experiment-analysis SKILL.md skillA
experiment-analysis from kimyx0207/kim_service is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kimyx0207/kim_service/experiment-analysis@git:20261110.c4dcec8Pins git:20261110.c4dcec8 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kimyx0207/kim_service
- Path
skills/experiment-analysis/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261110.c4dcec8, committed Nov 10, 2026
- Size
- 3,443 bytes
- Repository stars
- 193
- License
- MIT
设计和审查随机实验、分流质量、指标与效果解释 experiment analysis A/B testing randomization SRM.
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
# 实验设计与结果分析 在讨论效果之前核对实验分配、观测单位和数据质量,以可复核的指标与不确定性支持决策。 ## 开始前 - `design`:问题、假设、分配单位、目标人群、分流、期间和预先决策规则 缺失时:缺随机设计只做有范围的描述分析 - `observations`:按正确单位的分组样本、事件、缺失和曝光记录 缺失时:缺计数或分组无法给精确效果 - `metrics`:主要指标、护栏、分母、窗口、实际意义和多重检验计划 缺失时:先定义指标,不挑最好看的结果 ## 执行 1. 阅读 [工作方法](references/professional-method.md),先确定适用条件与证据范围。 2. 沿 [专业方法](method.json) 的 `steps` 执行具体操作,再用 [完整交付模板](references/delivery-template.md) 整理当前产物;诊断问题与空字段不能充当完成。 3. 按 [专业质量规则](method.json) 中的具体输出规则选择检查方法,保存本次输入/产物定位及未观察项。 4. 对照 [作者正反例](evals/professional-cases.json) 检查常见专业错误;作者预期不算本次评测结果。 5. 把规则结果、实际产物、未决问题交回调用方;缺口仅影响相关结论。 ## 交付 - `designReview`:可检验假设和识别边界。 - `integrityReview`:分流与数据可信度检查。 - `effectEstimate`:绝对/相对效果及不确定性。 - `decision`:效果、护栏与下一步。 - `facts`:当前输入、来源、期间单位及证据缺口。 - `limitations`:未执行、未观察、方法假设和外推边界。 - `handoff`:当前产物、规则结果、证据定位与待解决事项交调用方。 ## 关键验收条件 - `designReview`:写分配/分析单位、目标效果、干预与窗口;声明是否支持因果。 拒收:观察性分组、单位不独立或跨组污染被隐藏。 - `integrityReview`:核预期分流、实际入组/曝光、缺失、重复和SRM线索,失败时限制效果结论。 拒收:分流异常未解释仍挑显著结果,或删除坏组掩盖异常。 - `effectEstimate`:按声明分母重算各组指标、差值、相对变化,区间方法与适用前提可追溯。 拒收:百分点与百分比混淆、零基线照算相对提升,或没计算声称显著。 - `decision`:综合事前主要指标、实际意义、护栏、观察期与多重比较,列可支持和不可支持决定。 拒收:只靠p值或挑次要指标忽略负面护栏,或随时窥视后当固定样本检验。 …
Read the whole file at its exact version.
How to install
claude plugin marketplace add https://markdownregistry.com/mp/a/art_laa3ykhjiubjmwgp/6460cbea0e5b0d7e39c87db0f4036755508796367f3c8ea9a8bf57a631802abf.json
Then /plugin install experiment-analysis@markdownregistry-laa3ykhjiubjmwgp in Claude Code. It installs git:20261110.c4dcec8, the one graded A here, pinned to the commit it was graded at, and leaves it there.
mdr add kimyx0207/kim_service/experiment-analysis@sha256:6460cbea0e5b0d7eThe line at the top of this page pins the label git:20261110.c4dcec8, 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_laa3ykhjiubjmwgp)
2 badge image fetches in 30 days. What the badge shows.
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it: what changed in kimyx0207/kim_service/experiment-analysis since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.
Got a copy of experiment-analysis from somewhere else? Ask it: where did my experiment-analysis come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.
Versions
The registry has recorded 1 version of this file, committed on Nov 10, 2026.
Watch this file (sign in, one email per new version)
Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.
Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml
It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.
Installed this file, say at .claude/skills/experiment-analysis/SKILL.md? Drop it here to learn which saved version you have and what changed since. Your browser works out its SHA-256 fingerprint and sends only that; the file itself never leaves your computer.
Or paste its contents
Your agent can run this same check on the agent markdown files you have installed, up to 50 in one ask. Add the registry once:
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it to check the files you have installed. No key and no account.
From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies
In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies
No sha256sum on your machine? shasum -a 256 prints the same lines.
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 (3443 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
kimyx0207/kim_service · 193 stars · license MIT · pushed 2026-11-17 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_laa3ykhjiubjmwgp GET https://markdownregistry.com/api/v1/resolve?ref=kimyx0207/kim_service/experiment-analysis GET https://markdownregistry.com/api/v1/blob/6460cbea0e5b0d7e39c87db0f4036755508796367f3c8ea9a8bf57a631802abf
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 kimyx0207/kim_service
Every file in kimyx0207/kim_service