VE

verify-architecture

Validates project code against architecture rules, ADRs, and documentation to prevent structural debt.

Install

mkdir -p .claude/skills/verify-architecture && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16573" && unzip -o skill.zip -d .claude/skills/verify-architecture && rm skill.zip

Installs to .claude/skills/verify-architecture

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Run architecture compliance checks for BioETL (quick/full/category modes) before commit or PR.
94 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Execute architecture validation checks
  • Report blocking issues
  • Report non-blocking issues
  • Suggest actionable next fixes
  • Select validation mode based on request scope
  • Adapt commands to active shell and toolchain

How it works

The skill executes architecture validation checks by locating related architecture tests, ADRs, and documentation, then reports issues and suggests fixes.

Inputs & outputs

You give it
Structural edits, PR/merge request, or architecture debt closeout
You get back
Failing checks with actionable next fixes

When to use verify-architecture

  • Validating architecture before a PR merge
  • Checking for architecture debt in core services
  • Verifying structural consistency after refactoring

About this skill

Verify Architecture

Objective

Execute architecture validation checks and report blocking/non-blocking issues.

Source Of Truth

  • Root runtime contract: ../../../AGENTS.md
  • Project rules: ../../../docs/00-project/RULES.md
  • Requirements: ../../../docs/01-requirements/REQUIREMENTS.md
  • Accepted ADRs: ../../../docs/02-architecture/decisions
  • Normative index: ../../../docs/00-project/NORMATIVE_SOURCES.md
  • Canonical runtime entrypoint: this SKILL.md
  • Shared wrapper contract: ../py-audit-bot/references/wrapper-contract.md
  • Memory policy: ../../../docs/00-project/ai/agents/guides/MEMORY_USAGE.md

Trigger Scope

Use this wrapper when a task needs architecture verification after structural edits, before PR/merge, or for architecture debt closeout. It is a validation skill, not an audit replacement.

Workflow

  1. Follow the shared wrapper contract.
  2. Use memory plus repo search to locate related architecture tests, ADRs, docs, diagrams, and evidence reports before choosing validation scope.
  3. Select mode (quick, full, category) based on request scope.
  4. Adapt command examples to the active shell and installed toolchain.
  5. Report findings with failing tests/checks and actionable next fixes.

Expected Output

  • Selected mode and rationale.
  • Commands run and outcomes.
  • Failing checks with actionable next fixes.

Validation Modes

  • quick: focused architecture tests for touched surfaces.
  • category: named architecture family, for example config, docs drift, runtime mirrors, import boundaries, or inventory.
  • full: broad tests/architecture sweep when requested or needed by risk.

Fallback

If a full architecture run is too slow for the current environment, run the focused category checks and report the skipped full command exactly.

When not to use it

  • When the task is an audit replacement
  • When a full architecture run is too slow for the current environment and a focused category check is not sufficient

Limitations

  • This skill is a validation skill, not an audit replacement.

How it compares

This skill automates architecture compliance checks and provides actionable fixes, which is more efficient than manually reviewing architectural decisions and identifying discrepancies.

Compared to similar skills

verify-architecture side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
verify-architecture (this skill)01moNo flagsIntermediate
go-dev-guidelines149moNo flagsIntermediate
netalertx-code-standards12moReviewIntermediate
investigate16moReviewBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry