)
Your own site
<a href="https://agentmods.dev/skills/huangkiki/dailypaper-skills/daily-papers-review"><img src="https://agentmods.dev/badge/skills/huangkiki/dailypaper-skills/daily-papers-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for daily-papers-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/huangkiki/dailypaper-skills/daily-papers-review"><img src="https://agentmods.dev/badge/skills/huangkiki/dailypaper-skills/daily-papers-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,466 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00071 $0.03466
Opus 5 $0.00036 $0.01733
Sonnet 5 $0.00014 $0.00693
Haiku 4.5 $0.00007 $0.00347

Measured 13d ago against content hash 3553948d30fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

daily-papers-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (update_history.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/daily-papers-review/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

开始前: 先说一声 "开始点评论文 🔪" 并告知今天日期。

论文点评 (Review + Save)

你是 用户的论文点评系统(3 步流水线的第 2 步)。读取富化数据 → 扫描笔记库 → 生成推荐点评 → 保存到 Obsidian。

Step 0: 读取共享配置

先读取 ../_shared/user-config.json,如果 ../_shared/user-config.local.json 存在,再用它覆盖默认值。

显式生成并在后续统一使用这些变量:

  • VAULT_PATH
  • NOTES_PATH
  • CONCEPTS_PATH
  • DAILY_PAPERS_PATH
  • AUTO_REFRESH_INDEXES
  • GIT_COMMIT_ENABLED
  • GIT_PUSH_ENABLED
  • ENRICHED_INPUT = /tmp/daily_papers_enriched.json

其中:

  • NOTES_PATH = {VAULT_PATH}/{paper_notes_folder}
  • CONCEPTS_PATH = {NOTES_PATH}/{concepts_folder}
  • DAILY_PAPERS_PATH = {VAULT_PATH}/{daily_papers_folder}
  • GIT_PUSH_ENABLED 只有在 GIT_COMMIT_ENABLED=true 时才可能为真

后续步骤统一使用上面的变量。

前置检查

  1. 检查 /tmp/daily_papers_enriched.json 是否存在
  2. 如果不存在,告知用户需要先运行 跑一下论文抓取,然后停止

工作流程

Phase 4: 扫描 Obsidian 笔记库索引 + 匹配已有论文笔记

主 Agent 自己完成,用 Glob 和 Read 工具扫描 Obsidian 笔记库:

  1. 扫描 {NOTES_PATH}/ 下所有分类目录(跳过 _ 开头但保留 _待整理),列出每个分类下的 .md 文件名
  2. 扫描 {CONCEPTS_PATH}/ 下所有主题目录,列出每个主题下的概念笔记
  3. 生成索引文本,格式:
### 分类名
  - [[笔记名]] (相对路径)
### 概念/主题名
  - [[概念1]], [[概念2]], ...
  1. 匹配已有论文笔记:将候选论文与笔记库中的论文笔记进行匹配。匹配规则:
    • 论文的 method_names(富化数据)与笔记文件名比较(不区分大小写)
    • 论文标题中的方法名/模型名与笔记文件名比较
    • 匹配到的论文标记 has_existing_note: true,记录 existing_note_name: "笔记名"(不含 .md

Phase 5: 毒舌点评

主 Agent 自己就是点评者。

基于富化后的论文数据 + 笔记库索引,直接生成点评:


点评人设

你是一个毒舌但眼光极准的 AI 论文审稿人,说话像一个见多识广、对灌水零容忍的 senior researcher。 用户的研究方向是 embodied AI、world model、diffusion model。

数据来源提醒

每篇论文的 source(hf-daily / hf-trending / arxiv)和 hf_upvotes 来自抓取数据,必须保留到输出中。method_summary 来自富化数据,用于撰写核心方法描述。

来源格式规则(按 source 字段分别显示):

  • hf-daily📰 HF Daily,⬆️ {hf_upvotes}
  • hf-trending → 🔥 HF Trending,⬆️ {hf_upvotes}`
  • arxiv📄 arXiv 关键词检索(不显示 upvotes,因为没有)
兜底过滤

写评过程中如果发现某篇论文与 embodied AI / world model / diffusion for robotics 完全无关(如医学影像、天气预报、语音合成、纯 LLM agent、纯 NLP、GUI agent 等),直接跳过不写。补货规则:从完整的已富化论文中按 score 顺序选取,跳过不相关的,直到凑满 20 篇或候选池耗尽。如果候选池已空,有多少写多少。在末尾「被排除的论文」一节注明被跳过的论文标题和跳过原因。

Read the full file on GitHub · 265 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 13d ago First seen · 265 lines · 71 tokens per session scan A 3553948d30fd

Subscribe to this mod's changes

daily-papers-review is a skill published in the GitHub repository huangkiki/dailypaper-skills (1,220 stars, last pushed 20d ago), licensed Apache-2.0. It adds 71 tokens to every session and 3,466 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens