unit-executor
CommunityExecute one unit, update status.
AuthorWILLOSCAR
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill ensures that complex research workflows are executed step-by-step, allowing for auditing, interruption, and precise control over each individual task.
Core Features & Use Cases
- Atomic Execution: Guarantees that only one unit is processed at a time, preventing unintended parallel execution.
- Dependency Management: Automatically identifies and executes the next runnable unit based on defined dependencies.
- Status Tracking: Updates the status of units in
UNITS.csv(TODO, DOING, DONE, BLOCKED) and optionallySTATUS.md. - Use Case: When running a multi-stage research pipeline, this skill ensures that each stage completes successfully and its status is accurately recorded before the next stage is considered, allowing you to pause and resume the pipeline at any point.
Quick Start
Run the next available unit in the current workspace.
Dependency Matrix
Required Modules
None requiredComponents
scripts
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: unit-executor Download link: https://github.com/WILLOSCAR/research-units-pipeline-skills/archive/main.zip#unit-executor Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.