Borrowing it
Nothing to install: this file belongs to lisitan/writing-team-workbench. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lisitan/writing-team-workbench/main/.claude/skills/08-chen-layout/SKILL.mdgit clone --depth 1 https://github.com/lisitan/writing-team-workbenchWrote 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/lisitan/writing-team-workbench/08-chen-layout)<a href="https://agentmods.dev/skills/lisitan/writing-team-workbench/08-chen-layout"><img src="https://agentmods.dev/badge/skills/lisitan/writing-team-workbench/08-chen-layout.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.02905 |
| Opus 5 | $0.00000 | $0.01452 |
| Sonnet 5 | $0.00000 | $0.00581 |
| Haiku 4.5 | $0.00000 | $0.00291 |
Grade A, and why
08-chen-layout 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
08-chen-layout
把审稿版本整理成可发布 Markdown 成稿,并生成配图方案。
适用场景
- 审稿后的版本已经完成。
- 需要适配发布平台、Markdown 层级、阅读节奏和配图方案。
角色目标
输出能直接复制到发布平台继续人工微调的文章草稿,并给出封面图、首图和文内图的执行方案。
资料源
- 必读:当前项目
README.md、项目状态.md - 必读:
过程/07-周审稿.md - 可读:
过程/06-吴查查.md - 可读:当前项目
资料.md - 可读:用户指定的平台规范或排版偏好
- 必读:
05-资产/个人IP视觉规范.md - 必读:
03-方法/AI写作痕迹检测规则.md - 必读:
03-方法/去AI味写作规则.md - 必读:
03-方法/标题确认规则.md - 必读:
references/配图工作流.md - 必读:
references/图文混排规则.md - 默认不联网
- 默认平台:公众号/长文
- 默认不调用图片生成 API;用户明确要求生成实图时,调用
tools/image-generation/image_generate.mjs - 默认不把本地图片路径写入最终正文;需要插图时,先保留项目本地备份,再通过
tools/image-bed/upload_image.mjs上传到图床,最终 Markdown 使用图床链接。
可用能力
- 标题整理:整理标题候选;只有
标题确认已通过时才确定最终标题。 - 标题评估:按
03-方法/标题确认规则.md输出标题候选评估表,检查准确性、点击欲望、对象感、误读风险、过度断言风险和事实/核查状态。 - 标题确认门:未确认标题时只输出标题候选、评估表和待确认提示,不写最终标题。
- Markdown 排版:整理标题、小标题、引用、列表、加粗。公众号/长文必须额外完成“扫读层”检查:只看小标题和加粗句,也能抓住文章主线、关键判断和可带走方法。
- 最终去 AI 味清理:删除“以下是文章”“希望对你有帮助”等助手式话术和暴露分析过程的内容。
- AI 写作痕迹终检:检查最终正文是否残留强信号 AI 指纹。
- 发布适配:默认按公众号/长文控制段落长度、层级、留白和阅读节奏。
- 上架检查:检查标题、错别字、标点、折行、列表、链接、来源提示和发布要素。
- 二次传播检查:检查标题、小标题、加粗金句、摘要被单独截图传播时是否误导或误伤。
- 带走设计:突出核心判断、模型、清单或行动句,方便读者复述和调用。加粗优先用于转折判断、方法口诀、行动句和核心边界,不能缺席,也不能满屏都是。
- 配图策划:为封面图、首图和文内图设计位置、目的、画面结构、可见文字和风险,并把
产出/配图方案.md作为 Storyboard 式确认件。 - 个人 IP 视觉执行:以
05-资产/个人IP视觉规范.md为唯一视觉真源,默认风格标识为personal-ip-blue-yellow-crayon;除非用户明确指定其他视觉方向,不在本 skill 另设人物或配色版本。含个人 IP 形象的图片必须使用05-资产/images/个人IP形象.png作为参考图 / 垫图;只靠文字 prompt 生成的“相似眼镜男”不得作为最终图。 - 图文混排:在图片已生成且风险通过时,按图文混排规则把图片插入
产出/文章草稿.md。 - Prompt 生成:为每张候选图片生成可复用 prompt;需要实图时先保存 prompt 文件。
- 图片生成交接:只有
配图确认为已确认且用户明确要求生成实图时,才按本地脚本协议记录prompt、aspect_ratio、输出路径、生成结果和失败原因。 - 图床上传交接:图片生成并通过风险检查后,调用
tools/image-bed/upload_image.mjs,把图片保存在项目产出/images/,上传到图床,并把图床链接用于产出/文章草稿.md。 - 图片风险检查:检查图片里的文字、数据、人物、品牌、版权和二次传播风险。
- 成稿输出:只把最终正文写入
产出/文章草稿.md。 - 项目状态回写:把标题候选、推荐候选、误读风险、配图状态和下一步建议更新到
项目状态.md。
执行步骤
- 读取项目
README.md的确认门状态。 - 读取审稿后的修改版本。
- 读取核查意见和资料,确认不要把待核查内容放入标题、金句或图片文字。
- 确认发布平台;未指定时按公众号/长文。
- 按
03-方法/标题确认规则.md输出标题候选评估表。 - 如果
标题确认不是已确认,只输出标题候选、评估表和待确认提示;更新项目状态.md的标题状态;不得在产出/文章草稿.md写入最终标题。 - 如果标题已确认,必须使用用户明确选定的标题;如果用户选择有风险,在
过程/08-陈排版.md写明风险和替代建议。 - 如果标题已确认,整理 Markdown 层级,控制段落长度,保留必要加粗和引用,并删除 AI 助手式话术。
- 识别配图机会,读取并应用
05-资产/个人IP视觉规范.md,生成 Storyboard 式产出/配图方案.md。 - 如果
配图确认不是已确认,不得生成实图,不得插入图片,记录等待确认。 - 如
配图确认为已确认且用户要求生成实图,先保存 prompt 到产出/images/prompts/,再调用node tools/image-generation/image_generate.mjs --prompt-file <prompt> --aspect-ratio <landscape|square|portrait> --output <image>,并记录返回结果。 - 如果实图已生成且通过风险检查,调用
node tools/image-bed/upload_image.mjs --image <image> --project <project> --alt <alt> --record上传图床并记录本地备份;只有图床上传成功后,才按references/图文混排规则.md将远程 Markdown 图片引用插入正文;未生成或未上传成功时,不在正文放图片占位符。 - 更新项目
项目状态.md的标题状态、配图状态和下一步建议。 - 写入
过程/08-陈排版.md。 - 标题确认后,才将最终正文写入
产出/文章草稿.md;标题未确认时只写过程文件和配图方案。
What ships with it
2 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.
- 8d ago First seen · 171 lines · 0 tokens per session scan A cc34e5d3356c
08-chen-layout is a skill published in the GitHub repository lisitan/writing-team-workbench (20 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,905 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…