公众号技术传播风格规范
生成面向中文技术从业者的技术科普类公众号文章，要求语言通俗有力、类比精准、结构清晰，且严格禁用非标准符号（如 emoji、特殊分隔符、装饰性标点）。
npx skills add ECNU-ICALK/AutoSkill --skill 公众号技术传播风格规范 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# 公众号技术传播风格规范 生成面向中文技术从业者的技术科普类公众号文章，要求语言通俗有力、类比精准、结构清晰，且严格禁用非标准符号（如 emoji、特殊分隔符、装饰性标点）。 ## Prompt # Goal Generate a WeChat Official Account (gongzhonghao) article on a technical AI topic for Chinese engineering practitioners — clear, engaging, and production-ready. # Constraints & Style - Use only standard ASCII punctuation and Chinese characters; absolutely NO emojis (e.g., 🌱, 📱, ❌, ✅), NO decorative symbols (e.g., "---", "###", ">" used decoratively), NO non-standard bullets or dividers. - Replace all emoji-driven emphasis with concise verbal emphasis (e.g., replace "📱手机端App..." → "手机端App..."). - Maintain strong rhetorical structure: lead with a vivid metaphor or question, follow with "是什么/为什么/怎么用" logic, include concrete benchmarks or real-world constraints. - Prioritize analogies grounded in professional experience (e.g., doctors, engineers, teachers) over pop-culture or abstract metaphors. - All data points (e.g., "37%", "<0.8%", "500条") must be preserved verbatim — no rounding or paraphrasing. - Preserve all technical terms in original form (e.g., "EWC", "Replay Buffer", "L2P", "LoRA") and retain code identifiers (e.g., `avalanche`, `datasets`, `transformers`). - Keep sec
- Prompt
- Triggers
What does the 公众号技术传播风格规范 skill do?
生成面向中文技术从业者的技术科普类公众号文章，要求语言通俗有力、类比精准、结构清晰，且严格禁用非标准符号（如 emoji、特殊分隔符、装饰性标点）。
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill 公众号技术传播风格规范 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ECNU-ICALK/AutoSkill, a repository with 539 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.