duyunzhoudyz/dyz-gongwen-skills / skills/gongwen-humanize
gongwen-humanize
Verified公文去 AI 味:把 AI 腔重的公文改成熟手写法:事实冻结、表达放开,宏大开头、空泛总括、段尾拔高、名词堆叠、翻案句、破折号、新八股词等命中的句子改到位;保留有实质内容的“一是……二是……”;口号式小标题改写实;可只标注不改或轻度改写。用户说“去 AI 味”“AI 腔太重”“读着像机器写的”“DeepSeek 写的总结改自然点”“降 AI 率”时使用(只做文风改进,不承诺检测结果)。以免责、对冲、态度不明为主的转 gongwen-direct;格式、标点、数字和提法转 gongwen-review;压缩篇幅转 gongwen-polish;起草新稿转对应起草 skill。
evals/trigger.json
View on GitHub[
{"query": "这篇总结是 DeepSeek 写的,一股 AI 味,帮我改改", "should_trigger": true},
{"query": "读着像机器写的,帮我把 AI 腔去掉,数字别动", "should_trigger": true},
{"query": "帮我看看这份汇报哪些地方 AI 味重,先别改,标出来就行", "should_trigger": true},
{"query": "稿子里全是“不是……而是……”和破折号,帮我顺一顺", "should_trigger": true},
{"query": "领导说“赋能”“闭环”太多,像网上抄的,帮我清理一下这些词", "should_trigger": true},
{"query": "豆包生成的讲话稿太像 AI 了,改得像人写的", "should_trigger": true},
{"query": "学校要查 AI 率,帮我把这篇教研总结的 AI 味降一降", "should_trigger": true},
{"query": "轻度去一下 AI 痕迹就行,结构别动", "should_trigger": true},
{"query": "这篇信息稿开头“随着……”、结尾“未来可期”,太 AI 了,帮我改", "should_trigger": true},
{"query": "实施方案里的 AI 套话帮我清一下,一是二是和小标题别动", "should_trigger": true},
{"query": "帮我把这个请示里“可能”“建议考虑”这些含糊的话改成明确表态", "should_trigger": false},
{"query": "通知里“仅供参考”“请结合实际”这种免责的话太多,帮我删掉,语气改坚决点", "should_trigger": false},
{"query": "这个批复写得模棱两可,帮我改成明确同意", "should_trigger": false},
{"query": "帮我核一下这篇稿子,标点、数字用法和格式有没有问题", "should_trigger": false},
{"query": "送签前帮我按八关把一下关,列个问题清单", "should_trigger": false},
{"query": "这篇材料里的提法是不是最新的,帮我查一下", "should_trigger": false},
{"query": "下周要交科室年终总结,素材我发你,帮我写一篇", "should_trigger": false},
{"query": "给这篇汇报材料提炼几个对仗的小标题", "should_trigger": false},
{"query": "把这篇稿子排成国标格式的 Word", "should_trigger": false},
{"query": "这篇太长了,帮我压到2000字", "should_trigger": false}
]
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |