← ClaudeAtlas

architecture-intelligencelisted

Use whenever code work has structural consequences: project architecture, module boundaries, dependency direction, runtime topology, ownership, ADRs, fitness functions, or architecture refactoring.
Xopoko/plug-n-skills · ★ 3 · AI & Automation · score 76
Install: claude install-skill Xopoko/plug-n-skills
# Architecture Intelligence Bundled commands use `$PLUGIN_ROOT` for the plugin root. Set it once: use the host's plugin-root variable when defined (Claude Code: `PLUGIN_ROOT="$CLAUDE_PLUGIN_ROOT"`), otherwise the absolute path of this plugin's root directory. Use for architecture quality in code. Trigger from task context and code evidence: designing a new project or feature, choosing structure, changing boundaries, moving behavior between layers, introducing runtime/integration paths, protecting quality attributes, or reviewing code whose shape affects changeability, reliability, scalability, security, operability, or testability. ## Evidence First Before judging: 1. Define system boundary, users/workloads, and the delivery constraint. 2. Inspect source evidence: repo guidance, README, manifests, tests, ownership files, architecture docs, ADRs, dependency graph, runtime boundaries, and recent changes. 3. Name quality attributes under pressure: modifiability, reliability, scalability, performance, security, observability, testability, cost, operability. 4. Frame key scenarios: stimulus, environment, response, response measure. 5. Separate observed, inferred, assumed, and unknown. If context is thin, inspect source first or ask one decision-critical question. Do not invent scale, teams, boundaries, compliance, or domain facts. ## Probe From the plugin root: ```bash python3 "$PLUGIN_ROOT/scripts/architecture_probe.py" <repo-path> --json python3 "$PLUGIN_ROOT/scripts/ar