undress SKILL.md skillA
undress from howillmakeit/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add howillmakeit/skills/undress@git:20261008.8e53f92Pins git:20261008.8e53f92 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- howillmakeit/skills
- Path
undress/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261008.8e53f92, committed Oct 8, 2026
- First version recorded
- Aug 17, 2026
- Size
- 6,096 bytes
- Repository stars
- 9
- License
- MIT
去除论文、开源项目、技术博客、简历项目和产品介绍中的包装性语言,基于论文、代码、实验与原始材料,简单说明作者实际复用了什么、修改了什么、实现了什么、验证了什么。用于用户询问“这个工作到底做了什么”“是不是过度包装”“创新点本质是什么”“去掉术语重新解释”或需要审视技术工作的真实含金量时。.
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
# 技术工作去包装 ## 基本原则 保持客观,不替作者宣传,也不要为了“去包装”而反向贬低工作。 必须区分: - **概念复杂度**:核心想法是否简单; - **实现难度**:工程接入、训练和调试是否困难; - **实验严谨度**:是否有充分基线、消融和独立评测; - **证据强度**:结论来自论文、代码、日志,还是仅来自 README、简历或宣传材料。 “没有提出新理论”不等于“没有工作量”;“工程量大”也不等于“算法创新强”。 ## 分析流程 ### 1. 先读取一手材料 优先检查: 1. 论文方法、实验和附录; 2. 仓库代码、配置、提交记录和运行结果; 3. 官方技术报告; 4. README、博客和演讲稿; 5. 简历、新闻稿和社交媒体介绍。 如果只有作者自述,明确标注“以下基于作者描述,尚未由代码或实验验证”。 ### 2. 找出原有基础 说明作者直接采用了哪些现成内容: - 基础模型、算法和训练框架; - 数据集、Benchmark 和评测脚本; - 开源 Agent、工具链或已有 Pipeline; - 已知方法、公式或工程组件。 不要把“使用某个框架”写成作者实现了该框架。 ### 3. 提取真实增量 把工作压缩成可核查的动词: - 新增了什么; - 修改了哪条公式、损失、奖励或采样策略; - 接通了哪些模块; - 修复了什么具体问题; - 做了哪些对照和消融; - 指标在什么设置下发生了怎样的变化。 如果算法核心只有一条公式或几条规则,直接说清楚,不使用“创新框架”“系统性范式”等替代具体内容。 ### 4. 分层归类 将工作归入以下类别,避免混在一起制造复杂感: | 类别 | 要回答的问题 | |---|---| | 算法改动 | 奖励、损失、优势、采样或模型结构具体改了什么? | | 工程实现 | 接入、并发、显存、部署、容错具体做了什么? | | 数据工作 | 数据如何收集、筛选、标注或划分? | | 评测工作 | 使用什么基线、指标、消融、Seed 和测试集? | | 最终证据 | 哪个指标相对哪个基线提高了多少? | ### 5. 检查结论是否成立 逐项检查: - 对比条件是否一致; - 是否把训练指标当成测试效果; - 是否只挑选最佳 Checkpoint; - 是否有独立测试集或数据泄漏; - 是否有多 Seed、方差或置信区间; - 消融能否隔离每个组件的贡献; - 相对提升是否掩盖了很小的绝对提升; - 工程优化是否被包装成算法创新; - 使用现成组件是否被描述为从零实现。 无法验证时写“没有足够证据”,不要替作者补全故事。 ## 默认输出格式 优先使用下面的简洁结构。 ### 一句话结论 用一句话说明: …
Read the whole file at its exact version.
How to install
mdr add howillmakeit/skills/undress@sha256:4e1c415f4d7c868eThe line at the top of this page pins the label git:20261008.8e53f92, 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_kyfkftlragso3nli)
6 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 17, 2026 and Oct 8, 2026, about one every 52 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261008.8e53f92 latest | 2026-10-08 | 8e53f92 | 6,096 B | A | view · diff |
| git:20260817.1b6739b | 2026-08-17 | 1b6739b | 5,095 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 (6096 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
howillmakeit/skills · 9 stars · license MIT · pushed 2026-10-27 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_kyfkftlragso3nli GET https://markdownregistry.com/api/v1/resolve?ref=howillmakeit/skills/undress GET https://markdownregistry.com/api/v1/blob/4e1c415f4d7c868ed810177b859508402553c5ed4782afa72e68561a5ef6a45a
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.