query SKILL.md skillA
query from lkhfrgc/scholar-llm-wiki is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add lkhfrgc/scholar-llm-wiki/query@git:20261006.643223dPins git:20261006.643223d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- lkhfrgc/scholar-llm-wiki
- Path
.dsh/skills/query/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261006.643223d, committed Oct 6, 2026
- Size
- 7,086 bytes
- Repository stars
- 6
- License
- MIT
在本地 LLM Wiki 知识库中检索并回答问题。支持 `/query <问题>`。先读 index.md 定位，再深度阅读相关页面，综合出带 [[双链]] 引用的答案；若回答产生新洞见，主动提议保存为 synthesis / connection / question 页面。当用户说「wiki 里有没有关于 X 的内容」「帮我查一下 Y」「我的笔记里关于 Z 是怎么说的」时触发。禁止凭模型记忆回答。.
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
# query 技能 ## 前置：初始化 若 `.dsh/wiki.config.json` 或根目录的 `index.md` 不存在，说明骨架尚未生成，先跑一次 `python .dsh/scripts/setup_wiki.py`。知识库还没建立时没有可检索的内容，此时如实告知用户并建议先摄入资料。 ## 路径以配置为准 `.dsh/wiki.config.json` 是本仓**唯一配置源**，目录名与文件名都从它读，不写死绝对路径： ```bash python .dsh/scripts/wiki_env.py --paths # 常用目录一览 ``` > 下文出现的 `wiki/papers/`、`wiki/concepts/`、`index.md`、`log.md` 等**均为默认值**；若 `wiki.config.json` 改过，以配置为准，拿不准先跑上面的自省命令。 ## 核心目标 将用户的提问转化为对本地 Wiki 的深度检索。从 `wiki/` 下的 papers、concepts、connections、questions、syntheses 中提取相关信息，综合出带有明确 [[双链]] 引用的回答。当回答产生新洞见时，主动将其固化为知识库的一部分。 ## 触发场景 - 用户输入 `/query <问题>` - 用户用自然语言询问知识库内容，如"wiki 里有没有关于 X 的资料"、"帮我查一下 Y 概念"、"Z 和 W 之间有什么关系"、"有哪些论文讨论了 Q" - 用户提及 wiki、知识库、论文、概念、连接等关键词且需要检索答案时 ## 降级策略 如果问题属于纯通用知识（如"今天天气怎么样"），且通过步骤 1 确认 `wiki/` 中无相关内容： > 本地知识库中未找到相关内容，以下为通用知识回答： 然后直接基于通用知识回答。**此情况下不记录 log.md**（因为未使用知识库）。 如果问题与工作区关注的主题相关但 wiki 中确实没有覆盖，如实告知并建议用户摄入相关资料。 --- ## 检索与综合流水线 ### 步骤 1：查阅全局索引 + 关键词搜索 **永远的第一步**：读取 `index.md`。 在 index.md 中定位与问题相关的页面。index.md 的分类结构如下（与 AGENTS.md 一致）： - **Papers** — 论文讲解页面（一篇论文一个文件） - **Concepts** — 概念定义 - **Connections** — 跨概念连接 - **Questions** — 开放研究问题 - **Syntheses** — 综合论述 …
Read the whole file at its exact version.
How to install
mdr add lkhfrgc/scholar-llm-wiki/query@sha256:2abf0ba2a5be2e9fThe line at the top of this page pins the label git:20261006.643223d, 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_xubvnzki2an5e3sz)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 6, 2026.
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 (7086 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
lkhfrgc/scholar-llm-wiki · 6 stars · license MIT · pushed 2026-10-11 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xubvnzki2an5e3sz GET https://markdownregistry.com/api/v1/resolve?ref=lkhfrgc/scholar-llm-wiki/query GET https://markdownregistry.com/api/v1/blob/2abf0ba2a5be2e9f56f50e21fd1fe852cfcb9f8a14a4586008a17e479a38f9ec
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 lkhfrgc/scholar-llm-wiki
Every file in lkhfrgc/scholar-llm-wiki