SimpleEnglish 改写前后对比：8类技术文档改写实测（违规率下降74.6%）

SimpleEnglish 改写前后对比8类技术文档改写实测违规率下降74.6%【免费下载链接】SimpleEnglishAgent skill: make LLMs write docs in ASD-STE100 Simplified Technical项目地址: https://gitcode.com/gh_mirrors/si/SimpleEnglishSimpleEnglish 是一个 Agent skill让大语言模型LLM按照 ASD-STE100 简化技术英语标准写技术文档。开启它之后AI 生成的 README、错误消息、事故报告等 8 类技术文档平均少 74.6% 的规范违规7 个 Claude 模型 × 8 项写作任务实测RESULTS.md。本文用仓库里真实的 Before/After 原文对比逐类展示改写效果 什么是 SimpleEnglish1 分钟看懂一句话把AI 腔从技术文档里删掉换成航空维修手册式的写法。规则来源ASD-STE100航空业从 1983 年沿用至今的受控英语标准目标是让疲劳的非母语读者也不能误读指令落地形式一个文件夹零依赖MIT 协议。核心是 SKILL.md53 条编号规则 9 个章节工作方式装进任何支持 Agent Skills 标准的工具Claude Code、Cursor、Codex 等后说rewrite this with simple-english即可两种模式Pragmatic默认保留你的领域词和 Strict额外执行词典词汇纪律快速上手npx skills add AminBlg/SimpleEnglishClaude Code 用户可装插件含 skill 会话钩子 输出样式claude plugin marketplace add AminBlg/SimpleEnglish claude plugin install simple-englishsimple-english53 条规则里真正干活的是这些指令句 ≤20 词、描述句 ≤25 词一词一义只用简单时态主动语态条件放在命令之前一句一条指令。改写实测8 类文档 Before/After 全记录以下所有 Before 均为未加 skill 的真实 AI 输出After 为同一内容应用 skill 后的结果。完整 5 组对照在 examples/before-after.md更多原始输出在 evals/results/openai-2026-09-01/raw/。1️⃣ README 开头描述型Before1 个 30 词的长句 悬垂 -ing 从句sqlpipe is a command-line tool for syncing PostgreSQL tables to Amazon S3 as Parquet files. Its built for teams who need a lightweight way to move data out of Postgres into a data lake without standing up a full ETL platform. … Configuration lives in a single YAML file, making it easy to version-control your sync definitions…After最长句 21 词一段一个主题sqlpipe is a command-line tool that copies PostgreSQL tables to Amazon S3 as Parquet files. It moves data into a data lake without a full ETL platform.The configuration is one YAML file. You can keep this file in version control with your infrastructure code.2️⃣ Getting Started 快速上手步骤型BeforeNext, configure your pipeline by creating asqlpipe.yamlfile in your working directory. This file defines your data sources, SQL transformations, destinations, and any scheduling or environment variables required for your workflows. The YAML format is simple and flexible, enabling you to tailor pipelines according to your project needs.After编号步骤 条件在前Create the configuration filesqlpipe.yaml. Edit this file to set the source and target databases.Run sqlpipe using the configuration file. Enter this command:sqlpipe run --config sqlpipe.yamlWatch the output for any errors. If sqlpipe stops with an error, examine the message and fix the problem in the configuration.3️⃣ Troubleshooting 故障排查步骤型Before40 词长句、缩写、条件写在命令后面If sqlpipe hangs or fails withdial tcp: i/o timeout, check that the host running sqlpipe can reach the Postgres port (usually 5432) — this is often a security group or firewall rule blocking the connection. If youre connecting to a managed database (RDS, Cloud SQL, etc.), confirm the instance allows connections from sqlpipes IP. You can also try increasingsource.connect_timeout_seconds…After一句一条指令check/confirm 统一为 make sure thatsqlpipe stops withdial tcp: i/o timeoutwhen it cannot reach the Postgres port (5432 by default).Make sure that the host that runs sqlpipe can reach the Postgres port. A firewall or security group usually blocks it.If the database is managed (RDS, Cloud SQL), make sure that the instance accepts connections from the IP of sqlpipe.If the network is slow, increasesource.connect_timeout_secondsin the configuration.4️⃣ Error Message 错误消息步骤型BeforeOops! Something went wrong while attempting to establish a connection to the database. Please ensure your credentials have been properly configured and try again, or reach out to your administrator if the issue persists.AfterConnection to the database failed: the password for userappwas not correct. SetDB_PASSWORDto the correct value, then connect again. If the error continues, ask your database administrator for access.错误消息是收益最高的场景——它是凌晨 2 点给焦虑读者的指令use-cases.md 原话。5️⃣ Incident Report 事故报告描述型BeforeWe have identified an issue that may have impacted some users ability to access the service. Our team has been working diligently to resolve this and services have now been fully restored. We sincerely apologize for any inconvenience this may have caused.After只用简单过去时时间线一目了然Between 14:02 and 14:31 UTC, 12% of requests to the API failed with HTTP 502. A deploy at 14:00 removed the cache warmup step, and the cache nodes overloaded. We reverted the deploy at 14:27. All requests succeeded from 14:31.6️⃣ Release Notes 发布说明中的破坏性变更描述型BeforePlease note that weve made some changes to the users endpoint that may require updates to your integration. Thenamefield has been deprecated in favor of separatefirst_nameandlast_namefields, so youll want to update your code accordingly.AfterBreaking 警告模式命令在前Breaking:Update your calls to/v2/users. Thenamefield split intofirst_nameandlast_name. Thenamefield will return null after 2026-09-01.7️⃣ Runbook 运维手册极端简化BeforeVerify backup exists before migrating.After保留完整语法这才是 STE不是电报体Make sure that the backup exists before you run the migration.8️⃣ Architecture 架构说明描述型Before典型 AI 腔robust / leveraging / fault-tolerantSQLPipe is a data pipeline designed to efficiently transfer and convert data from a Postgres database to S3 storage in Parquet format. … It incorporates robust retry mechanisms to ensure data durability and successful uploads, even in the face of transient network or service disruptions.After一句一个新事实sqlpipe has three main parts. A reader process streams rows from Postgres in batches. A converter turns each batch into a Parquet row group. An uploader writes objects to Amazon S3 as multipart uploads. The uploader retries parts that fail to upload.为什么是 74.6%基准测试方法说明评分靠一个确定性正则 linterste_lint.py统计每 100 词的 STE 违规数两组条件用同一套规则112 次生成的原始文件全部提交在仓库里任何数字都可复现python3 evals/run_bench.py。模型基线 viol/100w开启 skill viol/100w下降幅度claude-opus-52.130.3285%claude-opus-4-81.050.6241%claude-opus-4-72.280.4282%claude-opus-4-62.240.4082%claude-opus-4-52.550.5778%claude-sonnet-52.670.5380%claude-sonnet-4-62.060.5275%跨框架同样成立GLM-5.2 max 下降 84.4%GPT-5.6 Sol 下降 88.0%gpt-4.1-mini 下降 95.8%。盲评56 组配对评委不知道哪边是 skill 输出中评委在 45 组里偏好 skill 版本且 7 个模型的输出 token 数全部下降——更短也更准。FAQ 常见问题会让文档变得机器人味十足吗会像空客手册平淡、无法误读。对文档来说这恰恰是目的——营销文案请保留自己的风格。为什么不直接提示 write clearly清晰是一种观点句子不超过 20 词是规格。Agent 只会照规格执行。支持哪些工具所有读取 Agent Skills 标准的 AgentClaude Code、Cursor、VS Code Copilot、OpenAI Codex、Gemini CLI 等约 25 工具。没有 skill 支持的模型可直接粘贴 system-prompt.md文末还附 60 token 精简版。规则细节在哪看完整 53 条规则在 SKILL.md改写用的词表在 word-swaps.md交付前的自查清单在 checklist.md压测场景在 pressure-tests.md。总结SimpleEnglish 把写清楚从玄学变成了可执行、可度量的规格8 类技术文档全部通过同一套 53 条规则改写违规率平均下降 74.6%。所有 Before/After 原文都在 examples/before-after.md想亲手验证的话装好 skill 后说rewrite this with simple-english就行 ✅【免费下载链接】SimpleEnglishAgent skill: make LLMs write docs in ASD-STE100 Simplified Technical项目地址: https://gitcode.com/gh_mirrors/si/SimpleEnglish创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考