skills.rest
HahyeonJeon
HahyeonJeonCOMMUNITY
Explore all skills by this author →
GitHub

_agent-evaluation-architecture

Identify structural problems in gobbi agent definitions across lifecycle stages.

Updated Mar 28, 2026
Search Tags:#architecture#agent#evaluation#lifecycle#design-review#gobbi
One-click install
npx skills add https://github.com/HahyeonJeon/gobbi --skill agent-evaluation-architecture
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: _agent-evaluation-architecture
Source: https://github.com/HahyeonJeon/gobbi/tree/main/plugins/gobbi/skills/_agent-evaluation-architecture
Command: npx skills add https://github.com/HahyeonJeon/gobbi --skill agent-evaluation-architecture

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Gobbi agent definitions are prone to structural issues that cause inconsistent behavior if not evaluated for architecture quality. This skill helps identify problems in lifecycle, boundaries, and opening statements before deployment.

Core Features & Use Cases

  • Lifecycle completeness: checks for Study, Plan, Execute, Verify phases and ensures domain-specific guidance.
  • Boundary and opening discipline: ensures clear scope, identity, and cognitive stance.
  • Findings format guidance: prescribes structured, prioritized findings for actionable improvements.

Quick Start

Provide an architecture review of a gobbi agent definition and surface structural issues.

Frequently Asked Questions about _agent-evaluation-architecture

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I evaluate agent architecture for structural problems before deployment?▼

To evaluate agent architecture, you must review agent definitions for explicit lifecycle sections, opening statements, scope boundaries, and defined abstraction levels to ensure well-formed structure and clear boundaries.

What lifecycle stages should an agent definition include for architecture review?▼

An agent definition architecture review checks for complete Study, Plan, Execute, and Verify lifecycle stages, ensuring each phase contains domain-specific guidance to prevent inconsistent agent behavior.

Why does my agent behave inconsistently across lifecycle stages?▼

Inconsistent agent behavior often stems from architecture flaws in agent definitions, specifically missing explicit lifecycle sections, unclear scope boundaries, or poorly defined cognitive stance in opening statements.

How do I check if my agent definition has clear scope and identity boundaries?▼

Checking agent boundary discipline involves verifying that the definition establishes clear scope, agent identity, and cognitive stance, preventing structural issues that cause inconsistent execution.

What format should agent architecture review findings follow?▼

Agent architecture review findings should follow a structured and prioritized format, highlighting actionable improvements for lifecycle completeness, boundary discipline, and opening statement quality.

Do I need explicit opening statements in my agent definition?▼

Explicit opening statements are functional requirements for agent definitions, establishing the necessary cognitive stance and identity discipline to prevent architectural flaws before the agent runs.

Related Skills

Explore More Software Engineering Skills→
HahyeonJeonHahyeonJeon

_agent-evaluation-aesthetics

Identify readability and style issues in gobbi agent definitions.

Community
Intermediate
thrawn01thrawn01
11

blueprint-review

Analyze Blueprint documents for gaps and inconsistencies against ADRs and glossary.

Community
Advanced
HahyeonJeonHahyeonJeon

_execution

Guide executors through study, plan, execute, verify, and final reporting stages.

Community
Intermediate
ruskibeatsruskibeats

zoom-out

Summarize software module interactions for high-level system architecture review.

Community
Intermediate