← 返回 Skills 市场
semfind
作者
PaperBoardOfficial
· GitHub ↗
· v0.1.2
574
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install semfind
功能描述
Semantic search over local text files using embeddings. Use when grep/ripgrep fails to find relevant results because the exact wording is unknown, or when se...
安全使用建议
This skill is coherent for local semantic search, but before installing: (1) review the semfind PyPI package and its source/repository to ensure it comes from a trusted maintainer; (2) install in a virtualenv or sandbox if you want isolation; (3) expect the tool to download a model from the internet on first run and to read/index any files you point it at (logs, notes, etc.), so avoid pointing it at sensitive system or credential files; (4) verify the model source (BAAI/...) if you require auditable provenance.
功能分析
Type: OpenClaw Skill
Name: semfind
Version: 0.1.2
The skill bundle describes a semantic search tool (`semfind`) and provides instructions for its installation and usage. The `_meta.json` contains standard metadata. The `SKILL.md` instructs the agent to install the tool via `pip install semfind` and provides usage examples involving local file access. There is no evidence of prompt injection attempts against the agent, data exfiltration, persistence mechanisms, or other malicious behaviors within the provided files. The `pip install` command, while a potential vector for supply chain attacks if the `semfind` package itself were malicious, is presented as a standard and necessary step for the tool's functionality and does not indicate malicious intent within this skill bundle.
能力评估
Purpose & Capability
Name/description match the instructions: semfind is described as a local semantic search tool and the SKILL.md tells the user to install and run a local CLI to embed and search files. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
Instructions explicitly require reading user-specified files and maintaining caches in /tmp and ~/.cache; they also describe downloading a ~65MB model on first run. These actions are expected for local embedding-based search but do mean the tool will read local files and access the network to fetch the model.
Install Mechanism
The registry contains no install spec; the SKILL.md instructs users to run `pip install semfind`. This is reasonable for an instruction-only skill, but pip packages are third-party code — installing them runs code from the package maintainer and pulls remote artifacts (model) over the network.
Credentials
No environment variables, credentials, or config paths are requested. The declared requirements are minimal and align with the stated local-search purpose.
Persistence & Privilege
always is false and the skill does not request persistent platform privileges or modifications to other skills. The behaviour described (local caches) is limited to the user's filesystem.
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 semfind - 安装完成后,直接呼叫该 Skill 的名称或使用
/semfind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
v0.1.2
- Initial release of semfind: semantic search tool for local text files using embeddings.
- Provides grep-like CLI for searching by meaning, not just exact text.
- Local, private: uses BAAI/bge-small-en-v1.5 model + FAISS, no API keys needed.
- Supports options for top results, context lines, similarity thresholds, reindexing, and cache control.
- Outputs results with similarity scores; ideal for logs, docs, code, and notes where grep fails to match wording.
- Includes resource usage notes and recommended grep fallback workflow.
元数据
常见问题
semfind 是什么?
Semantic search over local text files using embeddings. Use when grep/ripgrep fails to find relevant results because the exact wording is unknown, or when se... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 574 次。
如何安装 semfind?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install semfind」即可一键安装,无需额外配置。
semfind 是免费的吗?
是的,semfind 完全免费(开源免费),可自由下载、安装和使用。
semfind 支持哪些平台?
semfind 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 semfind?
由 PaperBoardOfficial(@paperboardofficial)开发并维护,当前版本 v0.1.2。
推荐 Skills