← Back to Skills Marketplace
622
Downloads
3
Stars
3
Active Installs
15
Versions
Install in OpenClaw
/install siyuan-skill
Description
思源笔记API转CLI工具，支持笔记本管理、文档操作、内容搜索、块控制。当用户操作思源笔记、管理笔记本、创建/更新/删除文档、搜索内容、管理块时调用。
Usage Guidance
This skill appears to do what it claims, but review and consider the following before installing/running:
- Inspect the included JavaScript files (they are bundled with the skill) before executing. Because there is no installation sandbox, the code will run under Node in your environment.
- Provide SIYUAN_BASE_URL and SIYUAN_TOKEN only for a Siyuan instance you control/trust. The token grants API access to your notes.
- Optional features (vector search, embedding, Qdrant, OLLAMA or external EMBEDDING_BASE_URL) will send note content or embeddings to those external services — do not enable them for sensitive data unless you trust the destination and understand data retention/privacy.
- The connector supports allowing self-signed TLS certificates; enabling that (SIYUAN_TLS_ALLOW_SELF_SIGNED and SIYUAN_TLS_ALLOWED_HOSTS) weakens TLS validation and should be used only for trusted internal endpoints.
- The CLI can read local files when given a --file path. Be mindful an automated agent invoking this skill could be used to read files if given paths; rely on the skill's delete-protection settings and do not grant the agent broad autonomy if you are concerned about file access.
If you want higher assurance, run the code in a restricted/test environment first, and verify that network endpoints used by embedding/Qdrant are the ones you expect.
Capability Analysis
Type: OpenClaw Skill
Name: siyuan-skill
Version: 1.7.8
The siyuan-skill bundle is a legitimate CLI tool for interacting with the Siyuan Notes API. It features a well-structured codebase with explicit security implementations, including a notebook-level permission system (utils/permission.js), multi-layered delete protection (utils/delete-protection.js), and SQL injection mitigation for search queries (lib/search-manager.js). The documentation in SKILL.md specifically instructs the AI agent to respect safety configurations and avoid unauthorized modifications. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; all network activity is directed to user-configured local or private endpoints (Siyuan API, Qdrant, and Ollama).
Capability Assessment
Purpose & Capability
Name/description, required binaries (node), and required env vars (SIYUAN_BASE_URL, SIYUAN_TOKEN, SIYUAN_DEFAULT_NOTEBOOK) align with a Siyuan Notes CLI/connector. Optional environment variables and modules (Qdrant, embedding, NLP) are appropriate for the described vector-search/NLP features.
Instruction Scope
SKILL.md instructs running the provided Node CLI (node siyuan.js ...) and documents config and environment usage. Instructions reference only relevant files/config (config.json) and the Siyuan API. The CLI can read files when a --file option is provided (expected for content import), but SKILL.md does not instruct collecting unrelated system data.
Install Mechanism
No install spec is provided (instruction-only install), which is low-risk. However the skill bundle includes many code files (JS modules and a CLI). Because there is no automated install step, the code will run where Node is available; users should verify and inspect the included source before running.
Credentials
Required env vars are proportional to purpose; SIYUAN_TOKEN is the primary credential and is justified. Several optional env vars enable external services (Qdrant, embedding providers such as OLLAMA/EMBEDDING_BASE_URL) — enabling them will send document content or embeddings to those external endpoints, so users should only set those when they trust the target services.
Persistence & Privilege
The skill does not request always:true and does not modify other skills. It reads/writes its own config and enforces a delete-protection policy; autonomous invocation is allowed (platform default) but not combined with elevated privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install siyuan-skill - After installation, invoke the skill by name or use
/siyuan-skill - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.7.8
siyuan-skill v1.7.8
- 更新版本号至1.7.8并重构版本管理
- 将版本号集中管理，从package.json移至index.js导出
v1.7.7
siyuan-skill 1.7.7
- 元数据字段从 "clawdbot" 调整为 "openclaw"
- 增加对更多可选环境变量的声明，包括向量搜索/NLP/安全相关配置
- 主用环境变量由 SIYUAN_BASE_URL 改为 SIYUAN_TOKEN
- 配套文档、命令和主要功能无实际变动
v1.7.6
- 移除了 package.json 文件。
- skill 配置描述（description）补充 API 表述，更加准确。
- 新增 metadata 字段，包含 Clawdbot 兼容信息和运行环境需求（如 node、必要环境变量）。
- CLI 示例中将 “siyuan” 命令补充为 “node siyuan.js”，强调调用方式。
- 其余文档结构和功能命令保持原样，无功能变更。
v1.7.5
**siyuan-skill v1.7.5**
- 新增 references/advanced/writing-guide.md，补充了内容书写规范和指南。
- 新增 references/commands/icon.md，文档化了“icon”命令和文档图标设置用法。
- SKILL.md 增加了 skillType 字段。
- 命令速查与最佳实践部分，增加了 icon/图标相关说明与用法示例。
- 书写规范部分现在指向新加入的 writing-guide.md 文档。
- 部分内容及参考文档目录进行了更新，细化书写、图标设置规范。
v1.7.4
siyuan-skill 1.7.4
- 新增 homepage 字段，补充了项目主页信息。
- CLI 操作原则和禁止绕过/直连 API 说明更加明确。
- 命令决策表分类优化，分为“笔记本与文档操作”和“块操作”。
- 各类命令参数补充，示例和参数选项更详细。
- 其它文档结构调整，使约束、安全、实践等说明更加清晰。
v1.7.3
siyuan-skill v1.7.3 Changelog
- SKILL.md 安装指引优化，推荐从 ClawHub 下载并更新相关说明
- 增加强调：严禁自动修改配置文件/环境变量，必须手动配置
- 明确约束：CLI 命令必须用于操作，不可直接调用 API 避免权限泄露
- 环境变量和功能说明部分小幅调整，内容表述更清晰
- 其他文档格式微调，内容未作功能或命令变更
v1.7.2
Version 1.7.2
- 增加 required_env_vars 和 optional_env_vars 字段，明确必需和可选环境变量及其描述。
- 指明 SIYUAN_BASE_URL、SIYUAN_TOKEN、SIYUAN_DEFAULT_NOTEBOOK 等为必需环境变量及用途。
- 对部分环境变量添加详细说明、是否必需及默认值示例，提升易用性和配置安全性。
- 其余说明和功能未作修改。
v1.7.1
siyuan-skill 1.7.1
- 增加 installType、installSpec 字段，完善 Git 克隆安装说明。
- 安全要点部分补充“配置只读保护”、“Token 安全”、“可选功能”子章节。
- 明确本技能不会自动写入/修改任何配置文件或 token，敏感信息仅读不写。
- 向量搜索/NLP 相关环境变量设置解释更详细，可选配置说明更清晰。
- 其余说明及使用文档结构未变。
v1.7.0
siyuan-skill v1.7.0
- 重大结构优化：所有文档迁移到 references/ 下，原 doc/ 路径废除，使文档结构更清晰。
- 新增 info 命令与对应文档，用于获取文档基础信息。
- 详细完善命令、参数与最佳实践指南，大幅补充与规范快速决策表、工作流与错误预防说明。
- 拆分并补全安装、环境变量、配置、安全、高级功能等独立参考文档。
- 移除内嵌大段教程，统一指引至 references/ 下分章节文档。
- 同步改进命令帮助、环境变量要求和使用示例。
v1.6.15
- Switched install type from "executable" to Git clone; added git-based install instructions and parameters.
- Updated and expanded environment variable options, including notebook list and timeout configuration.
- Improved and reorganized documentation: added a quick decision table, standard workflows, and concise best practices.
- Added new block operation command: `block-transfer-ref` (`btr`).
- Removed two code files: `lib/sync-manager.js` and `utils/cache.js`.
v1.6.12
siyuan-skill 1.6.12
- 新增文档“INSTALL.md”及相关开发说明文档
- 新增 `check-exists`、`update-document` 等命令，支持文档存在性检测和内容更新
- 新增 `lib/chinese-dictionary.js`、`lib/chinese-tokenizer.js`，添加中文分词和字典能力
- 命令层面严格区分文档/块操作（`update` 仅限文档ID，`block-update` 仅限块ID），错误类型ID将返回提示
- `create`、`move`、`rename` 命令自动进行重名检测，新增 `exists` 命令手动检测文档是否存在
- 文档重构与精简，环境变量与参数说明更加清晰直接
v1.6.3
siyuan-skill 1.6.3
- 增加 skill 元数据字段 skillType: "cli" 和 installType: "executable"，更精准描述技能类型和部署方式。
- 明确说明不允许 agent 自动修改配置文件与环境变量配置，加强安全约束表述。
- 相关文档中增加 CLI 和 API 的交互说明，强调交互方式。
- 其他说明性内容微调，无功能与命令变更。
v1.6.2
- Added `runtime` and `runtimeVersion` fields to SKILL.md for clearer Node.js runtime requirements.
- Updated constraints and documentation: removed references to agent-specific restrictions, now simply prohibit direct API and config modification.
- Clarified documentation guidance: changed “禁止agent自动修改配置文件与本技能相关环境变量配置” to “禁止自动修改配置文件与本技能相关环境变量配置”.
- Enhanced documentation guidance: users are now encouraged (not required) to consult docs before reading source code, and noted that the skill is fully open-sourced.
- No code or feature changes; documentation updates only.
v1.6.1
**Summary:**
This is a major update that adds granular “block” operation commands, introduces new documentation, and enhances environment variable configuration and documentation structure.
- Added extensive block operation commands (insert, update, delete, move, fold, attributes, tags, transfer ref, get info) for more granular document editing.
- Introduced detailed documentations for advanced features and each command, especially block control and protection mechanisms.
- Enhanced environment variable specification in SKILL.md and added clear “required_env_vars” for deployment and usage clarity.
- Updated and expanded SKILL.md with sectioned navigation, best practices, and clearer constraints, making usage, configuration, and troubleshooting much easier.
- Removed the command for direct document update and switched to a more granular block-based approach.
- Improved instructions and best practices for document content formatting, protection, and property/tag modification.
v1.3.2
siyuan-skill 1.3.2
- 新增详细 SKILL.md，系统性说明工具核心价值、关键原则、约束及使用场景
- 明确推荐命令行（CLI）作为唯一操作入口，禁止直连 API 和脚本调用
- 丰富命令及参数说明，列出常用命令和帮助指引
- 增加环境变量、配置文件说明及权限模式说明
- 强调缓存、向量搜索、增量索引等高级特性使用条件与注意事项
- 增补官方文档和用户指南引用链接
Metadata
Frequently Asked Questions
What is Siyuan Skill?
思源笔记API转CLI工具，支持笔记本管理、文档操作、内容搜索、块控制。当用户操作思源笔记、管理笔记本、创建/更新/删除文档、搜索内容、管理块时调用。 It is an AI Agent Skill for Claude Code / OpenClaw, with 622 downloads so far.
How do I install Siyuan Skill?
Run "/install siyuan-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Siyuan Skill free?
Yes, Siyuan Skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Siyuan Skill support?
Siyuan Skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Siyuan Skill?
It is built and maintained by daze (@dazexcl); the current version is v1.7.8.
More Skills