hypothesis-validation SKILL.md skillA
hypothesis-validation from wonglaitung/fortune is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add wonglaitung/fortune/hypothesis-validation@git:20261101.c5a5005Pins git:20261101.c5a5005 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- wonglaitung/fortune
- Path
.opencode/skills/hypothesis-validation/SKILL.md- Versions recorded
- 3
- Latest version
- git:20261101.c5a5005, committed Nov 1, 2026
- First version recorded
- Oct 16, 2026
- Size
- 8,250 bytes
- Repository stars
- 92
- License
- none declared
MUST USE when 需要验证一个市场/策略假设是否成立，或判断某个指标/结论是否可信。 触发词：验证/证明/假设检验/回测/显著性/这策略行不行/这个能赚钱吗/有没有 alpha/ 这数可信吗/靠不靠谱/准不准；以及改动类命题：换池/换周期/加特征/择时/风格因子/板块轮动/ 成本/换手/仓位。本技能给出本项目（港股 / A股 量化）**验证假设的标准 SOP + 硬规则 + 失败模式 + 命令附录**。凡是要把数字作为"结论"输出前，先跑本技能。.
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
# 假设验证 SOP（本项目的"尺子"） > **一句话**：把"任意市场假设 → 可信地信 / 否"固定成一条**自带反自欺机制**的流水线。 > **本技能的重点不是"会回测"，而是"在最容易被自己骗的地方都预埋了闸"。** > **核心信念**：结论不可信，**十有八九不是算错，而是"口径选错"** > （比较基准 / 采样粒度 / 显著性口径 / ⓠ 同一性）。所以 SOP 的重心是**堵口径**，不是堆指标。 ## 何时用 - 用户问"X 策略行不行 / X 有没有 alpha / 这个数可信吗 / 换个周期(池、特征、成本)会更好吗"。 - **任何要作为"结论"输出的数字**：先过 ⓠ 同一性闸 + A 闸，才轮到其它闸。 - 也用于**提出**假设（第 0 步的"命题 + 预登记"），不只在"验证"时。 --- ## SOP（7 步） ### 0. 命题 + 预登记（**看结果之前**） - 把假设写成**可证伪**形式：`H0 / H1 + 数字或区间`（例：`H0: IC ≤ 0.0234`）。 - **先写死成功/失败判据**（数字/区间），**再看结果**。 - **先问三态**（lessons 三.75）：**算不了**（缺数据 / 无 PIT）？**说不准**（功效不足）？**先验已否**（已有强反证）？ —— 任一命中 **就停，不跑**（省时且防止"跑到一个假阳"）。 ### 1. ⓠ 同一性闸（先于一切） 被评估的**量** = 会用的**量**？四问任一"否"即止： 1. 社区集合（`community_ids`）严格相等？2. 列集合：生产 pkl ⊆ WF 可用列 **且** F1/HIBOR 两边都在？ 3. 时点：`train()` / `predict()` 的 `use_shift`（`mode`）相等？4. 概率同源（`oof_glob` 校准 + 门槛 `GATE_SOURCE_CSV`）？ - 跑：`python3 -m pytest tests/test_pipeline_contract.py`（须 **0 xfailed**）。 ### 2. 数据卫生 + 三冻结 - **无前视**：滚动特征 `.shift(1)`；标签 `Close.shift(-(h+lag))/Close.shift(-lag)-1`；外部行情（HSI/美股）走**对齐函数**，别裸 `merge`。 - **无幸存者**：池成员要 PIT（时点还原），别用"今天还在的成分"回填历史； 除牌检查用 `data/hkex_delisted.csv`。 - **股本/筹码口径**：优先 FF301 `data/hkex_monthly_shares.csv`（历史 30 只）； …
Read the whole file at its exact version.
How to install
mdr add wonglaitung/fortune/hypothesis-validation@sha256:bebbf661cb511c95The line at the top of this page pins the label git:20261101.c5a5005, 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_lkvkg7pz6a46jktm)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Oct 16, 2026 and Nov 1, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261101.c5a5005 latest | 2026-11-01 | c5a5005 | 8,250 B | A | view · diff |
| git:20261025.397351b | 2026-10-25 | 397351b | 8,014 B | A | view · diff |
| git:20261016.42ab3f9 | 2026-10-16 | 42ab3f9 | 8,018 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 (8250 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
wonglaitung/fortune · 92 stars · license none declared · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lkvkg7pz6a46jktm GET https://markdownregistry.com/api/v1/resolve?ref=wonglaitung/fortune/hypothesis-validation GET https://markdownregistry.com/api/v1/blob/bebbf661cb511c95e2c7d5258b25c50356c5436d3d4cbb07cd8f172c6a40029b
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.
More from wonglaitung/fortune
Every file in wonglaitung/fortune