
ln-646-project-structure-auditor
Audits physical architecture structure: modules, domains, layer layout, junk drawers, and framework placement. Use for structure drift.
- Installs
- 376
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-646-project-structure-auditor- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads ln-646-project-structure-auditor automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Paths: File paths (
references/,../ln-*) are relative to this skill directory.
Project Structure Auditor
Type: L3 Worker
L3 Worker that audits whether physical project structure reflects the intended architecture.
Purpose & Scope
- Audit modules, domains, layer layout, framework placement, and junk drawer directories
- Detect structure drift that makes the architecture hard to navigate or enforce
- Complement code-level boundary checks with physical structure evidence
- Emit
MOVE_MODULE,SPLIT_JUNK_DRAWER, orALIGN_DOMAIN_STRUCTURE - Calculate compliance score (X/10)
Out of Scope:
.gitignore,.dockerignore, temp files, build artifacts, platform remnants, and large binaries- Import-level layer violations
- Package security, env-file hygiene, or runtime lifecycle checks
- Moving/deleting files
Inputs
MANDATORY READ: Load references/audit_worker_core_contract.md and references/mcp_tool_preferences.md.
Tool policy: You may run as an isolated subagent where host AGENTS.md is not in scope, so default to hex-line MCP first for file reads, search, and edits. Load references/mcp_integration_patterns.md only when MCP behavior is unclear.
Receives contextStore with: tech_stack, architecture, codebase_root, output_dir, domain_mode, scan_path.
Use hex-graph first when architecture summaries materially improve structure findings. Use hex-line first for local code, config, and manifest reads when available. If MCP is unavailable, unsupported, or not indexed, continue with built-in Read/Grep/Glob/Bash and state the fallback in the report.
Workflow
Detection policy: use two-layer detection (candidate scan, then context verification); load references/two_layer_detection.md only when the verification method is ambiguous.
- Parse context -- determine scan_root from domain-aware scope or codebase root
- Detect tech stack and intended structure
- MANDATORY READ: Load
references/stack_detection.md - Prefer explicit architecture docs/config when present; otherwise infer from source layout
- MANDATORY READ: Load
- Run structure checks (Layer 1)
- Framework expected source locations
- Domain/module grouping
- Layer directory layout
- Junk drawer directories
- Naming and placement consistency
- Verify context (Layer 2)
- Small projects may not need full domain/layer decomposition
- Framework conventions apply only to detected frameworks
- Mixed layouts are acceptable when split by app/package/test type and documented
- Collect findings with severity, location, action, effort, and recommendation
- Calculate score using
references/audit_scoring.md - Write report to
{output_dir}/ln-646--{identifier}.md - Return summary per
references/audit_summary_contract.md
Audit Rules
1. Framework Placement
What: Source files are placed outside framework or stack conventions
Detection: Load references/structure_rules.md and apply only rules for the detected stack.
Severity: HIGH when placement breaks tooling/routing, MEDIUM for maintainability drift
Action: MOVE_MODULE
2. Domain and Layer Layout
What: Domain or layer directories do not reflect the intended architecture
Detection:
- Compare documented or inferred domains/layers with physical directories
- Find domains missing expected substructure
- Find source files in root or generic folders when the project has a clear modular layout
Severity: MEDIUM by default, HIGH when structure hides critical ownership
Action: ALIGN_DOMAIN_STRUCTURE
3. Junk Drawers
What: Generic directories accumulate unrelated modules
Detection: Check directories such as utils, helpers, common, shared, services, and lib for mixed unrelated responsibilities above project thresholds.
Severity: MEDIUM for broad mixed responsibilities, LOW for small localized drift
Action: SPLIT_JUNK_DRAWER
Scoring Algorithm
MANDATORY READ: Load references/audit_scoring.md.
Output Format
MANDATORY READ: Load references/templates/audit_worker_report_template.md.
Write JSON summary per references/audit_summary_contract.md. In managed mode the caller passes both runId and summaryArtifactPath; in standalone mode the worker generates its own run-scoped artifact path per shared contract.
Write report to {output_dir}/ln-646--{identifier}.md with category: "Project Structure" and checks: framework_placement, domain_layer_layout, junk_drawers.
When summaryArtifactPath is absent, write the standalone runtime summary under .hex-skills/runtime-artifacts/runs/{run_id}/evaluation-worker/{worker}--{identifier}.json and optionally echo the same summary in structured output.
Critical Rules
Apply the already-loaded references/audit_worker_core_contract.md.
- Do not auto-fix: Report only, never move or delete files
- Unique angle: Audit physical architecture structure only. Do not audit file hygiene, ignore files, package health, env hygiene, import-level boundaries, or runtime lifecycle.
- Auto-detect, never assume: Apply framework rules only for detected stack
- Evidence always: Include file paths for every finding
- Action required: Every finding uses
MOVE_MODULE,SPLIT_JUNK_DRAWER, orALIGN_DOMAIN_STRUCTURE.
Definition of Done
Apply the already-loaded references/audit_worker_core_contract.md.
- contextStore parsed successfully
- scan_root determined
- Tech stack and intended structure detected
- Framework placement checked
- Domain/layer layout checked
- Junk drawer directories checked
- Layer 2 context verification applied
- Findings collected with severity, location, action, effort, recommendation
- Score calculated per
references/audit_scoring.md - Report written to
{output_dir}/ln-646--{identifier}.md(atomic single Write call) - Summary written per contract
Version: 1.0.0 Last Updated: 2026-03-15
FAQ
What does the ln-646-project-structure-auditor skill do?
Audits physical architecture structure: modules, domains, layer layout, junk drawers, and framework placement. Use for structure drift.
How do I install ln-646-project-structure-auditor?
Run npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-646-project-structure-auditor in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/ln-646-project-structure-auditor/ (personal) or .claude/skills/ln-646-project-structure-auditor/ (project).
Which AI agents can use ln-646-project-structure-auditor?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is ln-646-project-structure-auditor safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains ln-646-project-structure-auditor?
It is published by levnikolaevich in levnikolaevich/claude-code-skills. It has 376 recorded installs.
More from levnikolaevich/claude-code-skills
ln-100-documents-pipeline
levnikolaevich/claude-code-skills
Creates complete project documentation system (project docs, reference, tasks, tests). Use when bootstrapping docs from scratch or regenerating all.
ln-620-codebase-auditor
levnikolaevich/claude-code-skills
Use when auditing the codebase through the evaluation platform with mandatory research, coordinated domain audit workers, and structured summaries.
ln-775-api-docs-generator
levnikolaevich/claude-code-skills
Configures Swagger/OpenAPI documentation for backend APIs. Use when adding interactive API docs to a project.
ln-624-code-quality-auditor
levnikolaevich/claude-code-skills
Checks cyclomatic complexity, nesting, long methods, god classes, O(n2), N+1 queries, constants management. Use when auditing code quality.
ln-782-test-runner
levnikolaevich/claude-code-skills
Executes all test suites and reports results with coverage. Use when verifying that test infrastructure works after bootstrap.
ln-634-test-coverage-auditor
levnikolaevich/claude-code-skills
Identifies missing tests for unique critical local logic: money, auth, permissions, data integrity, algorithms, and domain rules. Use when auditing critical logic coverage gaps.
Popular frontend & design skills
setup-matt-pocock-skills
mattpocock/skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
frontend-design
anthropics/skills
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
hyperframes-animation
heygen-com/hyperframes
All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). Also covers auditing an existing composition's choreography (animation map) and 24 named text-animation effects. HyperFrames-native: single paused timeline, seek-safe, deterministic.
prototype
mattpocock/skills
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
hyperframes-core
heygen-com/hyperframes
The HyperFrames composition contract — build one renderable project. Use for composition structure, the data- timing attributes, class="clip", tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Read before writing composition HTML.
vercel-react-best-practices
vercel-labs/agent-skills
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.