agentsclimarketplace

Oracle oci mcp grounded advisor

Skill Raishin/vanguard-frontier-agentic/skills/oci/oracle-oci-mcp-grounded-advisor

Curated marketplace of AI skills, agents, and rules for cloud, zero-trust, and compliance-aware engineering - works with Claude Code, Codex, Cursor, Copilot, and more.

Install
npx -y skills add Raishin/vanguard-frontier-agentic --skill oracle-oci-mcp-grounded-advisor

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 18 stars18 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Ground Oracle, OCI, SQLcl, database, and Model Context Protocol recommendations in official Oracle sources and read-only evidence before advising.

SKILL.md

2.3 KB, 389 tokens by cl100k_base, as published. Nobody here has run it

Oracle and OCI MCP Grounded Advisor

Purpose

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.

Use When

  • Reviewing this OCI domain for stale, missing, risky, vague, over-permissive, or under-specified guidance.
  • Comparing current official OCI documentation against existing operational assumptions.
  • Producing a source-grounded advisory that separates documented behavior, sampled configured-environment evidence, inference, and unknowns.

Operating Rules

  • Keep primary responses lean; put detailed service behavior and caveats in references.
  • Use official OCI documentation for documented service behavior.
  • Use OCI API evidence through the user’s configured read-only OCI MCP only for command shape or sanitized sampled current-state observations.
  • Do not mention local connector names, internal tool names, profile names, account-specific identifiers, or environment-specific paths.
  • Never ask for credentials, tokens, tenancy details, compartment or resource identifiers, customer data, private keys, wallets, or config contents.
  • Require explicit approval before any mutation or external support-channel action.

Reference Pack

  • 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.

Response Contract

Return verdict, evidence_level, blockers, safe_next_actions, and open_questions. Be blunt when evidence is insufficient.

Gives 0 of the 12 instructions most mcp tooling skills give in 389 tokens

Counted across 638 of the 750 authors here whose files we hold, read 2026-08-07

  • create ten complex read-only evaluation questionsin 69 of 638, across 15 files
  • test servers using MCP Inspectorin 61 of 638, across 19 files
  • provide actionable error messagesin 54 of 638, across 12 files
  • prioritize comprehensive API coverage over specific workflowsin 54 of 638, across 12 files
  • use TypeScript and Streamable HTTP for remote serversin 54 of 638, across 8 files
  • define structured output schemas where possiblein 50 of 638, across 8 files
  • use Zod or Pydantic for input schemasin 47 of 638, across 5 files
  • fetch MCP specification pages with markdown suffixin 46 of 638, across 4 files
  • load framework documentation using WebFetchin 45 of 638, across 3 files
  • verify each evaluation answer independentlyin 45 of 638, across 3 files
  • implement API client with authentication and paginationin 45 of 638, across 3 files
  • Define input schemas with validationin 27 of 638, across 9 files

Said here and by no other author read

  • keep primary responses lean
  • use official OCI documentation for behavior
  • use OCI API evidence through read-only MCP
  • omit local connector and internal names
  • require explicit approval before mutations
  • return verdict evidence_level blockers safe_next_actions open_questions

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.