super-human

Name: super-human
Availability: InStock
Author: AbsolutelySkilled

Decompose work into a dependency graph and coordinate parallel execution with TDD verification.

207|31|Updated Mar 14, 2026

Search Tags:#planning #tdd #verification #ai-agent #dag #board #wave-execution

Ready to run

npx skills add https://github.com/AbsolutelySkilled/AbsolutelySkilled --skill super-human

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: super-human
Source: https://github.com/AbsolutelySkilled/AbsolutelySkilled/tree/main/skills/super-human
Command: npx skills add https://github.com/AbsolutelySkilled/AbsolutelySkilled --skill super-human

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AI agents often struggle with coordinating complex multi-step development tasks across multiple files and phases. Super-Human provides a structured, end-to-end lifecycle that decomposes work into a dependency graph, executes tasks in parallel waves, verifies via TDD, and maintains a persistent board for resume and audit.

Core Features & Use Cases

Dependency-first decomposition that clearly defines task dependencies and wave planning.
Wave-based parallel execution with cross-task verification and rollback points.
Persistent board at project root capturing intake, plan, execution, and verification.
Supports 7-phase lifecycle: Intake, Decompose, Discover, Plan, Execute, Verify, Converge.
Ideal for greenfield projects, major refactors, migrations, or multi-file feature work.

Quick Start

Activate Super-Human on a task and provide explicit guidance, then decompose the feature and approve the generated plan before execution.

Frequently Asked Questions about super-human

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

FAQPage Schema

How do I coordinate multi-file project planning and execution for an AI agent?▼

Multi-file project planning and execution for an AI agent is coordinated by decomposing work into a dependency graph. This allows parallel wave-based execution with TDD verification across complex features, refactors, and migrations.

What is wave-based execution in software development lifecycle automation?▼

Wave-based execution is a mechanism that runs decomposed tasks in parallel waves based on a dependency graph. It includes cross-task verification, rollback points, and conflict resolution to safely manage complex multi-file development.

How do I verify AI-generated code changes during multi-step refactoring?▼

AI-generated code changes during multi-step refactoring are verified using TDD verification. The lifecycle mandates tail tasks like Self Code Review, Requirements Validation, and Full Project Verification to ensure correctness.

Can I use dependency graph decomposition for greenfield project migrations?▼

Dependency graph decomposition works for greenfield projects, major refactors, and migrations. It supports a seven-phase lifecycle from intake through converge, maintaining a persistent board at the project root for resume and audit.

How do I resume a stalled AI agent task in a multi-file repository?▼

A stalled AI agent task is resumed using a persistent board maintained at the project root. This board captures intake, plan, execution, and verification states, allowing the lifecycle to recover and continue execution waves.

What are the limitations of using a seven-phase lifecycle for AI-assisted coding?▼

The seven-phase lifecycle requires explicit user guidance and plan approval before execution. It is designed for complex feature work, refactors, and migrations, and may be excessive for simple single-file modifications.