What kind of verification does it include in the output?

It filters out obvious criteria like 'tests pass' and focuses on non-obvious verification such as specific HTTP status codes, security constraints, and UI status checks.

How does it help with LLM context windows?

It utilizes glob patterns and terse language rules to compress descriptions and file lists, ensuring the AI receives maximum information while consuming minimal tokens.

Can it break down features into code-ready tasks?

Yes, it follows specific granularity and sequencing rules to turn high-level descriptions into actionable 5-30 minute development tasks that can be committed independently.

Which project management systems are supported?

This skill is system-agnostic and works with content pasted from Jira, GitHub Issues, Azure DevOps, Linear, or any other text-based project management tool.

Work Item Optimizer

Name: Work Item Optimizer
Author: dariuszparys

bydariuszparys

Productivity & Workflow

Streamlines project tickets and issues by optimizing structure, file paths, and task breakdowns for LLM-assisted development.

About

The Work Item Optimizer skill transforms verbose or poorly structured issues from systems like Jira, GitHub, and Azure DevOps into highly efficient, token-optimized formats tailored for AI-driven development. By applying specialized patterns such as glob-based file path compression, terse language rules, and logical task sequencing, it ensures that Claude has the precise context needed to implement features accurately. This skill acts as a bridge between project management and code implementation, enforcing quality standards for acceptance criteria and breaking down complex features into independent, committable tasks.

Key Features

Acceptance criteria filtering to remove redundant overhead
0 GitHub stars
Token-efficient output formatting for LLM context windows
Logical task breakdown and sequencing for development
Ticket completeness and readiness analysis
Automated file path compression using glob patterns

Use Cases

Breaking down a complex feature request into small, committable tasks with clear verification steps.
Converting a verbose Jira ticket into a concise technical implementation plan.
Auditing GitHub issues for missing context or vague acceptance criteria before starting work.

About

Key Features

Acceptance criteria filtering to remove redundant overhead
0 GitHub stars
Token-efficient output formatting for LLM context windows
Logical task breakdown and sequencing for development
Ticket completeness and readiness analysis
Automated file path compression using glob patterns

Use Cases

Breaking down a complex feature request into small, committable tasks with clear verification steps.
Converting a verbose Jira ticket into a concise technical implementation plan.
Auditing GitHub issues for missing context or vague acceptance criteria before starting work.