← 返回 Skills 市场
SAW Filter Expert
作者
lujie19941118-star
· GitHub ↗
· v1.0.0
· MIT-0
75
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install saw-filter-expert
功能描述
提供基于Hashimoto专著和经典文献的SAW滤波器设计、等效电路建模、横向模抑制、温度补偿及材料选型专业技术支持。
安全使用建议
This skill appears to be a legitimate SAW filter adviser, but it claims a local knowledge corpus at /workspace/knowledge_base/saw/docs/ that is not included in the package and is not declared in the metadata. Before installing or enabling it: 1) Ask the publisher where the referenced documents come from and whether they will be present on the agent's workspace; verify provenance and licensing (Hashimoto OCR and PDFs may be copyrighted). 2) Confirm what filesystem paths the skill will read and whether the agent will be allowed to access other workspace files — if you have sensitive files under /workspace, restrict access or run the skill in an isolated environment. 3) Prefer a version that either bundles the referenced documents (with clear rights) or removes hardcoded paths and instead asks the user to provide/upload specific files. 4) If you cannot verify point 1, treat the skill as untrusted and avoid granting it access to your workspace.
能力评估
Purpose & Capability
Name, description, and instructions are coherent for a SAW filter expert: formulas, models (BVD/MBVD), IDT design, TCF, COM theory and references all align with the declared purpose. However, the SKILL.md asserts a 'complete literature' stored at /workspace/knowledge_base/saw/docs/, but the skill bundle only contains SKILL.md and a references README; the claimed local corpus is not shipped with the skill.
Instruction Scope
The SKILL.md explicitly instructs the agent to use files under /workspace/knowledge_base/saw/docs/. That directs the agent to read workspace files at runtime. While those files are relevant to the skill's purpose, the platform metadata did not declare any required config paths and the referenced documents (Hashimoto OCR, PDFs, patents) are not included in the package — creating ambiguity about where the agent will read them from and whether it may access other workspace data.
Install Mechanism
This is an instruction-only skill with no install spec and no bundled executables or downloads, so it will not write new binaries to disk or pull code from external URLs during install.
Credentials
The skill declares no required env vars or config paths, yet its instructions expect access to a specific filesystem location containing many technical documents (including an OCR'd book and patents). That implicit requirement is not represented in the metadata and could lead the agent to read user workspace assets unexpectedly; there are also possible copyright/licensing considerations for the listed materials.
Persistence & Privilege
The skill is not marked always:true and does not request elevated or persistent presence. It does not include install-time behaviors that would alter other skills or system-wide settings.
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 saw-filter-expert - 安装完成后，直接呼叫该 Skill 的名称或使用
/saw-filter-expert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
v1.0.0
Initial publish: Hashimoto+9 papers, BVD/MBVD/COM/piston-mode/TCSAW/IHPSAW
元数据
常见问题
SAW Filter Expert 是什么？
提供基于Hashimoto专著和经典文献的SAW滤波器设计、等效电路建模、横向模抑制、温度补偿及材料选型专业技术支持。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 75 次。
如何安装 SAW Filter Expert？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install saw-filter-expert」即可一键安装，无需额外配置。
SAW Filter Expert 是免费的吗？
是的，SAW Filter Expert 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
SAW Filter Expert 支持哪些平台？
SAW Filter Expert 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 SAW Filter Expert？
由 lujie19941118-star（@lujie19941118-star）开发并维护，当前版本 v1.0.0。
推荐 Skills