← 返回 Skills 市场
agenticio

proof

作者 agenticio · GitHub ↗ · v2.0.1 · MIT-0
cross-platform ✓ 安全检测通过
362
总下载
0
收藏
3
当前安装
3
版本数
在 OpenClaw 中安装
/install proof
功能描述
A local-first cryptographic toolkit. Executes zero-knowledge proof (ZKP) generation, circuit compilation via SnarkJS/ZoKrates, and formal verification analys...
安全使用建议
This skill appears coherent and local-only, but take these precautions before installing: (1) confirm you trust and/or inspect the bundled scripts (they currently have commented-out subprocess calls that would execute local CLIs if enabled); (2) ensure you have the required local toolchain (node/snarkjs/zokrates/python) installed from trusted sources; (3) be aware the skill will create and read/write files under ~/.openclaw/workspace/proof, so check file permissions and contents it generates; (4) if you plan to enable or modify the scripts to run external CLIs, review those commands to ensure they don't invoke unexpected network or privileged operations.
功能分析
Type: OpenClaw Skill Name: proof Version: 2.0.1 The 'proof' skill bundle is a local-first cryptographic toolkit for ZKP generation and formal verification. The provided Python scripts (verify_lib.py and zkp_tool.py) contain harmless logic and commented-out placeholders for standard industry tools like SnarkJS and Slither. The skill.json configuration explicitly restricts permissions, disabling network access and environment variable reading, which aligns with the stated privacy goals.
能力评估
Purpose & Capability
Name/description, declared required binaries (node, snarkjs, zokrates, python3), and the two small scripts (zkp_tool.py, verify_lib.py) are consistent with a local ZKP/formal-check toolkit. The presence of optional ZoKrates and SnarkJS aligns with the stated purpose.
Instruction Scope
SKILL.md instructs the agent to call the included scripts and operate in the declared workspace (~/.openclaw/workspace/proof). The scripts only read/write local files and create a workspace directory; there are no instructions to read unrelated system files, environment variables, or transmit data externally. Commented-out subprocess calls show where local CLIs (snarkjs, slither, zokrates) would be used—this is expected for the stated purpose.
Install Mechanism
No install spec is provided (instruction-only behavior), and the included Python scripts are small. The skill does not download or extract code from remote URLs. Required toolchains are declared but not installed by the skill, which is appropriate for a local-toolchain-dependent skill.
Credentials
The skill requires no environment variables or credentials and the skill.json permissions explicitly disable network and environment variable access. That matches the claim of local-only computation.
Persistence & Privilege
always is false and the skill does not request system-wide modifications or persistent daemons. Autonomous invocation is allowed by default but is not combined with elevated privileges or broad credential access.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install proof
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /proof 触发
  4. 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
v2.0.1
- Added skill.json file to the project. - No other changes to code or documentation.
v2.0.0
Proof 2.0.0 introduces a powerful local cryptographic engine and formal verification toolkit. - Added local execution of zero-knowledge proof (ZKP) generation and circuit compilation using SnarkJS/ZoKrates. - Introduced static analysis and formal verification checks for project code. - Implemented cryptographic manifest auditing of local files. - All computations run locally—no cloud or external API data transmission. - Added requirements for Node.js, SnarkJS, Python 3.10+, and (optionally) ZoKrates. - Workspace isolation for enhanced security and privacy.
v1.0.0
Initial truth protocol release
元数据
Slug proof
版本 2.0.1
许可证 MIT-0
累计安装 4
当前安装数 3
历史版本数 3
常见问题

proof 是什么?

A local-first cryptographic toolkit. Executes zero-knowledge proof (ZKP) generation, circuit compilation via SnarkJS/ZoKrates, and formal verification analys... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 362 次。

如何安装 proof?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install proof」即可一键安装,无需额外配置。

proof 是免费的吗?

是的,proof 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

proof 支持哪些平台?

proof 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 proof?

由 agenticio(@agenticio)开发并维护,当前版本 v2.0.1。

💬 留言讨论