good-writing/SKILL.md
复现特定作者中文写作风格的轻量 Skill。用于从零写作、改写、终稿精修、风格审阅和结构保真翻译。默认先读风格摘要,不再启动时通读完整范文或大型检测清单。
npx skillsauth add oubigfa/de-ai-prompt-enhancer-writer-booster-skill good-writingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
默认先只读本文件。不要一上来读取完整 references/writing-samples.md、references/style-dna.md 或 references/ai-trace-detector.md。
references/style-summary.md。只有用户明确要求“强模仿原作者风格”或输出明显跑偏时,再用 references/writing-samples-index.md 选择一篇或一个片段读取。references/translation-guardrails.md。翻译任务中结构保真优先,覆盖风格偏好。references/style-summary.md;需要定位 AI 痕迹时,先读 references/ai-trace-index.md,再按索引读取详细章节。references/style-dna.md 的相关章节。本技能不是通用写作指南,而是特定作者风格复现工具。核心目标是让文章更像该作者,而不是把文章改成中性说明书。
核心气质:
风格规则不能制造病句。合并句子、删关联词、嵌入插入语后,必须确认主谓搭配和关联词完整。
“去模板”不能反客为主。宁可保留一点锋利和偏见,也不要把文章磨成四平八稳的说明文字。
翻译时不擅自增删,不合并或拆分段落,不把 Markdown 结构改写成散文化中文。
references/ai-trace-index.md 快速检查最显眼的 AI 痕迹。只基于当前草稿做补丁。没有草稿就先索取,不凭空重写。
审阅只列最影响成稿的 Top 5-10 个问题。每个问题给具体位置、原因和修法方向。不输出完整黑名单。
references/style-summary.md:默认风格摘要,先读它。references/writing-samples-index.md:范文片段索引,需要强模仿时先读它。references/style-dna.md:详细风格规则,只按标题或关键词读取相关章节。references/ai-trace-index.md:AI 痕迹轻量索引,先读它。references/ai-trace-detector.md:详细检测清单,只按索引读取相关章节。references/translation-guardrails.md:翻译任务规则。data-ai
中文写作、改写、润色、翻译和审阅的去 AI 味技能。用于保留原意和原文风格,减少路标词、讲义腔、模板句式、协作口吻和 AI 痕迹。默认轻量加载,按任务只读取必要参考章节。
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.