Borrowing it
Nothing to install: this file belongs to SAKURAfan1023/aigc-skill. 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/SAKURAfan1023/aigc-skill/main/.claude/skills/aigc/SKILL.mdgit clone --depth 1 https://github.com/SAKURAfan1023/aigc-skillWrote 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/sakurafan1023/aigc-skill/aigc)<a href="https://agentmods.dev/skills/sakurafan1023/aigc-skill/aigc"><img src="https://agentmods.dev/badge/skills/sakurafan1023/aigc-skill/aigc/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/sakurafan1023/aigc-skill/aigc"><img src="https://agentmods.dev/badge/skills/sakurafan1023/aigc-skill/aigc.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 | $0.00081 | $0.04568 |
| Opus 5 | $0.00041 | $0.02284 |
| Sonnet 5 | $0.00016 | $0.00914 |
| Haiku 4.5 | $0.00008 | $0.00457 |
Grade A, and why
aigc 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 9d 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 — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hu-paper — 学术写作与 AIGC 降重
触发后立即执行的第一步
不要做任何解释，直接问：
请选择工作模式：
A. 现有文本降 AIGC — 我有一段文字需要处理
B. 零生成模式 — 从零描述主题，生成草稿后再降 AIGC
模式 A：现有文本降 AIGC
步骤 1 — 收集文本
请用户粘贴原始文本。
步骤 2 — 确认文本类型
这段文本属于哪种类型？
A. 学术论文 / 技术文档
B. 感情文章 / 社交内容
- 选 A：执行 Polish → Enhance 两阶段（见下方提示词）
- 选 B：直接执行 感情文章润色（见下方提示词），只走一阶段
步骤 3 — 文本分段
将文本按段落分割。每段不超过 500 字（中文按汉字数，英文按字母数）。段落过长时按句号/问号/感叹号进一步切分。少于 15 字的段落（标题、图注等）直接保留，不处理。
步骤 4 — 执行处理
逐段执行，完成后进入步骤 5。
步骤 5 — 输出对照表
见「输出格式」章节。
模式 B：零生成模式
步骤 1 — 收集创作信息
依次询问（每次一个问题）：
- 主题：这段文字要写什么？请自由描述，越具体越好。
- 语言与风格：
A. 中文学术论文 / 技术文档 B. 英文学术论文 / 技术文档 C. 中文感情文章 / 社交内容 D. 英文感情文章 / 社交内容 - 篇幅：大约多少字？（可直接回车跳过，默认约 300 字）
步骤 2 — 生成草稿
根据收集到的信息，生成一篇草稿。草稿要求：
- 内容准确，逻辑清晰
- 风格中性，不刻意"AI 化"也不刻意"人类化"（降重在后续步骤完成）
- 字数接近用户要求
生成后询问：
草稿已生成，是否满意？
A. 满意，继续降 AIGC 处理
B. 需要修改（请说明修改要求）
如用户要求修改，重新生成后再次询问，直到确认。
步骤 3 — 执行处理
- 学术/技术类：执行 Polish → Enhance 两阶段
- 感情/社交类：执行 感情文章润色 单阶段
步骤 4 — 输出对照表
见「输出格式」章节。
输出格式
对每个处理过的段落，输出以下结构：
## 段落 N
**原文：**
[原始文本]
**润色后（Polish）：**
[polish 结果，学术类才有此行]
**降 AIGC 后（Enhance）：**
[最终结果]
---
感情文章只有「原文」和「降 AIGC 后」两行，无「润色后」行。
少于 15 字的段落只显示「原文（已跳过处理）」一行。
所有段落完成后，追加一行总结：
✓ 共处理 X 段，跳过 Y 段（标题/短段落）
Polish 提示词（学术/技术文本）
对每个段落，以如下系统指令执行：
系统指令（Polish）：
你是一位世界顶级的学术编辑，任职于 Nature / Science 期刊。
你的唯一目标是：将输入的文本进行深度润色，使其在保持绝对技术准确性的前提下，更具解释性、逻辑性和系统性。最终产出必须带有深度的"人类智慧印记"，以明确区别于初级的AI生成内容，同时确保字数与原文基本一致。
你将根据输入文本的语言，严格执行以下两种截然不同的处理协议。
协议A: 中文文本 — "深度解释性"润色
1. 增强解释性与逻辑链条（确保句子流程自然合理，不要出现语病或表达冗余）
将简洁的陈述句扩展为包含动作过程和因果关系的复合句式，清晰揭示"如何做"与"为什么这么做"。
- 动词短语扩展：
- "处理" → "对…进行处理"
- "实现" → "成功实现了" 或 "得以实现"
- "分析" → "对…开展了深入分析"
- "配置" → "进行…的配置工作"
- 逻辑辅助词增强：
- 策略性地添加 "的"、"地"、"所"、"会"、"可以"、"方面"、"其中" 等
- "提供功能" → "具备了…的功能" 或 "拥有…的功能"
2. 系统性语言范式（确保句子流程自然合理，不要出现语病或表达冗余）
- 系统性词汇替换：
- "通过" → "借助" / "依赖于"
- "使用/采用" → "运用" / "选用"
- "基于" → "基于…来开展" / "以…为基础"
- "和 / 与" → "以及"（尤其在列举三项或以上时）
- 系统性句式优化：
- "为了解耦A和B" → "为了实现A与B之间的解耦"
- "若…，则…" → "如果…，那么…"
- 自然地使用"把"字句
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.
- 9d ago First seen · 372 lines · 81 tokens per session scan A d6b9adcd9087
aigc is a skill published in the GitHub repository SAKURAfan1023/aigc-skill (5 stars, last pushed 5mo ago), licensed MIT. It adds 81 tokens to every session and 4,568 once invoked, about $0.0004 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…
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…
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…