← 返回 Skills 市场
Verifier
作者
ProjectSnowWork
· GitHub ↗
· v1.0.0
· MIT-0
264
总下载
0
收藏
3
当前安装
1
版本数
在 OpenClaw 中安装
/install verifier
功能描述
Trust and evidence verification engine for claims, sources, screenshots, profiles, offers, and suspicious messages. Use whenever the user asks whether someth...
安全使用建议
This skill appears internally consistent and local-only. Before installing, confirm that: (1) you are comfortable with the case file being created at ~/.openclaw/workspace/memory/verifier/cases.json (it is not synced externally by the scripts), (2) your agent or you will perform text extraction from images/links (the scripts expect structured evidence and do not fetch or OCR content), and (3) python3 is available. Optionally inspect the included Python files yourself — they are short and use only the standard library — and consider backing up or reviewing the cases.json file if it will contain sensitive information.
功能分析
Type: OpenClaw Skill
Name: verifier
Version: 1.0.0
The 'verifier' skill is a local-only tool for tracking and scoring evidence for claims, sources, and messages. All data is stored in a local JSON file (~/.openclaw/workspace/memory/verifier/cases.json), and the scripts (e.g., add_case.py, score_case.py) use standard Python libraries for data management without any external network calls, obfuscation, or high-risk execution patterns.
能力评估
Purpose & Capability
Name, description, and included scripts all implement a local claim/evidence verification workflow (capture, update, score, list, show, close). No unrelated binaries, credentials, or services are requested.
Instruction Scope
SKILL.md explicitly requires the LLM/agent to extract text from screenshots and summarize external links before calling the scripts; the scripts themselves do not fetch remote content or inspect images. This separation is coherent but means the agent (or user) must supply extracted evidence — review how your agent will collect that evidence to avoid accidental exfiltration when performing extraction.
Install Mechanism
No install spec (instruction-only) and scripts are pure Python using only standard library. Nothing is downloaded or written outside the user's home-based workspace directory.
Credentials
No environment variables, credentials, or external APIs are required. The only runtime requirement is a local python3 binary, which is appropriate for these scripts.
Persistence & Privilege
Skill does not request 'always: true', does not modify other skills or system-wide settings, and stores data only under ~/.openclaw/workspace/memory/verifier/cases.json. That local storage is proportional to the feature.
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 verifier - 安装完成后，直接呼叫该 Skill 的名称或使用
/verifier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
[email protected]: Reduce belief mistakes before they become costly. Built as a local-first trust gateway with structured evidence capture, defensive verification scoring, confidence and risk outputs, missing-evidence guidance, and clear next-step recommendations.
元数据
常见问题
Verifier 是什么？
Trust and evidence verification engine for claims, sources, screenshots, profiles, offers, and suspicious messages. Use whenever the user asks whether someth... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 264 次。
如何安装 Verifier？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install verifier」即可一键安装，无需额外配置。
Verifier 是免费的吗？
是的，Verifier 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Verifier 支持哪些平台？
Verifier 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 Verifier？
由 ProjectSnowWork（@projectsnowwork）开发并维护，当前版本 v1.0.0。
推荐 Skills