Domains
Forms
Mechanism
Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.
When setting up a Claude Code project that requires cryptographic audit trails, policy-gated tool execution, or compliance-ready evidence of agent actions (e.g., finance, healthcare, regulated research).
.claude/settings.json calling npx protect-mcp./receipts/npx @veritasacta/verify verifies single or chained receipts offlineTamper-evident, offline-verifiable receipts for every tool call plus enforced Cedar policies — third-party-provable compliance evidence with no server or operator trust.
Use Cases
A fintech startup uses Claude Code to automate payment reconciliation. To satisfy auditors, they install protect-mcp and define Cedar policies that forbid destructive Bash commands. Every tool call now produces a signed receipt in ./receipts/. During SOC 2 review, auditors run `npx @veritasacta/verify receipts/*.json` offline and confirm no tampering. The skill turns opaque agent logs into provable compliance evidence without trusting the operator.
A healthcare AI lab runs Claude Code for patient-data report generation. They configure protect-mcp hooks so only read-only tools and approved commands execute; writes outside the project are forbidden by Cedar. Each PostToolUse signs a receipt hash-chained to the prior one. Later, a regulator verifies the chain offline, proving the agent never exfiltrated data. The skill provides policy-gated execution and cryptographic proof of compliant behavior.
Skill Relationships
Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.
Tier 1 · These Skills Use Me
Tier 2 · Current Skill
Tier 3 · I Use These Skills
Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.
Skill File