Borrowing it
Nothing to install: this file belongs to levi-qiao/obsidian-llm-wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/levi-qiao/obsidian-llm-wiki/main/.claude/skills/query/SKILL.mdgit clone --depth 1 https://github.com/levi-qiao/obsidian-llm-wikiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/levi-qiao/obsidian-llm-wiki/query)<a href="https://agentmods.dev/skills/levi-qiao/obsidian-llm-wiki/query"><img src="https://agentmods.dev/badge/skills/levi-qiao/obsidian-llm-wiki/query/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/levi-qiao/obsidian-llm-wiki/query"><img src="https://agentmods.dev/badge/skills/levi-qiao/obsidian-llm-wiki/query.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.02115 |
| Opus 5 | $0.00035 | $0.01058 |
| Sonnet 5 | $0.00014 | $0.00423 |
| Haiku 4.5 | $0.00007 | $0.00212 |
Grade A, and why
query scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Query 技能
核心目标
将用户的提问转化为对本地 Wiki 的深度检索。支持三种查询模式，根据问题类型自动选择或手动指定。通过索引系统精准定位相关页面，提取信息，综合出带有明确引用来源的双链回答。
触发条件
- 用户输入
/query <问题>— 精准查询模式 - 用户输入
/query --explore <主题>— 探索查询模式 - 用户输入
/query --relate <概念A> <概念B>— 关系查询模式 - 用户用自然语言询问：
"我的笔记里关于 X 是怎么说的"、"过去我对 Y 的决策是什么"、"查询 Z 相关的知识"
降级策略
如果问题属于纯通用知识（如"太阳系有几颗行星"），且 wiki/index.md 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：[直接回答]
模式 1：精准查询（默认）
适用场景：具体问题，如"什么是 Transformer？"、"Claude Code 的核心功能是什么？"
步骤 1：索引导航
永远的第一步：读取 wiki/index.md
这是总索引，按 domain 和 type 双维度列出所有页面。根据问题关键词，定位到 5-10 个最相关的页面。
判断逻辑：
- 如果问题明确涉及某些实体或概念，直接定位到对应页面
- 如果问题较宽泛，选择多个可能相关的页面
- 如果索引中页面数量过多（> 100），先按 domain 或 type 筛选
关键优化：
- 只读取 wiki/index.md（通常 < 200 行）
- 精准定位到 5-10 个页面，不要全量扫描
步骤 2：深度阅读
只读取定位到的 5-10 个页面：
Read wiki/{type}/{page}.md
获取完整内容，提取与问题相关的信息。
关键优化：
- 只读取步骤 1 定位到的页面，不要额外读取
- 如果 5-10 个页面不足以回答问题，返回步骤 1 重新定位
步骤 3：综合与回答
综合信息，回答用户问题。
双链引用规范：
- 每当引用某个 Wiki 页面的信息，在文本中使用
[[页面名称]]标注 - 整段引用同一页面：段落首尾各引用一次
- 引用特定原文：使用 Markdown 块引用
> 引用内容
回答格式：
根据知识库中的信息：
[回答内容，使用 [[wikilink]] 标注引用]
## 参考页面
- [[type/页面1]] — 简短说明
- [[type/页面2]] — 简短说明
步骤 4：高价值内容固化
如果满足以下条件，主动询问用户是否保存为 synthesis：
- 回答超过 2 个段落
- 内容具有分析对比性或总结性
- 综合了多个页面的信息
询问话术：
这是一个有价值的总结，是否需要我将其保存到 wiki/syntheses/ 目录？
用户同意后，按照 CLAUDE.md 规范创建文件：
---
title: "页面标题"
type: synthesis
domain: AI | 财务 | 健康 | 未分类
tags: [标签1, 标签2, 标签3]
sources: []
last_updated: YYYY-MM-DD
backlinks_count: 0
---
# 总结内容
[回答内容]
## 关联连接
- [[页面1]] — 引用来源
- [[页面2]] — 引用来源
并在 wiki/index.md 的对应 domain 和 Syntheses 分类下注册。
步骤 5：记录操作日志
无论是否生成 synthesis 页面，查询结束后必须在 wiki/log.md 末尾追加：
## [YYYY-MM-DD] query | <操作简述>
- **模式**: 精准查询
- **输出**: <引用页面列表或"即时回答未保存">
- **引用页面**: N 个
模式 2：探索查询（/query --explore <主题>）
适用场景：广度优先探索，如"我对 AI 了解多少？"、"知识库中有哪些关于 LLM 的内容？"
步骤 1：广度扫描
读取 wiki/index.md，找到所有与主题相关的页面（不限数量）
只读取每个页面的 frontmatter + 第一段（摘要），不读取完整内容
步骤 2：生成知识地图
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 264 lines · 70 tokens per session scan A 346c3180c8d4
query is a skill published in the GitHub repository levi-qiao/obsidian-llm-wiki (10 stars, last pushed 27d ago), licensed MIT. It adds 70 tokens to every session and 2,115 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
kb-lint
Health check for the PARA Knowledge Base. Detects orphan documents, broken links, index drift, tag issues, and stale content. Run periodically or as part of weekly review.
kb-index
Update Knowledge Base indexes. Smart mode detects changes and updates only what's needed. Full rebuild available with --full flag. Use after adding/moving documents or when indexes feel stale.
ObsidianDataWeave: NotebookLM, Atomization, and LLM Wiki
Use when the user wants to control NotebookLM programmatically, import .docx into an Obsidian vault as atomic Zettelkasten notes, build a compiled LLM Wiki layer, or full-text-search the whole vault. Claude Code and Codex both supported.
wiki-ingest
File a new source into the LLM Wiki — create its Sources page, append a log entry, apply the proposed cross-reference edits. Use when the user says "ingest this", "file this source", "add this to the wiki", drops a URL/PDF/clipped article, or pastes notes they want captured. Never auto-applies cross-refs without…
wiki-lint
Health-check the LLM Wiki and offer fixes for each category of finding. Use when the user says "lint the wiki", "audit the wiki", "check wiki health", "clean up the wiki", or after a batch of ingests. Categories covered - orphans, broken links, stale sources, missing pages, tag drift, index parity.