laohan-cheat skillA
laohan-cheat is agent-read markdown (skill) from hanzhcn/laohan-skills: 内容校准工作流适配器。为 episode 选择正确的 cheat-on-content 校准 lane，保存可追溯的校准入口；评分、盲预测、发布登记、复盘和 rubric 更新一律由上游 cheat-on-content 执行。Use when 用户说校准这期、给本期打分并预测、把 episode 接入 cheat、选择校准轨道、进入④校准。.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# 内容校准适配器 ## 合同地位（2026-09-20治理裁定） 本skill是**校准适配器辅助工具**，未登记executor-registry——④节点合同入口是上游`cheat-on-content`（registry node 4），⑤深扫合同入口是`dbs-content-review`+`laohan-shencha-content-claims`（node 5）。宿主按registry/whois执行④⑤，不因本skill目录可见而路由到它；本skill的lane路由、防污染与登记流程作为操作手册参考。 这里不是第二套 Cheat。`cheat-on-content` 是唯一校准引擎；本 skill 只把 episode 和它的校准 lane 接起来，避免本地 fork 公式、预测规则或迁移规则漂移。 ## 不可跨越的边界 - 禁止在这里按固定教程型权重打分，禁止估算后把分数当预测，禁止另写 PREDICT / RETRO / BUMP。 - 禁止把 `tutorial-video` 的历史样本拿来评估 `opinion-video`；两种内容必须是独立 lane。 - 盲预测必须在拍摄、发布、查看本期实际数据之前，由上游 `cheat-on-content` 写入其 `predictions/`；预测段不可改写。 - 上游版本更新后若 state schema 不匹配，只能先执行 `cheat-migrate` dry-run。备份与用户确认前不得迁移历史 lane。 ## 路由 评分前的 `verify-blind-rubric.mjs` 不得只核对 header：`blind-rubric.md` 必须逐字保留来源 rubric 当前完整维度定义与占位规则。维度语义有缩写、遗漏或改写时保持 PENDING，修复后换全新隔离上下文重评。 1. 先运行 `laohan-bianpai vendors`。Cheat 或 dbskill upstream 有更新时只记录待办；只在新 episode 前或独立维护窗口运行 `vendors --sync`。它报告 schema migration 时停止，不能绕过，也不能在本期中途切换规则。 2. 读取 `episodes/<slug>/01-口播稿.md` 与 `00-选题.md`，判断内容形态。 - 教程、明确操作路径、资源交付 → `tutorial-video` lane。 - 观点、评论、议题、个人判断 → `opinion-video` lane。 - 无法判断时停止，不能默认为教程型。 …
Read the whole file at its exact version.
How to install
mdr add hanzhcn/laohan-skills/laohan-cheat@v2.1.0mdr add hanzhcn/laohan-skills/laohan-cheat@sha256:722eb9c8d35bffdePin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_plx357kuaa2sbqk2)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v2.1.0 latest | 2026-09-20 | 291afa6 | 7,350 B | A | view · diff |
| v2.1.0 | 2026-07-20 | eeb59f4 | 6,906 B | A | view · diff |
| v2.1.0 | 2026-07-20 | 446cb18 | 5,877 B | A | view · diff |
| v2.0.0 | 2026-07-10 | a229557 | 5,168 B | A | view · diff |
| v1.2.0 | 2026-05-28 | 4b2e974 | 10,150 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 (7350 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 · 11 stars · license MIT · pushed 2026-09-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_plx357kuaa2sbqk2 GET https://markdownregistry.com/api/v1/resolve?ref=hanzhcn/laohan-skills/laohan-cheat GET https://markdownregistry.com/api/v1/blob/722eb9c8d35bffde167ea976b9ab6bb239da4266dcec4d51ac6fc3b579511e3a
Your agent 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.