_plan-evaluation

Evaluate plan artifacts for task specificity, dependency ordering, completeness, feasibility, and researchability.

Updated Mar 28, 2026

Search Tags:#planning #quality-assurance #task-decomposition #plan-evaluation #dependency-ordering #researchability

Ready to run

npx skills add https://github.com/HahyeonJeon/gobbi --skill plan-evaluation

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: _plan-evaluation
Source: https://github.com/HahyeonJeon/gobbi/tree/main/plugins/gobbi/skills/_plan-evaluation
Command: npx skills add https://github.com/HahyeonJeon/gobbi --skill plan-evaluation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Plans often lack explicit deliverables, proper dependencies, and measurable criteria. This Skill provides a structured, repeatable method to evaluate planning outputs against explicit criteria, preventing ambiguity and scope creep before execution.

Core Features & Use Cases

Task Specificity — ensures deliverables, scope boundaries, agent assignments, and self-contained tasks.
Dependency Ordering — enforces correct dependency sequencing, maximizes parallelism, and avoids circular dependencies.
Completeness — verifies full scope coverage, defined verification criteria, collection plan, and scope containment.
Feasibility — assesses task sizing, agent capabilities, wave size, and domain gotchas.
Researchability — checks for clear research questions, bounded scope, codebase pointers, and external research needs.

Quick Start

Provide a plan artifact and run the plan-evaluation workflow to obtain a structured evaluation.

Frequently Asked Questions about _plan-evaluation

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

FAQPage Schema

How do I evaluate project plan quality before delegating tasks to agents?▼

Plan evaluation identifies and quantifies quality by checking task specificity, dependency ordering, completeness, feasibility, and researchability. It applies deterministic checks against artifacts like idea documents, codebase structures, and task lists to prevent ambiguity before execution.

How do I check task dependencies for circular dependencies and correct sequencing?▼

Checking task dependencies involves enforcing correct dependency sequencing, maximizing parallelism, and avoiding circular dependencies. The evaluation verifies proper ordering against task lists to prevent execution bottlenecks.

What makes a task plan feasible for automated agents and researchers?▼

A task plan is feasible when task sizing, agent capabilities, wave size, and domain gotchas are assessed. Feasibility evaluation checks these factors to ensure tasks match agent skills and avoid domain-specific pitfalls.

Can I verify plan completeness and scope coverage using codebase artifacts?▼

You can verify plan completeness by checking full scope coverage, defined verification criteria, and scope containment. The evaluation uses tools like Read, Grep, Glob, and Bash to inspect codebase structures and task lists.

How do I assess researchability when planning tasks with bounded scope?▼

Assessing researchability involves checking for clear research questions, bounded scope, codebase pointers, and external research needs. This ensures research tasks have well-defined objectives and necessary context before delegation.

Why do my task plans suffer from scope creep and ambiguous deliverables?▼

Task plans suffer from scope creep and ambiguous deliverables when they lack explicit deliverables, proper dependencies, and measurable criteria. Plan evaluation applies a structured, repeatable method to prevent these issues before execution.