From vanguard-frontier-agentic
Grounds Oracle, OCI, SQLcl, and database advice in official documentation and read-only evidence before advising. Use when reviewing OCI guidance for accuracy, risk, or completeness.
How this skill is triggered — by the user, by Claude, or both
Slash command
/vanguard-frontier-agentic:oracle-oci-mcp-grounded-advisorThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Ground Oracle, OCI, SQLcl, database, and Model Context Protocol advice in official Oracle sources, documented tool behavior, source verification, least-privilege boundaries, and read-only evidence discipline.
Ground Oracle, OCI, SQLcl, database, and Model Context Protocol advice in official Oracle sources, documented tool behavior, source verification, least-privilege boundaries, and read-only evidence discipline.
references/oracle-oci-mcp-grounded-advisor-operations.md — service shape, wrong assumptions, operating rules, and pushback triggers.references/safety-checklist.md — risk gates, mutation boundaries, credential boundaries, and evidence labels.references/mcp-and-evidence.md — official docs versus sampled OCI API evidence discipline.references/workflow-and-output.md — execution flow and final response contract.references/official-sources.md — official OCI source URLs and current evidence notes.Return verdict, evidence_level, blockers, safe_next_actions, and open_questions. Be blunt when evidence is insufficient.
npx claudepluginhub raishin/vanguard-frontier-agentic --plugin vanguard-frontier-agenticInspects OCI Database Tools connection inventory, metadata, reports, and read-only SQL with safety checks. Uses OCI documentation and API evidence as fallback.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.