Architecture Docs (Grade A)Security-tested development skill for Claude AI. Grade A. Workflow for creating and maintaining architecture documentation. Use when the user needs to document system architecture or make ADRs.

Why You Should Use This?

Audience | Key Benefits --- | --- Individual | 30%+ token savings, stop repeating standards, security guardrails, instant scaffolding Teams | Consistent AI behavior, day‑one onboarding, codified patterns, compounding cost savings Organizations | Always‑on compliance, same standards across 1,000 projects, central governance, measurable ROI

Asked by Renata Silva · Jan 26, 2026

What You Can Customize?

Section | What It Controls | Example --- | --- | --- project | Project identity | Name, description, repo URL techStack | Language, framework, tools | TypeScript + Express or Python + FastAPI paths | Directory structure | Where handlers, services, and common code live domain | Business entities | Order, Product, Customer + lifecycle states patterns | Code patterns | 7‑step handler flow, error handling strategy testing | Quality gates | 90% coverage, test/lint/type‑check commands database | DB conventions | Soft delete field, timestamp columns, naming packages | Internal packages | @your‑org scope, registry URL conventions | Git and workflow | Branch prefixes, commit format, PR templates

Asked by Otto Berg · Jan 25, 2026

What's Inside?

Layer | Count | What It Does | How It's Triggered --- | --- | --- | --- Rules | 47 | Enforces coding standards on every AI interaction | Automatically — always on Agents | 62 | Specialized assistants for complex tasks | On demand — /agent-name Skills | 50 | Step‑by‑step guided workflows with checklists | Contextually — when patterns match Commands | 37 | Lightweight, token‑efficient quick actions | On demand — /command Hooks | 12 | Automation scripts in the AI loop | Event‑driven — before/after actions Templates | 9 | Scaffolding for handlers, components, tests, etc. | Referenced by skills and agents

Asked by Salome Beridze · Jan 1, 2026

What it detects?

Category | Signals --- | --- Language | tsconfig.json, go.mod, Cargo.toml, requirements.txt, pom.xml, file extensions Framework | Dependencies in package.json / requirements.txt (React, Express, Django, Spring, etc.) Database | ORM configs (prisma/, sequelize, typeorm), .sql files, migration folders Testing | jest.config., vitest, pytest, cypress/, playwright.config. Infrastructure | Dockerfile, terraform/, cdk.json, serverless.yml, cloud SDK deps CI/CD | .github/workflows/, .gitlab-ci.yml, Jenkinsfile

Asked by Rina Desai · Jan 5, 2026

How It Works?

Layer 1 — Pre-Processing: Hooks inject project context and block dangerous commands before your prompt reaches the AI. Layer 2 — Rules Engine: 47 always‑on rules enforce token efficiency, security, architecture, code standards, database conventions, and testing thresholds. Layer 3 — Specialized Processing: The right component activates — an agent, skill, or command — based on your prompt. Layer 4 — Post-Processing: Hooks validate output, auto‑format, scan for secrets, and verify coverage.

Asked by Yosef Mizrahi · Dec 20, 2025