← 返回 Skills 市场
Obsidian Semantic Search
作者
Maxime Roy (new.blacc)
· GitHub ↗
· v1.0.1
· MIT-0
228
总下载
1
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install obsidian-semantic-search
功能描述
Semantic search across your Obsidian vaults using local embeddings (Ollama + pgvector). 10 MCP tools: hybrid/semantic/keyword search, file CRUD, batch reads,...
安全使用建议
This skill appears to implement what it claims (local semantic search) but has several mismatches and risky steps you should review before running: 1) SKILL.md asks you to run remote install scripts (curl | sh) — inspect those scripts on GitHub/astral.sh before executing or prefer cloning and running locally. 2) The registry only declared OBSIDIAN_VAULT, but the installer requires additional env vars (POSTGRES_PASSWORD, optional EMBEDDING_MODEL, OBSIDIAN_VAULTS). Provide only a database password you control; do not reuse other secret tokens. 3) The installer will run Docker containers and persist services that read your vault files — consider running initially in a disposable VM or containerized environment. 4) The instructions suggest writing into Claude Desktop's config files in your home directory; back up that config before modifying and only apply the suggested changes if you trust the repo. 5) If you want lower risk, manually git clone the repository, inspect install.sh and any Dockerfiles, and run the setup steps yourself rather than using piped installers. If you are not comfortable auditing the install scripts or exposing a local DB/service, treat this skill as higher-risk.
功能分析
Type: OpenClaw Skill
Name: obsidian-semantic-search
Version: 1.0.1
The skill bundle is classified as suspicious primarily because SKILL.md contains explicit instructions to ignore security warnings (VirusTotal) and use a `--force` flag, which is a common social engineering tactic to bypass detection. It also utilizes a high-risk installation method via `curl | bash` from an external GitHub repository (celstnblacc/obsidian-semantic-mcp). While the tools for semantic search and vault management are consistent with the stated purpose, the attempt to preemptively discredit security alerts and the use of unverified remote scripts present a significant security risk.
能力评估
Purpose & Capability
The stated goal—local semantic search of an Obsidian vault using Ollama + pgvector—fits the required use of Docker, Python, and a vault path. However the registry metadata and SKILL.md disagree: SKILL.md expects additional services (Postgres, Ollama, a dashboard) and tools (osm CLI, uv installer) that are not fully reflected in the declared requirements. Requiring 'uv' as a binary is unusual but explained by the SKILL.md installer. Overall capability is coherent but the declared requirements are incomplete.
Instruction Scope
The SKILL.md tells users to run remote install commands (curl|bash), clone a GitHub repo, bootstrap services in Docker, and it instructs adding entries to another application's config file (Claude Desktop JSON in user home). It also references environment variables (POSTGRES_PASSWORD, EMBEDDING_MODEL, OBSIDIAN_VAULTS, DASHBOARD_PORT) that are not listed in the registry metadata. The instructions will read and index user files (expected) but also write configuration into other app paths (modifying Claude Desktop config), which is outside a simple search tool's internal state and increases risk.
Install Mechanism
There is no formal install spec in the registry; the SKILL.md instructs executing remote installers: an install.sh from raw.githubusercontent.com and downloading an installer from astral.sh (uv). Running curl ... | sh is a high-risk pattern because it executes code fetched at runtime. The GitHub raw URL is a well-known host (lower risk than an unknown host) but the astral.sh host is a separate domain. The process will pull and run Docker containers and create persistent services.
Credentials
Declared required env in registry is only OBSIDIAN_VAULT, but SKILL.md requires/mentions several additional env vars (POSTGRES_PASSWORD is marked 'Yes (Docker)', OBSIDIAN_VAULTS, EMBEDDING_MODEL, RERANK_MODEL, DASHBOARD_PORT). The skill also references file-system paths and suggests editing Claude Desktop's config file — these are broader privileges than the simple registry declaration implies. Asking for a database password and the ability to run Docker is proportionate to running a local DB, but the mismatch between declared and used envs is a red flag.
Persistence & Privilege
The skill does not set always:true and defaults to allowing model invocation, which is normal. However the installation creates persistent services (Docker containers, PostgreSQL, watcher) and instructs edits to another application's configuration (Claude Desktop). Persisting services and modifying other app configs combined with the remote-install pattern increases the blast radius if something goes wrong.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install obsidian-semantic-search - 安装完成后，直接呼叫该 Skill 的名称或使用
/obsidian-semantic-search触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.1
Add VirusTotal false positive note to troubleshooting
v1.0.0
Initial release of Obsidian Semantic Search.
- Provides semantic, hybrid, and keyword search across Obsidian vaults using local embeddings (Ollama + pgvector)
- Offers 10 MCP tools for search, file management, batch operations, live re-indexing, and monitoring
- Fully local and privacy-focused—no API keys, no cloud, zero cost
- Includes a real-time monitoring dashboard and search testing UI
- Supports both Docker and native (macOS/Linux) installation options, with multi-vault support
元数据
常见问题
Obsidian Semantic Search 是什么？
Semantic search across your Obsidian vaults using local embeddings (Ollama + pgvector). 10 MCP tools: hybrid/semantic/keyword search, file CRUD, batch reads,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 228 次。
如何安装 Obsidian Semantic Search？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install obsidian-semantic-search」即可一键安装，无需额外配置。
Obsidian Semantic Search 是免费的吗？
是的，Obsidian Semantic Search 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Obsidian Semantic Search 支持哪些平台？
Obsidian Semantic Search 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Obsidian Semantic Search？
由 Maxime Roy (new.blacc)（@celstnblacc）开发并维护，当前版本 v1.0.1。
推荐 Skills