skills.rest
Lizhiyu-foshan
Lizhiyu-foshanCOMMUNITY
Explore all skills by this author →
GitHub

superpowers

Automate structured task execution and two-stage code review in development pipelines.

Updated Mar 16, 2026
Search Tags:#tdd#debugging#code-review#prompt-templates#pipeline-orchestration#ast-analysis#hashline-edit
One-click install
npx skills add https://github.com/Lizhiyu-foshan/Multi-Agent-Pipeline --skill superpowers-lizhiyu-foshan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: superpowers
Source: https://github.com/Lizhiyu-foshan/Multi-Agent-Pipeline/tree/main/.skills/superpowers
Command: npx skills add https://github.com/Lizhiyu-foshan/Multi-Agent-Pipeline --skill superpowers-lizhiyu-foshan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Superpowers provides a disciplined engineering execution layer that enforces TDD, structured task execution, two-stage reviews, and deterministic, hash-verified file edits to reduce buggy, unreviewed changes and overbuilt implementations.

Core Features & Use Cases

  • Structured Task Execution: Generate implementer prompts, dispatch implementers, and collect implementer reports for deterministic task completion.
  • Two-Stage Review: Separate spec compliance checks from AST-based code quality reviews using the CodeAnalyzer to ensure both correctness and quality.
  • TDD & Debugging Enforcement: Enforce RED-GREEN-REFACTOR cycles and a four-phase systematic debugging workflow to find root causes before fixes.
  • Hashline-Verified Edits: Apply content-hash-verified edits (read, replace, insert, delete, preview, restore) to avoid accidental file corruption and support reproducible, verifiable changes.
  • Use Case: Run an implementer to implement a feature, validate it against the spec via spec_review, perform an AST-driven code_quality_review, and apply safe edits with hashline_edit.

Quick Start

Invoke the superpowers skill to execute a task, run two-stage reviews, or perform hashline edits on project files.

Frequently Asked Questions about superpowers

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

FAQPage Schema
How do I enforce TDD cycles in a multi-agent development pipeline?▼

To enforce TDD in a development pipeline, use a structured execution layer that automates RED-GREEN-REFACTOR cycles and dispatches implementer tasks, ensuring tests are written and passed before code changes are applied.

What is AST-based code review and how does it improve code quality?▼

AST-based code review is an automated analysis process that examines abstract syntax trees to audit code quality. It separates spec compliance checks from structural quality reviews, ensuring deterministic validation of correctness and code standards.

How do I apply safe, deterministic edits to files during automated testing?▼

To apply safe file edits during automated testing, use content-hash-verified edit operations like read, replace, insert, and delete. This hashline verification prevents accidental file corruption and supports reproducible changes.

What's the best way to automate a two-stage code review for build and deployment workflows?▼

The best way to automate two-stage code reviews is by orchestrating a workflow that first checks spec compliance via implementer reports, then performs an AST-driven code quality audit to produce reviewable artifacts.

Can I use multi-agent orchestration to run systematic debugging workflows?▼

Yes, multi-agent orchestration can run systematic debugging workflows by enforcing a four-phase debugging cycle to find root causes before fixes, integrating seamlessly with structured task execution and AST analysis.

Why does my automated pipeline produce overbuilt or unreviewed code changes?▼

Automated pipelines produce overbuilt or unreviewed changes when lacking a disciplined engineering execution layer. Enforcing structured task execution, two-stage reviews, and TDD reduces buggy implementations and ensures deterministic, hash-verified file edits.

Related Skills

Explore More Software Engineering Skills→
trotsky1997trotsky1997
6

cursor-agent-development

Orchestrate interactive development sessions with the cursor-agent CLI.

Community
Intermediate
dislerdisler
379

Agent Sandboxes

Execute isolated code and tasks inside E2B sandboxes.

Community
Advanced
HuynhHoangPhucHuynhHoangPhuc

sl:hashline-edit

Edit files by hashline references with hash-mismatch checks.

Community
Intermediate
VoDaiLoczVoDaiLocz
24

lint-and-validate

Automate linting and static analysis of code in CI pipelines.

Community
Intermediate