Menu
Portable, scalable methodology for building AI agent systems using the AGENT Blueprint framework — validated at enterprise and personal scale
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Build and validate OCI draw.io architecture diagrams with embedded icon stencils (icon-native mode) to prevent mxgraph.oci fallback rendering issues like red placeholder blocks. Use for any OCI diagram creation or refactor in draw.io.
Enforce confidentiality protocol across all Oracle AI Architect deliverables. Pre-delivery audit, codename enforcement, and content sanitization. This skill has VETO power — if it fails, delivery is blocked.
Generate structured Solution Design Documents (SDD) for OCI-based customer solutions. Converts architecture decisions into a formal deliverable document with all required sections.
Orchestrate a full 5-phase OCI solution design — from discovery to customer-ready deliverables. Combines research, architecture, visuals, prototype, and confidentiality audit into a structured workflow.
Expert guidance for OCI Dedicated AI Clusters — private LLM hosting, fine-tuning, sizing, and cost optimisation for enterprise deployments
Model Context Protocol (MCP) integration patterns for Oracle Cloud — Oracle Database MCP, OCI resource management, and enterprise agent architecture
| name | frank-method |
| description | Portable, scalable methodology for building AI agent systems using the AGENT Blueprint framework — validated at enterprise and personal scale |
| version | 1.0.0 |
| platform | ["claude-code","cline","cursor","roocode"] |
| activation | {"cline":"@skills/frank-method/SKILL.md","cursor":"@skills/frank-method/SKILL.md"} |
You are an expert in "The Frank Method" — a portable, scalable methodology for building AI agent systems that works at both enterprise and personal scale.
## Primary Function
[One-sentence mission]
## Core Competencies
[3-5 capability areas]
## Communication Style
[Voice and tone]
## Typical Outputs
[Deliverables]
| Level | Scope | Risk |
|---|---|---|
| Full Authority | Domain expertise | Low, reversible |
| Collaborative | Cross-domain | Medium |
| Advisory Only | Outside domain | High, irreversible |
Single-purpose, composable tools with clear inputs/outputs.
| Category | Metrics |
|---|---|
| Efficiency | Time saved, error reduction, velocity |
| Quality | Accuracy, satisfaction, revisions |
| Business | Revenue, cost savings, goal advancement |
| Agent | Efficiency Gain |
|---|---|
| Finance | 60% |
| HR | 50% |
| Customer Support | 70% |
| Marketing | 85% |
| Sales | 55% |
| Operations | 65% |
| Legal | 45% |
| IT | 70% |
| Executive | 40% |
| Enterprise Agent | Personal Version |
|---|---|
| Finance Agent | Personal Finance Tracker |
| Marketing Agent | Personal Brand Manager |
| Operations Agent | Productivity System |
| Strategy Agent | Goal & Planning Assistant |
To use this skill in Cline, reference it at the start of your message:
@skills/frank-method/SKILL.md
Apply the AGENT Blueprint to design a multi-agent sales enablement system for an enterprise.
Or in a .clinerules workflow:
## Agent Design
When designing AI agent systems, load @skills/frank-method/SKILL.md and apply the AGENT Blueprint (Architecture, Governance, Execution, Network, Transformation).
Triggers: AGENT Blueprint, agent design methodology, enterprise agent patterns, multi-agent orchestration planning