proof

A local-first cryptographic toolkit. Executes zero-knowledge proof (ZKP) generation, circuit compilation via SnarkJS/ZoKrates, and formal verification analysis on local files. Requires local toolchains. No external API or cloud data transmission.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "proof" with this command: npx skills add agenticio/proof

PROOF 2.0: The Execution Layer

I. System Capability

Proof is now a functional engine for local cryptographic operations. It interfaces with your local environment to provide mathematical certainty.

Key Operations:

  • proof.zkp_gen: Compiles circuits and generates proofs locally.
  • proof.formal_check: Runs static analysis and formal verification templates on code.
  • proof.audit: Generates a cryptographic manifest for local project files.

II. Local Environment Requirements

  • Node.js & SnarkJS (ZKP)
  • ZoKrates (optional)
  • Python 3.10+ (glue scripts)

III. Usage & Examples

User: "Generate a ZKP for this statement: x * y = 12."
Agent: (Calls scripts/zkp_tool.py) -> "Compiling circuit... generating witness... proof.json created in `~/.openclaw/workspace/proof/`."

User: "Run a formal check on my Solidity contract."
Agent: (Calls scripts/verify_lib.py) -> "Scanning for reentrancy and integer overflow... Result: PASS."

IV. Security & Privacy

  • Local-only computation
  • Workspace isolation (`~/.openclaw/workspace/proof/`)
  • No persistent daemons or background processes
  • No credentials requested or transmitted

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Open Registry RecordOpen in ClawHub

Related Skills

Related by shared tags or category signals.

Security

Agentshield Audit

Trust Infrastructure for AI Agents - Like SSL/TLS for agent-to-agent communication. 77 security tests, cryptographic certificates, and Trust Handshake Protoc...

Registry SourceRecently Updated
6630Profile unavailable
Security

CAN: Clock Address Naming

Agent & MCP integration. CAN stamps what flows through any pipe. Verify, name, log locally.

Registry SourceRecently Updated
1.4K0Profile unavailable
Security

CrawSecure

Offline security scanner that detects unsafe code patterns in ClawHub skills before installation to help users assess potential risks locally.

Registry SourceRecently Updated
1.6K1Profile unavailable
Security

Praesidia

Verify AI agents, check trust scores (0-100), fetch A2A agent cards, discover marketplace agents, apply guardrails for security and compliance. Use when user mentions agent verification, trust scores, agent discovery, A2A protocol, agent identity, agent marketplace, guardrails, security policies, content moderation, or asks "is this agent safe?" or "find agents that can [task]" or "apply guardrails to protect my agent".

Registry SourceRecently Updated
1.7K3Profile unavailable