aigc-reduce-playbook SKILL.md skillA
aigc-reduce-playbook from gxgeek-n/wenqu-mem is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add gxgeek-n/wenqu-mem/aigc-reduce-playbook@git:20260807.c0a57aaPins git:20260807.c0a57aa in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- gxgeek-n/wenqu-mem
- Path
skills/aigc-reduce-playbook/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260807.c0a57aa, committed Aug 7, 2026
- First version recorded
- Jul 4, 2026
- Size
- 8,100 bytes
- Repository stars
- 4
- License
- a license file GitHub does not identify
「论文 AIGC 报告复核与表达风险诊断」——把检测报告解析、可疑段落定位、证据补强建议、定向表达修订和复核串成闭环。 适用于中文学位论文/期刊在 PaperYY、PaperPass、知网等平台出现 AIGC 疑似提示，或导师认为文字过度模板化、 证据链不足、论证太顺滑的场景。目标是回到真实材料和学术表达质量，不承诺平台结果、不提供造假方案。 包含平台差异认知、风险定位杠杆、报告解析脚本、 铁律、以及该做/不该做清单。触发词：AIGC报告复核、AIGC疑似、AIGC检测、PaperPass、PaperYY、知网AIGC、 论文AI痕迹、表达太模板化、证据链不足、AI味风险。已整合：理论+替换表(references/theory/)、5维语义检测(references/detector/)、全部脚本(scripts/)，单一入口。 分工（去AI味三角）：语体正向写法→ thesis-style；"像不像AI"的判定→ thesis-deai-review； 本 skill 专管 **平台检测报告**（PaperYY/PaperPass/知网）的解析、定位与合规修订闭环。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 论文 AIGC 报告复核与表达风险诊断（Playbook） 把「检测报告 → 定位高疑似句 → 回查真实材料 → 定向修订表达 → 编译/复核」串成可复用闭环。**理论/替换表见 `references/theory/`，5维语义检测见 `references/detector/`，本 skill 是 AIGC 报告复核和表达风险诊断入口。** > **配套 `thesis-deai-review`（项目级）管"判断什么该改不翻车"**（体裁基准校准、"完美统计=强信号"、保留真实不完美、"别改成口语"铁律）。本 playbook 管平台工具+复测，deai-review 管确定性脚本与隔离 AI 并行判断，配合用。 ## 学术诚信边界 - 本 skill 不承诺任何 AIGC 检测平台给出特定结果，也不提供伪装、篡改 PDF 或篡改字符编码的方法。 - 只允许基于真实材料做表达修订、结构调整、证据补强和风险定位。 - 不新增不存在的数据、访谈、日志、引用、案例或导师意见。 - 检测报告只能作为写作风险线索；最终质量以学校规范、事实证据和导师意见为准。 ## 0. 一句话心智模型（先建立，否则白干） **AIGC 检测器 = 拿一个"裁判 AI 模型"算你的文字"有多好猜"（困惑度）+ "句长够不够起伏"（突发性）。** - **不同平台 = 不同刻度的尺子**：同一篇文 PaperYY 判 19.6%、PaperPass 判 49%，都不算错。**别拿最严平台的分吓自己。** - **真正算数的是学校的工具（多为知网）**；PaperYY/PaperPass 只是便宜预检。 - 统计型检测器**惩罚"信息密集的流畅学术中文"本身**——你写得越像正经论文，它越觉得像 AI。所以**有地板，降不到 0**。 ## 1. 风险收敛杠杆排序（按质量收益） | 杠杆 | 风险收敛 | 伤质量? | 说明 | |---|---|---|---| | **破枚举/序号** | 高 | 否 | "首先/随后/最后""第一/第二/第三""其一~其四""一是二是""(1)(2)(3)"→流水句。**头号 AI-tell** | | **打散句长(突发性)** | 高 | 否 | 长短句交错，插极短句。人类 CV≈0.52 vs AI≈0.32 | | **数据句瘦身** | 中 | 否 | "由A提升至B""从表X看…占比…说明…"模板→数字不动、换动词/语序，删与表重复的罗列 | | **数据罗列搬进表格** | 中 | 否 | 纯数字句→小表格，进"不予检测"区，移出分母（结构法，不反弹） | | **特异性下沉** | 中 | 否 | 把已有真实细节(日期/角色/事故)织进泛句，拉高困惑度。**绝不编造** | …
Read the whole file at its exact version.
How to install
mdr add gxgeek-n/wenqu-mem/aigc-reduce-playbook@sha256:29b806929746e0fcThe line at the top of this page pins the label git:20260807.c0a57aa, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_hhr5k2e4cokv4uaf)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 4, 2026 and Aug 7, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260807.c0a57aa latest | 2026-08-07 | c0a57aa | 8,100 B | A | view · diff |
| git:20260726.b8c0edb | 2026-07-26 | b8c0edb | 7,371 B | A | view · diff |
| git:20260726.6c7e134 | 2026-07-26 | 6c7e134 | 7,395 B | A | view · diff |
| git:20260704.1ab6c99 | 2026-07-04 | 1ab6c99 | 7,112 B | A | view · diff |
| git:20260704.eb9bb8b | 2026-07-04 | eb9bb8b | 7,204 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8100 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
gxgeek-n/wenqu-mem · 4 stars · license a license file GitHub does not identify · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hhr5k2e4cokv4uaf GET https://markdownregistry.com/api/v1/resolve?ref=gxgeek-n/wenqu-mem/aigc-reduce-playbook GET https://markdownregistry.com/api/v1/blob/29b806929746e0fcc81e77abbd88778cd279c8d22b9037fc23f238eb7c8ae41d
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.