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 where an agent may post PR reviews, comments, merges, edit CI config, or push to protected branches, and you need a cryptographically auditable human approval trail.
protect-mcp sign/approve-reviewnpx @veritasacta/verifyA tamper-evident receipt chain of all review actions with human approval gates enforced by Cedar, verifiable by auditors offline.
Use Cases
A fintech team lets a Claude Code agent triage GitHub issues and post PR reviews. To satisfy compliance, they install review-agent-setup: copy the Cedar policy, create sign keys, and use `/approve-review` before each merge. Every action writes a signed receipt. Auditors later run `npx @veritasacta/verify` to prove no unreviewed merge occurred, reducing regulatory risk.
An open-source maintainer uses an agent to comment on and merge contributor PRs. They set REVIEW_APPROVAL_FLAG to lock down CI, forcing all tool calls through Cedar. In normal dev they touch `.review-approved` to permit specific actions. The signed receipt chain lets the community verify that no bot action landed without human sign-off, building trust.
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