roosch269 skills on Claude Market
2 skills published by roosch269. Each listing includes a one-command install for Claude Code, OpenClaw, Codex, and Hermes, plus a link to the upstream source.
agent-audit-trail
Hash-chained audit logging for AI agents using SHA-256 to create tamper-evident records. Covers EU AI Act Articles 12, 14, and 50 on record-keeping, human oversight, and transparency. Runs as a standalone Python script with no external dependencies.
agent-self-assessment
Runs a 10-check security and compliance self-assessment on an AI agent's own configuration. Covers decision boundaries, credential scoping, audit trails, plane separation, and EU AI Act readiness across Articles 6, 14, and 50. Produces a structured RED/AMBER/GREEN rated report across three domains: security, EU AI Act readiness, and data governance.