laohan-shencha SKILL.md skillA
laohan-shencha from hanzhcn/laohan-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add hanzhcn/laohan-skills/laohan-shencha@v1.7.2Pins v1.7.2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- hanzhcn/laohan-skills
- Path
laohan-shencha/SKILL.md- Versions recorded
- 9
- Latest version
- v1.7.2, committed Nov 7, 2026
- First version recorded
- Jul 10, 2026
- Size
- 19,185 bytes
- Repository stars
- 16
- License
- MIT
深度联网核验器，验证技术文档的外部声明，或核验口播稿中可外部验证的事实主张。Use when 用户说"深度审查""老韩审查""联网审查""技术文档审查""核验口播事实"或要求对技术方案、部署脚本、配置文件、口播稿的事实主张进行查证；默认只审查，只有用户明确要求修复或工作流合同授权时才改文件，不做纯文风审查。.
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
# Laohan Shencha（老韩深度审查）
## 核心原则
LLM 写技术文档时天然相信自己写的声明是对的。本 Skill 的唯一目的：**找出那些“看起来正确但实际是错的”声明，并在获得授权时修正。**
核验含对抗性（Jeffrey 2026-10-28）：对每条可核主张主动检索矛盾证据与反例，不能只找支持性来源；回执含反证搜索记录，缺该节不称核验完成。
纯文字审查（表述矛盾、格式不统一）不是本 skill 的重点——那些靠文本比对就能发现。
## 模式与动作
先分别选择“核验对象”和“是否修改”，不要把二者混在一起：
- `TECH_CLAIMS`：默认模式，用于技术文档、脚本、配置和外部资源声明。
- `CONTENT_CLAIMS`：仅在真人口播工作流⑤或用户明确要求核验口播事实时使用。
- `RECORDED_FINAL_INPUT_GUARD + AUDIT_ONLY`：仅在已录制最终稿的编排入口使用，审计是否必须重录。
- `AUDIT_ONLY`：用户说“审查、核验、看看有没有问题”时的默认动作，只出发现与证据，不改文件。
- `VERIFY_AND_FIX`：只有用户明确要求“修复、改掉”，或上游工作流合同明确授权修改时使用。
选择 `CONTENT_CLAIMS` 不等于降低事实标准，选择 `VERIFY_AND_FIX` 也不授权修改文风、方法论或与事实无关的内容。
开发技术核验按当前全局开发合同和项目实际版本执行；先登记文件/声明全量清单与已核/未核，不能用风险排序或默认Top N替代已声明的全量范围。用户明确选抽样时才在TECH_CLAIMS按该范围抽样并标PARTIAL/样本依据；下方CONTENT_CLAIMS的节点规则和抽样段不作为开发技术核验的默认豁免，内容制作合同本轮不变。
## RECORDED_FINAL_INPUT_GUARD + AUDIT_ONLY
仅当episode记录`USER_PROVIDED_FINAL_SCRIPT_AND_RAW`且上游Prompt明确指定`RECORDED_FINAL_INPUT_GUARD + AUDIT_ONLY`时启用。读取当前`01-口播稿.md`与`06-拍摄素材/raw.mp4`，分别计算SHA-256；只做不改口播的阻断性审计。普通不可核验、非核心措辞和可安全剪辑的问题写入非阻断观察后继续，不得自动回②、重跑③—⑤或伪造常规审核历史。
固定写入`00-编排/recorded-input-guard.json`和`00-编排/recorded-input-guard.md`。JSON必须为：
```json
{
"schema_version": 1,
"mode": "RECORDED_FINAL_INPUT_GUARD",
…Read the whole file at its exact version.
How to install
mdr add hanzhcn/laohan-skills/laohan-shencha@sha256:d771a9c3af3c9482The line at the top of this page pins the label v1.7.2, 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_6styowm3qh2nehrj)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 9 versions of this file, between Jul 10, 2026 and Nov 7, 2026, about one every 15 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.7.2 latest | 2026-11-07 | 5fb5bf3 | 19,185 B | A | view · diff |
| v1.7.1 | 2026-10-28 | c2231ab | 17,927 B | A | view · diff |
| v1.7.1 | 2026-10-15 | e884956 | 17,733 B | A | view · diff |
| v1.7.0 | 2026-09-30 | 25ee0fd | 17,203 B | A | view · diff |
| v1.7.0 | 2026-08-15 | 3d55ae7 | 16,259 B | A | view · diff |
| v1.4.0 | 2026-07-20 | eeb59f4 | 14,753 B | A | view · diff |
| v1.4.0 | 2026-07-20 | 446cb18 | 14,572 B | A | view · diff |
| v1.2 | 2026-07-11 | a268666 | 12,970 B | A | view · diff |
| v1.1 | 2026-07-10 | a229557 | 11,470 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 (19185 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
hanzhcn/laohan-skills · 16 stars · license MIT · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6styowm3qh2nehrj GET https://markdownregistry.com/api/v1/resolve?ref=hanzhcn/laohan-skills/laohan-shencha GET https://markdownregistry.com/api/v1/blob/d771a9c3af3c9482bf8735fb9caa825891c7515b825b27f2a6df4c4146e20b51
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.