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 tranfu-labs/tranfu-skills --skill proofread-contentgit clone --depth 1 https://github.com/tranfu-labs/tranfu-skillsWrote 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/tranfu-labs/tranfu-skills/proofread-content)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/proofread-content"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/proofread-content/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/tranfu-labs/tranfu-skills/proofread-content"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/proofread-content.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 | $0.00144 | $0.04776 |
| Opus 5 | $0.00072 | $0.02388 |
| Sonnet 5 | $0.00029 | $0.00955 |
| Haiku 4.5 | $0.00014 | $0.00478 |
Grade A, and why
proofread-content 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.
How it starts
The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proofread Content
对已经成稿的简体中文自媒体内容做三轮审校。成功结果是纯净正文,不是诊断稿,也不包含审校说明。
总控 Provider 路由
执行独立流程前先检查结构化请求。请求只要出现 contract: content-production-provider/v2、
capability: proofreading、provider_contract: proofreading-v1 或
content-production-provider: proofreading-v1 任一标记,就必须改走
references/orchestrated-provider.md 并使用 scripts/provider-contract.mjs。完整合同仍要求前三项
同时精确匹配;部分、冲突或无效标记必须结构化阻断,不得回退独立模式。
Provider 路由不覆盖输入 draft.md,不执行独立模式的原子写回和 YAML PROOFREAD_RESULT,也不
创建嵌套 run、门禁或用户偏好文件。没有上述标记的普通请求继续执行下方独立流程,行为不变。
交付边界
- 支持微信公众号、小红书、微博、知乎和头条号的完整成稿。
- 支持对话中粘贴的正文,以及可读、非空、UTF-8 编码的
.md或.txt单文件。 - 只调整字句、删除不承载独立信息的冗余,并在同一小节内调整段落顺序。
- MUST 保持标题、标题层级、核心观点、立场、事实、数据、案例、引用、链接、术语和整体结构。
- MUST 原样保留数字、百分比、日期、金额、版本号、数字与单位组合及专有名词的字面形式;不得为 “统一排版”在这些受保护字面值内部插删空格、标点或字词。
- NEVER 发明数字、人物、经历、对话、时间、地点、情绪、引用或来源。
- NEVER 为平台增长新增钩子、CTA、emoji、话题标签或爆款结构。
- NEVER 以 AI 检测百分比作为目标,也不声称绕过检测器。
- 默认只检查原稿内部一致性。外部事实真实性、法律合规和平台最新政策不属于
READY_FOR_LAYOUT的保证。
调用本 Skill 处理文件,表示用户授权在全部硬门禁通过后覆盖该输入文件。处理粘贴文本,表示用户
授权在全部硬门禁通过后原子创建或覆盖当前工作目录下的 proofread-content.md。除此之外,不得
编辑其他用户文件。
规则优先级
规则冲突时,序号小的优先:
- 禁止虚构和双向事实保真。
- 标题、立场、事实、案例与整体结构保护。
- 当前原稿体现的作者声口。
- 目标平台的语体与阅读节奏。
- Humanizer-zh 24 类模式。
- 错别字、标点、排版与局部精炼。
不得为了满足后一级规则破坏前一级规则。无法兼容时,停止写回,把状态设置为
NEEDS_AUTHOR_INPUT 或 BLOCKED,再转至统一输出子流程。
必读参考
每次执行 MUST 完整读取:
references/humanizer-zh-24.md:24 类检测面、检查清单和内部五维诊断。references/platform-registers.md:五个平台和通用自媒体语体的适配边界。
执行流程
CREATE A TODO LIST FOR THE TASKS BELOW:
- 校验输入并确定目标产物。
- 识别平台并建立不可变基线。
- 执行第一轮:内容、逻辑与内部一致性。
- 执行第二轮:24 类去 AI 味与作者声口。
- 执行第三轮:语言细节、Markdown 与阅读节奏。
- 运行最终回归门禁;失败时最多内部修复两次。
- 仅在门禁通过后原子写回。
- 转至子流程「输出结果」,输出唯一的
PROOFREAD_RESULT并结束。
1. 校验输入
- 初始化内部
RESULT_CONTEXT:status未设置,platform=unknown,source=none,output=unchanged,hard_gates=not_run,三个changes字段均为not_run,author_questions=[],block_reason=""。 - 接收文件路径或粘贴正文。两者都没有时,设置
status=NEEDS_AUTHOR_INPUT,写入一个索取完整 成稿的具体问题,转至子流程「输出结果」。 - 同时收到文件路径和粘贴正文时,只有用户明确且排他地指向其中一种输入,才能按该唯一指向继续。
用户同时要求处理两者、没有排他指向或指向含糊时,不读取或覆盖任一目标;设置
status=NEEDS_AUTHOR_INPUT,要求二选一,转至子流程「输出结果」。 - 确定唯一输入后,文件输入把
source设为输入文件绝对路径;粘贴输入设为inline。 - 文件输入必须是可读、非空、UTF-8 的单个
.md或.txt文件;否则设置status=BLOCKED和具体block_reason,转至子流程「输出结果」。 - 输入必须是完整成稿。只有选题、提纲、零散素材或明显未完成片段时,设置
status=NEEDS_AUTHOR_INPUT,写入索取完整成稿的具体问题,转至子流程「输出结果」。 - 学术、法律、公文等专业文本,或从零创作、翻译、排版、发布、爆款重构请求,设置
status=BLOCKED和具体越界原因,转至子流程「输出结果」。 - 文件输入的最终目标是原文件路径;粘贴输入的最终目标是当前工作目录中的
proofread-content.md。 - 此阶段不得写入最终目标。所有改写先保存在内存中;只有通过硬门禁后,才可在最终目标同目录 创建临时文件。
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.
- agents/openai.yaml 347 B
- assets/icon.png 564 B
- assets/icon.svg 472 B
- LICENSE 1.0 KB
- NOTICE 777 B
- README.md 2.5 KB
- README.zh.md 2.2 KB
- references/humanizer-zh-24.md 15 KB
- references/orchestrated-provider.md 3.7 KB
- references/platform-registers.md 3.3 KB
- scripts/claim-regression.mjs 16 KB runs code
- scripts/provider-contract.mjs 23 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 · 293 lines · 144 tokens per session scan A 971957cdbfe4
proofread-content is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 144 tokens to every session and 4,776 once invoked, about $0.0007 per session on Opus 5. 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 2026-08-31.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…