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 taxueseek/say-it-human --skill tech-doc-style-chinesegit clone --depth 1 https://github.com/taxueseek/say-it-humanWrote 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/taxueseek/say-it-human/tech-doc-style-chinese)<a href="https://agentmods.dev/skills/taxueseek/say-it-human/tech-doc-style-chinese"><img src="https://agentmods.dev/badge/skills/taxueseek/say-it-human/tech-doc-style-chinese/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/taxueseek/say-it-human/tech-doc-style-chinese"><img src="https://agentmods.dev/badge/skills/taxueseek/say-it-human/tech-doc-style-chinese.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 | $0.00112 | $0.01987 |
| Opus 5 | $0.00056 | $0.00993 |
| Sonnet 5 | $0.00022 | $0.00397 |
| Haiku 4.5 | $0.00011 | $0.00199 |
Grade A, and why
tech-doc-style-chinese 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 12d 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
100% identical to tech-doc-style-chinese — 6 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.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
中文技术文档与产品文案规范
适用范围
将本 Skill 用于中文技术内容的撰写、改写、校对和审阅，包括：
- 文档首页、产品介绍、解决方案页和更新日志
- API 文档、参数说明、错误码和常见问题
- 操作手册、故障排查、运维 Runbook 和安全说明
- 界面文案、按钮、导航、状态和提示信息
不要改写代码字面量、JSON 键名、URL、API 路径、数据库字段名、命令、配置项或其他机器可读标识符。
规则优先级
发生冲突时，按以下顺序处理：
- 保留事实、逻辑、限制、安全信息和法律含义。
- 服从用户明确要求和目标项目约定。
- 保持技术术语和机器可读内容准确。
- 改善结构、语义、语气和可扫读性。
- 最后处理标点、留白、大小写等排版细节。
不得为了句子更短、语气更确定或格式更统一而牺牲更高优先级的信息。
事实保真
- 不新增原文或可靠上下文没有提供的日期、数字、时限、SLA、能力、条件、因果关系或结论。
- 不删除前置条件、适用范围、例外、风险、安全警告、兼容性说明或失败处理。
- 不把可能、计划、建议、通常等不确定表达改成确定事实。
- 信息不足时保留原意，或明确标记「待确认」；不要自行补全。
- 改写引用、法规、合同、错误原文或用户提供的固定文案时，优先保持原文并将建议单独列出。
示例：
截止 4 月 12 日->截至 4 月 12 日尽快处理->在约定时限内处理〔具体时限待确认〕- 不要凭空补成
截至 2026 年 4 月 12 日或30 分钟内处理
先判断任务模式
撰写
- 先确定受众、内容类型、事实来源、发布载体和篇幅。
- 缺少会改变结论的事实时，先标记缺口，再继续组织可确认内容。
改写
- 保留事实、逻辑关系、信息层级、限制和必要例外。
- 默认交付完整改写稿；重大语义选择或待确认内容另行说明。
校对
- 只处理约定范围内的错字、标点、留白、大小写和术语一致性。
- 未经要求，不改变结构、语气或事实表达。
审阅
- 先列问题，再给建议；按影响程度排序并引用具体原文。
- 未经授权，不直接修改文件。
核心写作规则
语义与语气
- 准确先于修辞，清晰先于热闹。
- 使用克制、直接、可执行的中文。
- 优先说明「是什么、适用于什么、需要做什么、接着看哪里」。
- 避免问候式开场、宣传口号、空泛形容和连续堆叠黑话。
- 默认不直接称呼读者；必要时使用明确角色，如「开发者」「实施人员」。
- 第二人称、感叹号和品牌语气属于风格选择；项目约定或特定界面语境可以覆盖默认规则。
结构与句子
- 一个段落承载一个主要信息点。
- 一个句子保持一个清晰的主干；不要连续堆叠多个条件、动作和例外。
- 列表项保持相同层级、句式和信息密度。
- 标题反映用途，不只使用抽象名词。
- 删除重复信息，不删除事实、条件和例外。
- 指代可能不清时，用具体名称替代「该」「其」「此」「上述」。
术语与排版
- 同一概念使用同一首选术语，不因追求变化而替换同义词。
- 中文引号默认使用直角引号
「」；项目或地区规范可以覆盖。 - 在可见正文中按语义处理中文与英文、独立数字和版本号之间的留白。
- 术语、产品名和缩写优先采用项目规范或官方写法，不机械替换。
- 不直接批量运行排版替换工具；先保护 Markdown、代码和机器可读内容。
详细规则见 术语与排版。
按内容类型处理
入口页和介绍页
首段优先回答：
- 内容覆盖什么
- 适合谁使用
- 从哪里开始读
避免标题、正文和行动按钮重复同一信息。
API 文档
- 请求方法、路径、字段和值使用代码环境保护。
- 参数说明一列一义，并写清类型、单位、默认值、限制和是否必填。
- 状态和错误文案根据实际语义翻译，不机械对应单个英文词。
- 写明前置条件、成功结果、失败结果和恢复方式。
详细规则见 API 状态与错误文案。
界面文案
- 按钮说明动作和目标，不重复页面标题。
- 错误提示说明发生了什么、影响是什么，以及如何恢复。
- 危险操作写清对象、后果和是否可撤销。
- 空状态区分「没有数据」「尚未创建」「无权限」和「加载失败」。
操作与故障排查
对操作手册、故障排查、运维 Runbook、安全说明和多步骤 API 流程，读取并应用 受控中文技术写作。不要把这些规则机械应用于品牌文案、叙事文本或固定引用。
What ships with it
12 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.
- .github/workflows/skill-lint.yml 447 B
- agents/openai.yaml 282 B
- LICENSE 1.0 KB
- NoCode-Skill.md 2.7 KB
- README.md 7.9 KB
- references/api-status-copy.md 2.2 KB
- references/controlled-technical-chinese.md 7.7 KB
- references/project-overrides-example.md 1.1 KB
- references/terminology-and-typography.md 5.6 KB
- scripts/lint_copy_rules.py 12 KB runs code
- tests/test_lint_copy_rules.py 3.6 KB runs code
- tests/test_skill_structure.py 1.5 KB runs code
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.
- 12d ago First seen · 164 lines · 112 tokens per session scan A f264e644f97a
tech-doc-style-chinese is a skill published in the GitHub repository taxueseek/say-it-human (65 stars, last pushed 24d ago), licensed MIT. It adds 112 tokens to every session and 1,987 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to tech-doc-style-chinese, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
stop-slop-zh
A Blender animation guide for changing objects, cameras, lights, and other properties over time. It covers keyframes, motion curves, shape keys for morphs, drivers, and reusable animation actions.
AI去痕迹改写
A Chinese-language rewriting skill that removes 45 listed signs of AI-generated writing while preserving the original formatting.
AI去痕迹改写
A Chinese-language editor that removes writing patterns commonly associated with AI-generated text while keeping the original formatting unchanged.
OwnPen
A set of 45 Chinese writing rules for making text sound less machine-written while keeping its original formatting unchanged.
story-import
A tool for turning an existing novel into a structured writing project. It analyzes the book and organizes its characters, settings, plot plans, chapters, and tracking data for later writing.
story-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.