القائمة
Manages Architecture Decision Records (ADRs) when modifying architecturally significant files.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Scans the codebase for tech debt — balls of mud, shallow modules, and DRY violations — then presents prioritized bottlenecks and hands off to TDD-driven refactoring via superpowers.
Forces DDD ubiquitous language definition before writing complex logic. Grills the user on business terminology, extracts a glossary, and documents it before handing off to brainstorming.
Sets up a new project for the AI workflow — creates AGENTS.md, mise.toml tasks, initializes CodeGraph, and seeds Engram memory. Optional/auxiliary skill.
Evidence-first development for high-stakes code. Writes a concrete spec, enforces strict TDD, then runs code through a gauntlet of 6 checks and generates an EVIDENCE.md report with raw numbers.
Enforces Red-Green-Refactor Test Driven Development workflow.
Enforces build, test, and lint gates with a self-correction loop and retry budget.
| name | adr-manager |
| description | Manages Architecture Decision Records (ADRs) when modifying architecturally significant files. |
You are responsible for maintaining the architectural history of this project.
This skill is triggered whenever you modify files that are "architecturally significant." This includes, but is not limited to:
requirements.txt, package.json, pyproject.toml)docs/adr directory to understand existing decisions and determine the next ID (e.g., 0005).docs/adr/XXXX-title.md using the following template:# ADR [ID]: [Title]
**Status**: Proposed | Accepted | Superseded
**Date**: [YYYY-MM-DD]
## Context
What is the problem we are solving? What are the constraints?
## Decision
What is the proposed change? Why this path over others?
## Consequences
What are the trade-offs? What new technical debt or benefits are introduced?
adr_log tool to update the index file (docs/adr/README.md).Documenting decisions ensures that the reasoning behind complex changes is not lost as the AI or team evolves.