structai skillA
structai is agent-read markdown (skill) from black-yt/skills: Use when building, testing, or debugging LLM applications with the StructAI Python toolkit, including LLMAgent calls, structured outputs, LLM judging, batch concurrency, file/PDF utilities, text parsing, private-IP no_proxy handling, and timeout wrappers..
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
# StructAI ## 使用边界 - 用于基于 `structai` 快速搭建 LLM workflow、批量推理、结构化输出、评测、PDF 解析和常用 I/O。 - 不要把 API key、token、私有 base URL 写进代码或日志；优先读取环境变量。 - 不要擅自安装、升级或修改共享 Python/conda 环境；需要安装 `structai` 或依赖时，先征得用户同意。 - 如果本地 `structai` 版本和示例不一致，先用 `python -c "from structai import structai_skill; print(structai_skill())"` 查看当前版本文档。 ## 环境变量 ```bash export LLM_API_KEY="[API_KEY]" export LLM_BASE_URL="[OPENAI_COMPATIBLE_BASE_URL]" export MINERU_TOKEN="[MINERU_TOKEN]" # 仅 PDF 解析需要 ``` - PyPI 安装：`pip install structai` - GitHub 源码：https://github.com/black-yt/structai ## 上游版本锚点 - 当前 skill 对照 structai `pyproject.toml` package version：`0.1.24`。 - 当前 skill 对照 GitHub HEAD：`d20df602578bee124a9c93b293493e63212d0aab`。 - 维护本 skill 前，先重新检查上游 `pyproject.toml` 版本和 HEAD；如果任一变化，必须阅读 README、`pyproject.toml`、`structai_skill()` 输出和相关源码后再更新。 安装模板： ```bash pip install structai ``` 开发版本模板： ```bash git clone https://github.com/black-yt/structai.git cd structai pip install -e . ``` ## 源码追溯 - 如果示例和当前行为不一致，优先追溯已安装包源码，而不是猜测 API。 - `inspect.getsource(...)` 适合快速查看函数、类、方法的真实实现。 - `module.__file__` 可定位包安装路径，再按需打开源码文件。 - 源码只用于阅读和定位问题，不要改源码，不要修改 `site-packages` 或共享环境；需要改库时，先 clone 仓库并使用 editable install，且必须征得用户同意。 ```python …
Read the whole file at its exact version.
How to install
mdr add black-yt/skills/structai@git:20260713.9b7b32bmdr add black-yt/skills/structai@sha256:3e63e8bc28a17782Pin 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_z23d422m7nh557oj)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260713.9b7b32b latest | 2026-07-13 | 9b7b32b | 11,219 B | A | view · diff |
| git:20260605.e763408 | 2026-06-05 | e763408 | 10,641 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 (11219 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
black-yt/skills · 13 stars · license none · pushed 2026-09-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_z23d422m7nh557oj GET https://markdownregistry.com/api/v1/resolve?ref=black-yt/skills/structai GET https://markdownregistry.com/api/v1/blob/3e63e8bc28a17782c1a6de2082d1ce577e71a4d4dac29958e706e6634dce9fb7
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.