Publish Tracelab Huggingface
uw-syfi/TraceLab
Prepare, publish, refresh, or validate the TraceLab public dataset on Hugging Face under UW-SyFI/TraceLab.
抓取并分析"数据库、AI、GitHub、AI论文"相关的近1周内最新内容,分类汇总,输出图文并茂(含内置 Mermaid 图)的 Markdown 周报到当前项目的 markdown/ 目录。
$ npx skills add digoal/blog --skill db-ai-github-paper-weekly-news -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install digoal/blog db-ai-github-paper-weekly-news --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skills_for_claude_web/db-ai-github-paper-weekly-news .claude/skills/db-ai-github-paper-weekly-news && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "db-ai-github-paper-weekly-news" agent skill from https://github.com/digoal/blog/tree/master/skills/skills_for_claude_web/db-ai-github-paper-weekly-news into .claude/skills/db-ai-github-paper-weekly-news/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "db-ai-github-paper-weekly-news", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/digoal/blog/tree/master/skills/skills_for_claude_web/db-ai-github-paper-weekly-newsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add digoal/blog --skill db-ai-github-paper-weekly-news -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install digoal/blog db-ai-github-paper-weekly-news --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/skills_for_claude_web/db-ai-github-paper-weekly-news .agents/skills/db-ai-github-paper-weekly-news && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "db-ai-github-paper-weekly-news" agent skill from https://github.com/digoal/blog/tree/master/skills/skills_for_claude_web/db-ai-github-paper-weekly-news into .agents/skills/db-ai-github-paper-weekly-news/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "db-ai-github-paper-weekly-news", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add digoal/blog --skill db-ai-github-paper-weekly-news -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install digoal/blog db-ai-github-paper-weekly-news --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/skills_for_claude_web/db-ai-github-paper-weekly-news .cursor/skills/db-ai-github-paper-weekly-news && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "db-ai-github-paper-weekly-news" agent skill from https://github.com/digoal/blog/tree/master/skills/skills_for_claude_web/db-ai-github-paper-weekly-news into .cursor/skills/db-ai-github-paper-weekly-news/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "db-ai-github-paper-weekly-news", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/digoal/blog.git --path skills/skills_for_claude_web/db-ai-github-paper-weekly-news--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add digoal/blog --skill db-ai-github-paper-weekly-news -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install digoal/blog db-ai-github-paper-weekly-news --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/skills_for_claude_web/db-ai-github-paper-weekly-news .gemini/skills/db-ai-github-paper-weekly-news && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "db-ai-github-paper-weekly-news" agent skill from https://github.com/digoal/blog/tree/master/skills/skills_for_claude_web/db-ai-github-paper-weekly-news into .gemini/skills/db-ai-github-paper-weekly-news/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "db-ai-github-paper-weekly-news", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install digoal/blog db-ai-github-paper-weekly-newsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add digoal/blog --skill db-ai-github-paper-weekly-news -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/skills_for_claude_web/db-ai-github-paper-weekly-news .github/skills/db-ai-github-paper-weekly-news && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "db-ai-github-paper-weekly-news" agent skill from https://github.com/digoal/blog/tree/master/skills/skills_for_claude_web/db-ai-github-paper-weekly-news into .github/skills/db-ai-github-paper-weekly-news/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "db-ai-github-paper-weekly-news", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add digoal/blog --skill db-ai-github-paper-weekly-news -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install digoal/blog db-ai-github-paper-weekly-news --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/skills_for_claude_web/db-ai-github-paper-weekly-news .opencode/skills/db-ai-github-paper-weekly-news && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "db-ai-github-paper-weekly-news" agent skill from https://github.com/digoal/blog/tree/master/skills/skills_for_claude_web/db-ai-github-paper-weekly-news into .opencode/skills/db-ai-github-paper-weekly-news/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "db-ai-github-paper-weekly-news", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
db-ai-github-paper-weekly-news抓取并分析"数据库、AI、GitHub、AI论文"相关的近1周内最新内容,分类汇总,输出图文并茂(含内置 Mermaid 图)的 Markdown 周报到当前项目的 markdown/ 目录。
DB AI GitHub Paper Weekly News is an agent skill from digoal/blog. 抓取并分析"数据库、AI、GitHub、AI论文"相关的近1周内最新内容,分类汇总,输出图文并茂(含内置 Mermaid 图)的 Markdown 周报到当前项目的 markdown/ 目录。 覆盖数据源:PostgreSQL Weekly、Planet PostgreSQL、Planet PostGIS、PostgreSQL 官方新闻、PostgreSQL Git 提交记录、DuckDB 新闻、AI每日资讯(aibase.com、ai-bot.cn)、GitHub Trending(周榜)、HuggingFace 热门论文。 触发条件:用户提到"数据库周报"、"AI周报"、"GitHub 周报"、"AI 论文周报"、"db weekly"、"抓取本周数据库新闻"、"抓取本周AI动态"、"生成技术周报"、"帮我整理本周的数据库/AI/Github/论文动态"、"weekly news"、"weekly report"、"周刊",或用户希望获取 DB/AI/GitHub/Paper 领域近期综合资讯时,必须使用本 skill。即使用户只说"帮我看看这周有什么技术大事"或"PostgreSQL 最近有什么新闻",也应使用本…
Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Databases, covering Diagrams, Model hubs and datasets and Git workflow. It works with GitHub, PostgreSQL, Mermaid and Hugging Face. The repository describes itself as: AI,Opensource,Database,Business,Finance,Minds. git clone --depth 1 https://github.com/digoal/blog. The licence is GPL-2.0.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit ad6fcb7. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are mermaid, bash and markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
postgresweekly.compostgresql.orggit.postgresql.orgduckdb.orgaibase.comai-bot.cngithub.comhuggingface.coarxiv.orgplanet.postgresql.orgplanet.postgis.netFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
DB AI GitHub Paper Weekly News loads about 2.4k tokens when it runs. Until then it costs about 139 tokens; SKILL.md has 248 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from digoal/blog at commit ad6fcb7, republished under its GPL-2.0 licence (© digoal). 248 words, ~2,430 tokens.
.claude/skills/db-ai-github-paper-weekly-news/SKILL.md (or your agent's skills folder).核心目标:每次运行,抓取并整合 10 个权威数据源在最近 7 天内发布的内容,去重、分类、分析,产出一份对数据库工程师、AI 研究者、开源爱好者都有价值的技术周报。
| # | 分类 | 数据源 URL | 抓取策略 |
|---|---|---|---|
| 1 | 🐘 PostgreSQL 周刊 | https://postgresweekly.com/issues | 先获取列表页,找最新期号,再抓具体期 |
| 2 | 🐘 Planet PostgreSQL | https://planet.postgresql.org/ | 直接抓,过滤7天内文章 |
| 3 | 🗺️ Planet PostGIS | https://planet.postgis.net/ | 直接抓,过滤7天内文章 |
| 4 | 📣 PostgreSQL 官方新闻 | https://www.postgresql.org/about/newsarchive/ | 直接抓,过滤7天内条目 |
| 5 | 🔧 PostgreSQL Git 提交 | https://git.postgresql.org/gitweb/?p=postgresql.git;a=shortlog | 直接抓,过滤7天内提交 |
| 6 | 🦆 DuckDB 新闻 | https://duckdb.org/news/ | 直接抓,过滤7天内文章 |
| 7 | 🤖 AI Base 每日资讯 | https://www.aibase.com/zh | 直接抓,若内容简单则钻取文章页 |
| 8 | 🤖 AI Bot 每日新闻 | https://ai-bot.cn/daily-ai-news/ | 直接抓,若内容简单则钻取文章页 |
| 9 | ⭐ GitHub Trending 周榜 | https://github.com/trending?since=weekly&spoken_language_code= | 直接抓,提取排名前20 repo |
| 10 | 📄 HuggingFace 热门论文 | https://huggingface.co/papers/trending | 直接抓,若内容简单则钻取论文页 |
mkdir -p markdown
TODAY=$(date +%Y%m%d)
WEEK_START=$(date -d "7 days ago" +%Y-%m-%d 2>/dev/null || date -v-7d +%Y-%m-%d)输出本次周报的时间范围:{WEEK_START} ~ {TODAY}。
⚠️ 所有抓取使用
web_fetch。遇到需要真人验证(Cloudflare / reCAPTCHA)时,改用web_search搜索站点名+关键词,从搜索结果摘要中提取内容。
Step A: web_fetch("https://postgresweekly.com/issues")
Step B: 解析 HTML,找到最新期号 N(如 href="/issues/652" 中的 652)
Step C: web_fetch("https://postgresweekly.com/issues/{N}")
Step D: 提取本期所有文章标题、URL、摘要若 Step A 被封锁:web_search("site:postgresweekly.com issues 2025") 推断最新期号。
web_fetch(URL)
→ 提取 <article> / <item> / <entry> 等块
→ 检查日期字段(pubDate / updated / datetime),过滤7天内
→ 若内容只有标题+摘要,则 web_fetch 原文 URL 获取正文前500字web_fetch("https://www.postgresql.org/about/newsarchive/")
→ 找到 <li> 条目,提取标题+日期+链接
→ 过滤7天内
→ 钻取每条新闻的详情页(内容通常很短,必须钻取)web_fetch("https://git.postgresql.org/gitweb/?p=postgresql.git;a=shortlog")
→ 提取 commit 列表(哈希、作者、日期、subject)
→ 过滤7天内提交
→ 按主题分组:性能、修复、新功能、文档、测试
→ 重要提交(非修复类)钻取 commit 详情页web_fetch("https://duckdb.org/news/")
→ 提取博客/新闻列表,过滤7天内
→ 若列表简短,钻取每篇文章首段web_fetch("https://www.aibase.com/zh")
→ 提取今日/本周推荐内容
→ 若内容过于简单(只有标题),钻取前5条详情
web_fetch("https://ai-bot.cn/daily-ai-news/")
→ 提取最新一期(或最近7天的条目)
→ 若内容过于简单,钻取文章页若被封锁:web_search("aibase.com AI新闻 本周 2025") + web_search("ai-bot.cn 每日AI新闻 2025")。
web_fetch("https://github.com/trending?since=weekly&spoken_language_code=")
→ 提取所有 repo(名称、描述、语言、本周 star 增量、总 star 数)
→ 按语言/主题归类
→ 重点 repo 访问 README 获取1句话描述(若描述不够清晰)若被封锁:web_search("github trending weekly 2025 AI database") 辅助补充。
web_fetch("https://huggingface.co/papers/trending")
→ 提取论文列表(标题、摘要、upvote数、发布日期)
→ 过滤7天内,按 upvote 排序取前10
→ 摘要不足100字的钻取论文详情页(或访问 arxiv 摘要)将所有抓取内容按以下6个分类整理:
A. 🐘 PostgreSQL 生态 — PG Weekly + Planet PG + 官方新闻 + Git提交
B. 🦆 DuckDB & 数据库周边 — DuckDB + 其他DB动态(从AI资讯中筛选)
C. 🤖 AI 每日动态 — AIBase + AI-Bot(模型发布、产品更新、行业动态)
D. ⭐ GitHub 开源热榜 — GitHub Trending(AI/DB/工具/语言分类)
E. 📄 AI 论文精选 — HuggingFace Trending Papers
F. 🔧 工程与实践 — 从各源中提取实操、教程、最佳实践类内容去重规则:同一事件在多个源出现时,合并为一条,标注"来源:A+B"。
对每条内容评分(1-5星),依据:
每个分类按评分从高到低排列。
必须生成以下3张图,内嵌在 Markdown 中:
graph TD
PW[PostgreSQL Weekly] --> PG[🐘 PG生态分类]
Planet[Planet PostgreSQL] --> PG
PostGIS[Planet PostGIS] --> PG
PGNews[PG官方新闻] --> PG
GitLog[PG Git提交] --> PG
DuckDB[DuckDB新闻] --> DB[🦆 数据库周边]
AIBase[AIBase资讯] --> AI[🤖 AI动态]
AIBot[AI-Bot新闻] --> AI
GitHub[GitHub Trending] --> GH[⭐ 开源热榜]
HF[HuggingFace Papers] --> Paper[📄 论文精选]根据抓取内容,找出本周最热的3-5个技术主题(如"AI Agent"、"PG 18 开发进展"、"向量数据库"等),画出主题之间的关联:
graph LR
主题A --> 主题B
主题A --> 主题C
主题B --> 主题D
...统计本周 GitHub Trending 中各编程语言的占比:
pie title GitHub Trending 本周语言分布
"Python" : 12
"Rust" : 4
"TypeScript" : 5
...以上数据根据实际抓取结果填写,不要使用占位数字。
按以下模板输出完整 Markdown,所有章节必须存在:
# 🗞️ DB × AI × GitHub × Paper 技术周报
> 期号:第 {N} 期 | 时间范围:{WEEK_START} ~ {TODAY} | 生成时间:{DATETIME}
---
## 📋 本周摘要
> 用3-5句话,总结本周最值得关注的技术动态(跨领域综合)
**本周关键词**:`关键词1` · `关键词2` · `关键词3` · `关键词4` · `关键词5`
---
## 数据源覆盖总览
[图1:数据源覆盖 Mermaid 图]
---
## A. 🐘 PostgreSQL 生态
> 来源:PostgreSQL Weekly #{N}、Planet PostgreSQL、PG官方新闻、Git提交记录
### 🔥 重磅内容
[⭐⭐⭐⭐⭐ / ⭐⭐⭐⭐ 的内容,含标题、摘要、原文链接]
### 📌 Git 提交亮点(本周)
| 类别 | 提交主题 | 作者 | 日期 |
|------|---------|------|------|
| 新功能 | ... | ... | ... |
| 性能 | ... | ... | ... |
| 修复 | ... | ... | ... |
### 其他更新
[⭐⭐⭐ 及以下内容]
---
## B. 🦆 DuckDB & 数据库周边
> 来源:DuckDB News、AI资讯中的DB相关内容
[重磅内容 + 其他更新,同上格式]
---
## C. 🤖 AI 每日动态
> 来源:AIBase、AI-Bot每日AI新闻
### 🔥 本周AI大事
[⭐⭐⭐⭐⭐ 内容:模型发布、重大产品更新、行业动态]
### 📅 逐日速览
| 日期 | 事件 | 重要程度 |
|------|------|---------|
| {日期} | ... | ⭐⭐⭐⭐⭐ |
| ... | ... | ... |
---
## D. ⭐ GitHub 开源热榜(本周)
> 来源:GitHub Trending (since=weekly)
[图3:语言分布 Mermaid 饼图]
### 🏆 Top Repos(按周 Star 增量)
| 排名 | Repo | 语言 | 本周 ⭐ | 描述 |
|------|------|------|--------|------|
| 1 | [name](url) | Python | +2.3k | ... |
| ... | ... | ... | ... | ... |
### 按主题分类
**🤖 AI / LLM 相关**
- [repo-name](url):...
**🗄️ 数据库 / 存储相关**
- [repo-name](url):...
**🛠️ 开发工具 / 基础设施**
- [repo-name](url):...
---
## E. 📄 AI 论文精选(HuggingFace Trending)
> 来源:HuggingFace Papers Trending,过滤近7天,按 upvote 排序
### Top 10 热门论文
| # | 标题 | upvote | 核心贡献(一句话) | arxiv |
|---|------|--------|-----------------|-------|
| 1 | ... | 🔺NNN | ... | [link] |
| ... | ... | ... | ... | ... |
### 深度解读(Top 3)
对 upvote 最高的3篇论文,各写100-200字解读:
#### 📄 [论文标题]
- **问题**:解决了什么问题
- **方法**:核心思路
- **结论**:主要结果
- **意义**:对业界的影响
---
## F. 🔧 工程实践精选
> 从各数据源中筛选出有实操价值的教程、最佳实践、工具推荐
[每条包含:标题、来源、一句话价值说明、原文链接]
---
## 🔗 本周技术热点关系图
[图2:热点关系 Mermaid 图]
---
## 📌 编辑推荐(TOP 5)
> 如果你只有5分钟,这周最值得读的5条内容:
1. 🥇 **[标题]** — [一句话理由] → [链接]
2. 🥈 **[标题]** — [一句话理由] → [链接]
3. 🥉 **[标题]** — [一句话理由] → [链接]
4. **[标题]** — [一句话理由] → [链接]
5. **[标题]** — [一句话理由] → [链接]
---
## 📊 本周数据汇总
| 分类 | 抓取条目数 | 7天内有效 | 精选入报 |
|------|----------|---------|---------|
| 🐘 PostgreSQL 生态 | N | N | N |
| 🦆 DuckDB & DB周边 | N | N | N |
| 🤖 AI 动态 | N | N | N |
| ⭐ GitHub Trending | N | N | N |
| 📄 AI 论文 | N | N | N |
| 🔧 工程实践 | N | N | N |
| **合计** | **N** | **N** | **N** |
---
*本报告由 Claude 自动抓取生成,内容来源均已标注。如有遗漏或错误,欢迎反馈。*
*下期预计发布:{下次周报日期}*| 场景 | 处理方式 |
|---|---|
| URL 返回 403/429 | 改用 web_search("site:xxx.com ...") 补充 |
| Cloudflare 验证拦截 | 使用 web_search 搜索该站近期内容 |
| 内容为空/极少 | 标注"本周无新内容",不强行填充 |
| 找不到最新期号 | 用 web_search("postgresweekly latest issue 2025") 辅助 |
| 日期无法解析 | 保守估计,宁可多保留(7+2天缓冲) |
| 论文无摘要 | 访问 https://arxiv.org/abs/{id} 获取 |
| GitHub 被封 | 使用 web_search("github trending weekly AI 2025") |
# 文件命名:YYYYMMDD_db-ai-github-paper-weekly.md
# 保存路径:markdown/
mkdir -p markdown
# 文件内容见 Step 5 模板保存完成后输出:
输出前逐项核对:
□ 所有10个数据源都尝试过抓取(即使部分为空)?
□ postgresweekly 已找到最新期号并钻取详情?
□ 内容均已过滤到7天内(或标注了日期缺失的情况)?
□ 3张 Mermaid 图均已生成且数据是真实的(非占位符)?
□ GitHub Trending 至少列出了15个 repo?
□ HuggingFace 论文有 Top 3 的深度解读?
□ 每条内容都有原文链接?
□ 去重已执行(同一事件不重复出现)?
□ "编辑推荐 TOP 5"跨越了至少3个不同分类?
□ markdown/ 目录存在且文件已保存?
□ 数据汇总表中的数字与正文一致?为节省时间,以下数据源可同时发起请求(无依赖关系):
并行组 A(无需预处理):
- Planet PostgreSQL
- Planet PostGIS
- PostgreSQL 官方新闻
- PostgreSQL Git shortlog
- DuckDB 新闻
- GitHub Trending
- HuggingFace Papers
串行组 B(需先获取列表页):
- PostgreSQL Weekly(先获取期号)
- AIBase(先获取列表,再钻取详情)
- AI-Bot(先获取列表,再钻取详情)## A. 🐘 PostgreSQL 生态
### 🔥 重磅内容
#### PostgreSQL 18 Beta 2 发布 ⭐⭐⭐⭐⭐
> 来源:PostgreSQL 官方新闻 | 2025-06-12
PostgreSQL 18 Beta 2 已发布,包含以下重要改进:OAuth 2.0 设备授权流支持、
`MERGE` 语句增强(支持 `RETURNING`)、pg_basebackup 性能提升约 30%。
建议开发者在生产环境迁移前重点测试扩展兼容性。
🔗 [官方公告](https://www.postgresql.org/about/news/...)
---
## E. 📄 AI 论文精选
### Top 10 热门论文
| # | 标题 | upvote | 核心贡献(一句话) | arxiv |
|---|------|--------|-----------------|-------|
| 1 | FlashAttention-3 | 🔺2847 | H100 上注意力计算速度提升 2.6x | [2407.08608](https://arxiv.org/abs/2407.08608) |
### 深度解读:FlashAttention-3
- **问题**:H100 GPU 有 FP8 和异步特性,但 FA2 未充分利用
- **方法**:Warp 专业化 + 流水线异步化 + FP8 精度
- **结论**:在 H100 上达到 740 TFLOPS,接近硬件峰值的 75%
- **意义**:Transformer 训练和推理成本将进一步降低,直接惠及所有大模型训练场景以上即为 db-ai-github-paper-weekly-news Skill 的完整指南。
每次运行请严格遵循抓取 → 分类 → 评分 → 制图 → 撰写 → 自检 → 保存的顺序。
© digoal, GPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/skills_for_claude_web/db-ai-github-paper-weekly-news of digoal/blog.
Open the folder on GitHubat commit ad6fcb7
DB AI GitHub Paper Weekly News next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| DB AI GitHub Paper Weekly News this skilldigoal/blog | 8.6k | — | ~2.4k | Automated safety check: Pass | GPL-2.0 | |
| Publish Tracelab Huggingfaceuw-syfi/TraceLab | 142 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Database Scoutzebbern/claude-code-guide | 4.7k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Setup Devrelytcloud/pg_ducklake | 143 | — | ~2k | Automated safety check: Notes | MIT | |
| Data Model CreationTencentCloudBase/CloudBase-AI-Toolkit | 1.1k | 1 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Database Inspectorrongxinzy/RongxinAI | 154 | — | ~835 | Automated safety check: Pass | MIT |
uw-syfi/TraceLab
Prepare, publish, refresh, or validate the TraceLab public dataset on Hugging Face under UW-SyFI/TraceLab.
zebbern/claude-code-guide
Explore SQLite and PostgreSQL databases: list tables, inspect schemas (columns/types/constraints), preview data, generate Mermaid ER diagrams, and run safe read-only queries.
relytcloud/pg_ducklake
Dev environment setup for build tools, PostgreSQL, submodules, and worktrees.
TencentCloudBase/CloudBase-AI-Toolkit
[Deprecated] Optional advanced tool for complex data modeling.
rongxinzy/RongxinAI
探索 SQLite 或 PostgreSQL 数据库,执行安全只读查询,提供表列表、详细表结构(列/类型/约束/索引)、数据预览,并生成 Mermaid ER 图。当用户需要查看数据库架构、探索表关系、预览数据、执行只读查询,或提及 schema、ER 图、SQL 查询、数据预览、describe table、数据库探索等关键词时触发。
HKUDS/OpenHarness
Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.
digoal/blog
三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…
digoal/blog
Find latent bugs in a local PostgreSQL source tree (RELxxSTABLE branch or HEAD) the way a core hacker does: build a heavily-poisoned debug instance (cassert + cache-discard + -O0/-ggdb3 + core…
digoal/blog
Portable digital employee distilled from digoal's personal blog for PostgreSQL, PolarDB, DuckDB, AI+database, vector/RAG, database operations, source-code reading, technical content creation…
digoal/blog
从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读,并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…
digoal/blog
Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles…
digoal/blog
Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points.
Categories
抓取并分析"数据库、AI、GitHub、AI论文"相关的近1周内最新内容,分类汇总,输出图文并茂(含内置 Mermaid 图)的 Markdown 周报到当前项目的 markdown/ 目录。. DB AI GitHub Paper Weekly News is an agent skill from digoal/blog.
DB AI GitHub Paper Weekly News fits situations like: tasks that involve Diagrams; tasks that involve Model hubs and datasets; tasks that involve Git workflow.
Run `npx skills add digoal/blog --skill db-ai-github-paper-weekly-news -a claude-code`. Or copy the skill folder (skills/skills_for_claude_web/db-ai-github-paper-weekly-news in digoal/blog) into .claude/skills/db-ai-github-paper-weekly-news in your project. Claude Code loads it when a task matches its description.
Run `npx skills add digoal/blog --skill db-ai-github-paper-weekly-news -a codex`. Or copy the skill folder (skills/skills_for_claude_web/db-ai-github-paper-weekly-news in digoal/blog) into .agents/skills/db-ai-github-paper-weekly-news in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add digoal/blog --skill db-ai-github-paper-weekly-news -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/db-ai-github-paper-weekly-news, .gemini/skills/db-ai-github-paper-weekly-news, .github/skills/db-ai-github-paper-weekly-news and .opencode/skills/db-ai-github-paper-weekly-news in your project.
SKILL.md names no scripts, command-line tools or credentials: DB AI GitHub Paper Weekly News is instructions for the agent only. Our summary lists: Python 3.
SKILL.md names 11 domains. In commands or code: postgresweekly.com, postgresql.org, git.postgresql.org, duckdb.org, aibase.com, ai-bot.cn, github.com, huggingface.co, arxiv.org, planet.postgresql.org and planet.postgis.net; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
DB AI GitHub Paper Weekly News is published under the GPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.4k tokens (SKILL.md is roughly 9.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with DB AI GitHub Paper Weekly News: Publish Tracelab Huggingface (uw-syfi/TraceLab, 142 stars), Database Scout (zebbern/claude-code-guide, 4.7k stars), Setup Dev (relytcloud/pg_ducklake, 143 stars) and Data Model Creation (TencentCloudBase/CloudBase-AI-Toolkit, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
digoal (a GitHub user) maintains it in digoal/blog, which has 8,588 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on October 9, 2026.
Source: digoal/blog on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.