blog
100 / 100 · Low risk
Fine to try.
effect.video(及同模板站点)文章类页面的书写与上线流程:模型页 /models/<slug>、blog、模型对比、产品对比。 这不是通用写作 Skill,它把我们已定的分工(X 调研交 Grok、成文交 Gemini 3.8 Flash、review 交 Claude Sonnet、设计与实现交 Claude)、 资料采集规范(只拼别人的资料、来源可核实)、页面组件标准(YouTube iframe、X 评论墙、Prompt 集合卡、参数表/对比表、shadcn 图表、引导 card)、 以及最后的评判阶段(哥飞 AI 评分、AITDK 的 SEO/关键词密度/GEO 监测、ChatGPT 匿名问答)串在一起,并和 rankup、agent-fleet、write、gefei、opencli、design 联动。 只要任务是“写/改/迁移一篇站内文章或模型页”“给模型页补视频/评价/参数表”“写模型对比或产品对比文”“把页面内容写出来”,就用它;rankup 里凡是要写页面内容都引导到这里。 触发词:/blog、封面图、配图、文章封面、写文章、写 blog、model 页…
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'blog' ] || [ -L ~/.agents/skills/'blog' ]; then echo 'A skill folder named blog already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/yan-labs/yan-skills' "$d" && git -C "$d" checkout --quiet '7c6856a9db1bd5c28cbe5047010458fc1a3e29b9' -- 'blog' && mkdir -p ~/.agents/skills && cp -R "$d"/'blog' ~/.agents/skills/'blog' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'blog' ~/.claude/skills/'blog' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/yan-labs/yan-skills/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-10 | 7c6856a | 100 |
| 2026-11-07 | 3164ecd | 100 |