← 返回 Skills 市场
149
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install zqtest
功能描述
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
安全使用建议
This skill appears to be a local, file-backed ontology helper and is coherent with its description. Before installing, ensure you are comfortable with the agent writing to the workspace path (memory/ontology/graph.jsonl and schema.yaml). Confirm python3 is available in the environment. Do not store plaintext secrets in entity properties — follow the secret_ref convention and keep any secret stores (keychain, vault) separate. If you want extra assurance, inspect scripts/ontology.py in full and run it in an isolated workspace or container so the graph file and schema are confined to a directory you control.
功能分析
Type: OpenClaw Skill
Name: zqtest
Version: 1.0.0
The ontology skill provides a structured knowledge graph for agent memory, allowing for entity and relation management via a local JSONL file. The implementation in `scripts/ontology.py` includes proactive security measures such as a `resolve_safe_path` function to prevent path traversal and schema validation that explicitly forbids the storage of sensitive credentials (passwords, tokens) within the graph. No indicators of malicious intent, data exfiltration, or prompt injection were found.
能力评估
Purpose & Capability
Name/description (typed ontology for agent memory) match the provided artifacts: SKILL.md, schema references, and a Python script that implements create/query/relate/validate operations. The skill only needs local file storage and a Python runtime (implied) which is proportionate to the described functionality.
Instruction Scope
Runtime instructions operate on a local append-only graph file (memory/ontology/graph.jsonl) and schema files in the workspace. The SKILL.md and scripts only instruct reading/writing those workspace files and do not direct the agent to access unrelated system paths, external endpoints, or unspecified environment variables.
Install Mechanism
No install spec is provided (instruction-only plus included script). That minimizes installation risk — the only code is the included Python script which runs locally. No remote downloads or package installs are requested.
Credentials
The skill declares no required environment variables, credentials, or config paths. It documents a convention for referencing secrets via secret_ref rather than storing secrets directly; that convention is enforced in the schema/validation logic. There are no unexpected credential requests.
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform privileges. It writes only to files under the workspace (memory/ontology) and does not modify other skills or system-wide agent settings. Autonomous invocation is allowed by platform default but is not combined with other red flags.
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 zqtest - 安装完成后，直接呼叫该 Skill 的名称或使用
/zqtest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 release of the ontology skill: a typed knowledge graph for agent memory and composable skills.
- Supports entity creation, querying, linking, and validation with type constraints.
- Core types include Person, Project, Task, Event, Document, and more.
- Provides CLI workflows for managing entities, relations, and schema validation.
- Designed for cross-skill data sharing and planning as graph transformations.
- Enforces append-only storage to preserve historical data and schema evolution.
元数据
常见问题
zqtest 是什么？
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 149 次。
如何安装 zqtest？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install zqtest」即可一键安装，无需额外配置。
zqtest 是免费的吗？
是的，zqtest 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
zqtest 支持哪些平台？
zqtest 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 zqtest？
由 ywqsimmon（@ywqsimmon）开发并维护，当前版本 v1.0.0。
推荐 Skills