Agent skill

Zhouyilab Testing

by banderzhm in banderzhm/ZhouYiLab

为 ZhouYiLab 排盘或分析变更设计回归测试、运行示例并核验报告时区分独立基准和契约检查. An agent skill from banderzhm/ZhouYiLab.

MITAuto-check passed

Install Zhouyilab Testing

skills CLI
$ npx skills add banderzhm/ZhouYiLab --skill zhouyilab-testing -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install banderzhm/ZhouYiLab zhouyilab-testing --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/banderzhm/ZhouYiLab.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/zhouyilab-testing .claude/skills/zhouyilab-testing && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
zhouyilab-testing
GitHub stars
137
Token cost
~271 tokens
SKILL.md length
37 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

为 ZhouYiLab 排盘或分析变更设计回归测试、运行示例并核验报告时区分独立基准和契约检查. An agent skill from banderzhm/ZhouYiLab.

  • SKILL.md covers 回归与示例分离 and 执行与隔离
  • Calls cmake

What it does

Zhouyilab Testing is an agent skill from banderzhm/ZhouYiLab. 为 ZhouYiLab 排盘或分析变更设计回归测试、运行示例并核验报告时区分独立基准和契约检查。

Its SKILL.md is about 270 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 玄学计算引擎,包含大六壬、六爻、紫薇斗数、八字、奇门遁甲、梅花易数,适用于玄学算法训练、文化研究或教育类项目。 The licence is MIT.

Example prompts

  • “/zhouyilab-testing”

What it can do on your machine

Read from SKILL.md and the folder at commit d8aea5d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • cmake

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Zhouyilab Testing loads about 271 tokens when it runs. Until then it costs about 17 tokens; SKILL.md has 37 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~17
When it runs · the whole SKILL.md, loaded when a task matches
~271

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from banderzhm/ZhouYiLab at commit d8aea5d, republished under its MIT licence (© banderzhm). 37 words, ~271 tokens.

Download SKILL.mdSave it as .claude/skills/zhouyilab-testing/SKILL.md (or your agent's skills folder).
name
zhouyilab-testing
description
为 ZhouYiLab 排盘或分析变更设计回归测试、运行示例并核验报告时区分独立基准和契约检查。

回归与示例分离

  • tests/ 放独立回归目标并注册 CTest;examples/ 演示真实入口与完整排盘报告,不承担另一份算法或大量断言语料。测试链接生产模块,不复制生产算法算“预期”。
  • 固定预期注明参考来源、输入历法、地点/时间口径及流派。修复前保留失败案例;不能因新结果不同就自动刷新预期,也不能只看报告读起来合理。
  • 每条新规则覆盖成立、不成立、边界和组合场景,检查方向、参与位置、角色互斥、来源去重及原局/岁运一致性。半合不能当三合成化,同支/同柱/自刑按条件分别断言。
  • 例如盲派跨层修复可保留 2023 三合、2033 三刑、2025 争合、2017 自刑/交运/填实这组结构回归;它们验证规则检出,不证明个人事件可预测。
  • 所有时间入口检查未提供 location 时原时间不变、有地点时统一修正、跨日/节气及无效日期。新增报告字段同时检查 JSON、中文映射和 Markdown 表格,验证结果而非仅检查字段存在。

执行与隔离

sh
cmake -S . -B build -DBUILD_EXAMPLES=ON -DBUILD_TESTING=ON
cmake --build build --config Debug --parallel
ctest --test-dir build -C Debug --output-on-failure --no-tests=error

首次配置还须按实际平台选择编译器、生成器及模块模式;不得混用已有构建目录的工具链。

  • CTest 报告工作目录在 build/tests/reports/<术数>/。手工运行测试也用隔离目录,不能覆盖源码 docs/。用户要求更新示例 txt 时才运行对应输出流程并核对目标路径。
  • 修改 C++ 模块至少构建受影响目标并运行相关测试;公共契约、基础规则、构建链路变更运行全量现有回归及示例编译。
  • 现有三套 CTest 为紫微、奇门、梅花,详见 tests/README.md;其他模块若缺独立测试应补测试,不以“全量 CTest 通过”声称所有术数均有覆盖。
  • 编译、链接、执行、独立预期逐值核对、穷举契约检查和展示检查分别记录。性能提升若没有测量,只能说明减少了哪些重复工作,不报虚构百分比。

© banderzhm, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/zhouyilab-testing of banderzhm/ZhouYiLab.

Open the folder on GitHubat commit d8aea5d

Compare with similar skills

Zhouyilab Testing next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Zhouyilab Testing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Zhouyilab Testing this skillbanderzhm/ZhouYiLab137—~271Automated safety check: PassMIT
Zhouyilab Workflowbanderzhm/ZhouYiLab137—~126Automated safety check: PassMIT
Zhouyilab Domainbanderzhm/ZhouYiLab137—~297Automated safety check: PassMIT
Zhouyilab Reportingbanderzhm/ZhouYiLab137—~217Automated safety check: PassMIT
Zhouyilab Modulesbanderzhm/ZhouYiLab137—~367Automated safety check: PassMIT
Zhouyilab Buildbanderzhm/ZhouYiLab137—~259Automated safety check: PassMIT

Similar skills

  • Zhouyilab Workflow

    banderzhm/ZhouYiLab

    在 ZhouYiLab 仓库执行代码、文档或审查任务时确定工作范围、工具选择与交付边界. An agent skill from banderzhm/ZhouYiLab.

    137 GitHub stars~126 tokensUpdated 13 days ago
    Auto-check passed
  • Zhouyilab Domain

    banderzhm/ZhouYiLab

    修改 ZhouYiLab 排盘、干支关系、原局及岁运分析时约束共用基础复用、流派口径与时间语义. An agent skill from banderzhm/ZhouYiLab.

    137 GitHub stars~297 tokensUpdated 13 days ago
    Auto-check passed
  • Zhouyilab Reporting

    banderzhm/ZhouYiLab

    修改 ZhouYiLab 中文报告、Markdown 表格及 JSON 输出时保证展示职责、专业术语和结构化结果一致. An agent skill from banderzhm/ZhouYiLab.

    137 GitHub stars~217 tokensUpdated 13 days ago
    Auto-check passed
  • Zhouyilab Modules

    banderzhm/ZhouYiLab

    在 ZhouYiLab 新增或重构 C++23 模块、分析入口与公共契约时规范分层、依赖和 cppm/cpp 组织. An agent skill from banderzhm/ZhouYiLab.

    137 GitHub stars~367 tokensUpdated 13 days ago
    Auto-check passed
  • Zhouyilab Build

    banderzhm/ZhouYiLab

    修改 ZhouYiLab 的 CMake、依赖、模块构建和 GitHub Actions 时保持三平台兼容及真实运行验证。

    137 GitHub stars~259 tokensUpdated 13 days ago
    DevOps & CloudAuto-check passed
  • Zhouyilab Cpp Style

    banderzhm/ZhouYiLab

    编写 ZhouYiLab C++ 代码时落实性能、命名、枚举定义、成员注释和 WSL clang-format 规范. An agent skill from banderzhm/ZhouYiLab.

    137 GitHub stars~289 tokensUpdated 13 days ago
    Auto-check passed

More from banderzhm/ZhouYiLab

All 8 skills in this repo
  • Zhouyilab Skill Maintenance

    banderzhm/ZhouYiLab

    维护 ZhouYiLab 仓库 skills 规范、聚合顺序及 AGENTS.md 生成脚本时使用,避免规范重复和生成文件漂移。

    137 GitHub stars~288 tokensUpdated 13 days ago
    Auto-check passed

Questions about Zhouyilab Testing

What does Zhouyilab Testing do?

为 ZhouYiLab 排盘或分析变更设计回归测试、运行示例并核验报告时区分独立基准和契约检查. An agent skill from banderzhm/ZhouYiLab. Zhouyilab Testing is an agent skill from banderzhm/ZhouYiLab.

How do I install Zhouyilab Testing in Claude Code?

Run `npx skills add banderzhm/ZhouYiLab --skill zhouyilab-testing -a claude-code`. Or copy the skill folder (skills/zhouyilab-testing in banderzhm/ZhouYiLab) into .claude/skills/zhouyilab-testing in your project. Claude Code loads it when a task matches its description.

How do I install Zhouyilab Testing in Codex?

Run `npx skills add banderzhm/ZhouYiLab --skill zhouyilab-testing -a codex`. Or copy the skill folder (skills/zhouyilab-testing in banderzhm/ZhouYiLab) into .agents/skills/zhouyilab-testing in your project. Codex loads it when a task matches its description.

Can I use Zhouyilab Testing in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add banderzhm/ZhouYiLab --skill zhouyilab-testing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/zhouyilab-testing, .gemini/skills/zhouyilab-testing, .github/skills/zhouyilab-testing and .opencode/skills/zhouyilab-testing in your project.

What does Zhouyilab Testing need to run?

Going by SKILL.md and its folder, Zhouyilab Testing needs the command-line tools its instructions call (cmake).

Does Zhouyilab Testing access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Zhouyilab Testing safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Zhouyilab Testing use?

Zhouyilab Testing is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Zhouyilab Testing use?

About 271 tokens (SKILL.md is roughly 1.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Zhouyilab Testing?

Skills that share tags, products or a category with Zhouyilab Testing: Zhouyilab Workflow (banderzhm/ZhouYiLab, 137 stars), Zhouyilab Domain (banderzhm/ZhouYiLab, 137 stars), Zhouyilab Reporting (banderzhm/ZhouYiLab, 137 stars) and Zhouyilab Modules (banderzhm/ZhouYiLab, 137 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Zhouyilab Testing?

banderzhm (a GitHub user) maintains it in banderzhm/ZhouYiLab, which has 137 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 28, 2026.

Source: banderzhm/ZhouYiLab on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.