How does the Unit Planner prevent 'hollow' progress?

It employs an evidence-first methodology, meaning tasks are only marked as DONE when they satisfy the structured acceptance criteria and produce the intermediate artifacts defined in the execution contract.

What is a 'unit' in the context of this skill?

A unit is a specific, atomic task defined within a UNITS.csv file. Each unit includes a unique ID, required skills, inputs, outputs, and specific acceptance criteria for the AI to follow.

Does this skill require network access?

No, the Unit Planner operates locally on your workspace files, processing your pipeline markdown files and CSV templates without external network calls.

Can I use this with existing projects?

Yes, the Unit Planner can either instantiate a new UNITS.csv from a template or update an existing one to reflect changes in scope, corrected dependencies, or new checkpoints.

Unit Planner

Name: Unit Planner
Author: WILLOSCAR

byWILLOSCAR

•

227

•

生产力与工作流

Orchestrates research and development workflows by converting abstract pipelines into concrete, executable task units.

The Unit Planner skill bridges the gap between high-level project design and granular execution by generating and maintaining a workspace-specific UNITS.csv contract. Following an evidence-first methodology, it ensures that every task in a research or coding pipeline is defined with explicit inputs, outputs, and acceptance criteria. This prevents hollow progress by requiring verifiable checkpoints before units are marked as complete, making it ideal for managing complex, dependency-heavy AI research projects and structured software development workflows.

主要功能

01Synchronization between task units and project checkpoints

02227 GitHub stars

03Dynamic scope expansion for evolving project requirements

04Evidence-first dependency tracking and task validation

05Structural CSV validation to ensure tool and script compatibility

06Automated UNITS.csv generation from pipeline templates

使用场景

01Updating project scope and adding task dependencies during active development

02Initializing a structured research project from a predefined execution pipeline

03Standardizing acceptance criteria across complex, multi-agent workflows

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add willoscar/research-units-pipeline-skills unit-planner

For use in Claude.ai and ChatGPT

主要功能

01Synchronization between task units and project checkpoints

02227 GitHub stars

03Dynamic scope expansion for evolving project requirements

04Evidence-first dependency tracking and task validation

05Structural CSV validation to ensure tool and script compatibility

06Automated UNITS.csv generation from pipeline templates

使用场景

01Updating project scope and adding task dependencies during active development

02Initializing a structured research project from a predefined execution pipeline

03Standardizing acceptance criteria across complex, multi-agent workflows

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add willoscar/research-units-pipeline-skills unit-planner

For use in Claude.ai and ChatGPT