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.
npx skills add Holden323/ldm-skill --skill ldm-ai-to-human-zhgit clone --depth 1 https://github.com/Holden323/ldm-skillWrote 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.
[](https://agentmods.dev/skills/holden323/ldm-skill/ldm-ai-to-human-zh)<a href="https://agentmods.dev/skills/holden323/ldm-skill/ldm-ai-to-human-zh"><img src="https://agentmods.dev/badge/skills/holden323/ldm-skill/ldm-ai-to-human-zh/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.
<a href="https://agentmods.dev/skills/holden323/ldm-skill/ldm-ai-to-human-zh"><img src="https://agentmods.dev/badge/skills/holden323/ldm-skill/ldm-ai-to-human-zh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00164 | $0.01294 |
| Opus 5.5 | $0.00066 | $0.00518 |
| Sonnet 5.5 | $0.00033 | $0.00259 |
| Haiku 4.5 | $0.00016 | $0.00129 |
Grade A, and why
ldm-ai-to-human-zh 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 1mo ago.
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.
This is a copy
89% identical to smart-search — 177 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
中文去 AI 味
目标是让文字更像具体的人在具体场景里表达，而不是机械替换一组“AI 高频词”。
先判断用户要什么
- 只要审查：给出最影响阅读的候选问题和少量代表性例子，不改原文。
- 直接改写：完成改写，不额外停下来询问是否修改。
- 审查并改写：先简述主要判断，再给改写结果。
- 用户指定语气、长度、平台或禁改内容时，以这些要求为准。
输入是聊天中的文本时，直接在对话中返回。输入是文件时，遵循用户指定的保存方式；未指定覆盖时，默认保留原文件并创建下一个 _V2/_V3 版本。
工作方法
先通读并确认四件事：作者想说什么、写给谁、发布在哪里、哪些事实和表达不能改变。缺少的信息只有在会实质改变结果时才询问；其余从上下文合理推断。
改写时优先处理：
- 空泛判断：换成事实、动作、场景或可感知细节。
- 模板句式：减少连续使用相同的转折、排比、反问和总结结构。
- 虚假身份：不替作者编造经历、朋友、采访或亲眼所见。
- 节奏单一：按体裁调整句长、段落和停顿，不追求故意制造毛边。
- 术语和套话：能用简单、准确的说法就不用展示腔、汇报腔和广告腔。
- 过度解释：观点或故事已经成立时，删掉重复总结和强行升华。
- 空转评点：对别人的话只做情绪评点的句子（「这话说得挺狠」类）一律删掉，直接接事实、推论或动作。
- 假迟钝与回指：作者是行家时不写「琢磨了一阵才发现」式的慢发现；转场不用「说回X」，可用问句过渡（问读者真正会问的问题）或直接接内容。
- 假装震惊：替作者编情绪反应（「我有点坐不住」「我震惊了」类）一律删掉，直接给判断或事实；情绪只在真实发生过后才写，并且克制。
- 口语与语气：平词换真人说法（「上道了」「心里有底」），关键处语气可以更冲（「这特么到底」）；虚指数字用俗语类比防较真（「三人行，必有我师」式）。
- 抽象落到主体：「有被重新设计的可能」→「有被AI重新设计并且替你干活的可能」。
- 回指要显化：用「这两样」「那段话」回指时读者要回头数，重复具体名词，不省那几个字。
- 结果要落一句：讲完机制别停在过程描述上，把结果拍成一句话（「很快，200 人的名单就挑出来了」），读者才有落点。
- 自问自答：不替读者提问（「这个说法到底什么意思？」类），直接往下聊；读者真有疑问会自己问。
这些都是语境信号，不是全局禁词。破折号、排比、三段式、专业词和对比句在合适的体裁中可以保留。不要为了“像人”故意加入语病、跑题、未经证实的细节或情绪。
真实性边界
- 不新增无法验证的数据、引语、案例和人物经历。
- 原文已有可疑事实时，标出或保守改写；不要在润色过程中替它补造出处。
- 虚构设定必须保持其虚构属性，不能伪装成事实。
- 保留作者核心立场、信息密度和关键限定，除非用户明确要求重写观点。
工具与参考
处理本地文件且机械信号较多时，可运行：
python3 scripts/hanyihan_qc.py <文章路径>
脚本结果只是候选信号，必须结合体裁和上下文判断，不能按命中数决定质量。
需要逐项审稿或大幅改写时，读取 references/editing-guide.md。简单润色不必加载完整参考。
输出
默认只交付用户需要的结果。审查报告按影响排序，说明“哪里不自然、为什么、建议怎么改”；改写结果不附冗长自我表扬或逐句解释。用户要求对照时再提供改动清单。
完成前检查：观点未被偷换、事实未被编造、体裁和长度符合要求、明显模板重复已减少、读起来顺口但仍像原作者。
What ships with it
7 files 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.
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.
- 1mo ago Changed · +8 lines 012e317a9b0e
- 1mo ago Changed · -573 lines · +97 tokens per session 566189976d08
- 1mo ago First seen · 633 lines · 67 tokens per session scan A 3d309476e22d
ldm-ai-to-human-zh is a skill published in the GitHub repository Holden323/ldm-skill (43 stars, last pushed 1mo ago), licensed MIT. It adds 164 tokens to every session and 1,294 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to smart-search, differing in 177 lines, and is treated as a copy.
Other skills, from other repositories
intl-expansion
International market expansion strategy. Market selection, entry modes, localization, regulatory compliance, and go-to-market by region. Use when expanding to new countries, evaluating international markets, planning localization, or building regional teams.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
azure-ai-translation-text-py
Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
edit-site
Plans, coordinates and customizes PAC CLI-downloaded Standard or Enhanced data model non-SPA Power Pages sites created from Microsoft templates or manually in Design Studio. Use for requests involving pages, localized content, navigation, assets, snippets, site markers, Liquid/web templates, page layouts, or styling.…
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.