Agent skill

Architecture Mapper

by EmeaAppGbb in EmeaAppGbb/spec2cloud

Map application architecture — components, layers, data flow, and integration points.

MITAuto-check passedDevelopment

Install Architecture Mapper

skills CLI
$ npx skills add EmeaAppGbb/spec2cloud --skill architecture-mapper -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install EmeaAppGbb/spec2cloud architecture-mapper --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/EmeaAppGbb/spec2cloud.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/architecture-mapper .claude/skills/architecture-mapper && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
architecture-mapper
GitHub stars
100
Token cost
~2.4k tokens
SKILL.md length
870 words
Files
1
Skills in repo
38
Repo updated
First seen
Licence
MIT

At a glance

Map application architecture — components, layers, data flow, and integration points.

  • Works in 6 steps: Identify Application Boundaries → Map Internal Layers and Modules → Trace Data Flow → …
  • You need to understand and document an existing systems structure before any migration
  • SKILL.md covers Role, Inputs, Process and Output Format, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Architecture Mapper is an agent skill from EmeaAppGbb/spec2cloud. Map application architecture — components, layers, data flow, and integration points. Produce Mermaid diagrams. Pure extraction — document the as-is architecture without assessment, judgment, or improvement suggestions. Use when you need to understand and document an existing system's structure before any migration or modernization planning.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Legacy modernization. The licence is MIT.

When your agent uses it

  • You need to understand and document an existing systems structure before any migration
  • Modernization planning

Example prompts

  • “/architecture-mapper”

Requirements

  • Node.js

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Identify Application Boundaries
  2. Map Internal Layers and Modules
  3. Trace Data Flow
  4. Identify Integration Points
  5. Detect Architectural Patterns
  6. Generate Mermaid Diagrams

What it can do on your machine

Read from SKILL.md and the folder at commit 8e76618. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are mermaid and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Architecture Mapper loads about 2.4k tokens when it runs. Until then it costs about 91 tokens; SKILL.md has 870 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~91
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from EmeaAppGbb/spec2cloud at commit 8e76618, republished under its MIT licence (© EmeaAppGbb). 870 words, ~2,366 tokens.

Download SKILL.mdSave it as .claude/skills/architecture-mapper/SKILL.md (or your agent's skills folder).
name
architecture-mapper
description
Map application architecture — components, layers, data flow, and integration points. Produce Mermaid diagrams. Pure extraction — document the as-is architecture without assessment, judgment, or improvement suggestions. Use when you need to understand and document an existing system's structure before any migration or modernization planning.

Architecture Mapper

Role

You are the Architecture Mapper — a documentation agent that reads code and produces accurate diagrams and descriptions of the system as it exists today. You trace imports, analyze module boundaries, identify integration points, and map data flow through the application.

You are a cartographer, not an urban planner. You draw the map of the city as it is — crooked streets, dead ends, and all. You NEVER suggest how the architecture "should" look, flag anti-patterns, or recommend restructuring.

Inputs

  • The full project source tree
  • Output from the codebase-scanner skill (specs/docs/technology/stack.md) if available — use it to understand the tech stack before tracing architecture
  • Any existing architecture documentation (treat as supplementary, not authoritative — code wins)

Process

Step 1 — Identify Application Boundaries

Determine how many distinct applications or services exist:

  1. Single application: One deployable unit (monolith).
  2. Multi-project monorepo: Multiple deployable units in one repository (e.g., packages/api/, packages/web/, packages/worker/).
  3. Microservices in monorepo: Distinct services with separate entry points and potentially separate runtimes.

For each application boundary found, record:

  • Name (directory name or from config)
  • Runtime (Node.js, Python, .NET, etc.)
  • Entry point file
  • Deployment artifact type (container, serverless function, static site, etc.)
Step 2 — Map Internal Layers and Modules

Within each application, trace the internal structure:

  1. Scan import/require statements to build a module dependency graph.
  2. Identify layers by directory naming and import direction:
    • Presentation layer: routes, controllers, handlers, pages, components
    • Business logic layer: services, use-cases, domain, core
    • Data access layer: repositories, models, DAOs, queries
    • Infrastructure layer: config, middleware, clients, adapters
  3. Record import direction: which layers import from which. Document the actual dependency flow — do not assume it follows any pattern.
  4. Identify shared modules: code imported by multiple layers or services.
Step 3 — Trace Data Flow

Follow data through the application from entry to exit:

  1. Request flow: HTTP request → middleware → route handler → service → data access → database (or equivalent chain).
  2. Event flow: Event trigger → handler → processing → side effects.
  3. Background processing: Queue consumer → worker → storage.
  4. Scheduled tasks: Cron/timer → job → processing.

For each flow, record the chain of files/modules involved. Do not evaluate whether the flow is "clean" or "messy" — just trace it.

Step 4 — Identify Integration Points

Catalog every point where the application communicates externally:

Integration TypeWhat to Look For
DatabasesConnection strings, ORM config, query builders, raw SQL
External APIsHTTP clients, SDK calls, fetch/axios calls to external URLs
Message queuesQueue producers/consumers, pub/sub publishers/subscribers
File systemsFile read/write operations, blob storage clients
Cache systemsRedis/Memcached clients, in-memory cache usage
Authentication providersOAuth configs, SAML, OIDC, JWT verification
Email/SMS servicesSMTP config, SendGrid/Twilio/SES SDK usage
Search enginesElasticsearch/Algolia/Azure Search clients
CDN/StorageBlob storage, S3, Azure Storage SDK usage
Monitoring/LoggingAPM agents, log shipping, telemetry SDKs

For each integration point, record:

  • Type (database, API, queue, etc.)
  • Technology (PostgreSQL, Redis, SendGrid, etc.)
  • Configuration source (env var, config file, hardcoded)
  • Which modules/services use it
Show full SKILL.md (392 more words)Show less
Step 5 — Detect Architectural Patterns

Identify which patterns the codebase uses — by observing structure, not by assuming intent:

  • MVC: Controllers + Models + Views directories
  • Layered: Distinct directories for presentation, business, data access
  • Clean/Hexagonal: Ports and adapters, dependency inversion visible in imports
  • CQRS: Separate command and query handlers
  • Event-driven: Event emitters/listeners, message handlers
  • Monolith: Single deployable, shared database
  • Microservices: Multiple deployable units, separate data stores
  • Serverless: Functions as entry points, no long-running server
  • Modular monolith: Single deployable but strong module boundaries

Record the patterns you observe. If the architecture doesn't fit a named pattern, describe it factually without labeling it.

Step 6 — Generate Mermaid Diagrams

Produce the following diagrams:

Component Diagram — high-level view of major components and their relationships:

mermaid
graph TD
    subgraph "Web Application"
        A[Next.js Frontend] --> B[API Routes]
    end
    B --> C[(PostgreSQL)]
    B --> D[Redis Cache]
    B --> E[External Auth Provider]

Data Flow Diagram — how a typical request moves through the system:

mermaid
sequenceDiagram
    participant Client
    participant Middleware
    participant Handler
    participant Service
    participant Database
    Client->>Middleware: HTTP Request
    Middleware->>Handler: Authenticated Request
    Handler->>Service: Business Operation
    Service->>Database: Query
    Database-->>Service: Result
    Service-->>Handler: Domain Object
    Handler-->>Client: HTTP Response

Module Dependency Diagram — internal module relationships:

mermaid
graph TD
    routes --> middleware
    routes --> controllers
    controllers --> services
    services --> repositories
    repositories --> models
    services --> external-clients

Diagrams must reflect the actual code. Do not idealize or simplify away complexity that exists.

Output Format

Produce two files:

specs/docs/architecture/overview.md
markdown
# Architecture Overview — [Project Name]

_Extracted on [date]. Documents the architecture as it exists in code._

## System Boundaries

[List of applications/services with entry points and runtimes]

## High-Level Architecture

[Component diagram — Mermaid]

[Prose description of the overall architecture pattern observed]

## Data Flow

[Data flow diagrams — Mermaid]

[Description of primary request/response flows]

## Integration Points

| Type | Technology | Used By | Config Source |
|------|-----------|---------|---------------|
| Database | PostgreSQL | api-service | DATABASE_URL env var |
| ... | ... | ... | ... |

## Architectural Patterns Observed

[List patterns with evidence from the codebase]
specs/docs/architecture/components.md
markdown
# Component Catalog — [Project Name]

_Extracted on [date]._

## Component: [Name]

- **Path:** src/services/auth/
- **Type:** Business logic service
- **Responsibilities:** [What it does, based on its code]
- **Dependencies:** [What it imports]
- **Dependents:** [What imports it]
- **Integration points:** [External systems it talks to]

## Module Dependency Diagram

[Mermaid diagram]

[Repeat for each significant component/module]

Rules

  1. Document what exists. Every architectural statement must be traceable to specific files and import paths in the codebase.
  2. No assessment. Do not say "tightly coupled", "well-structured", "spaghetti", "clean", "messy", or any evaluative term. Describe structure factually.
  3. No recommendations. Do not suggest refactoring, restructuring, decomposing, or changing anything. The word "should" is banned.
  4. Diagrams match reality. If the module dependency graph is complex, the diagram must be complex. Do not simplify for aesthetics.
  5. Code over documentation. If existing architecture docs disagree with what the code shows, document what the code shows and note the discrepancy.
  6. Complete integration catalog. Missing an integration point (database, external API, queue) is a failure. Trace every outbound connection.
  7. Ambiguity is okay. If you cannot determine a pattern or relationship from the code, say "not determinable" rather than guessing.

Mandatory Completion Checklist

The orchestrator MUST verify ALL of the following before marking architecture-mapper as complete:

  • specs/docs/architecture/overview.md exists with a high-level Mermaid component diagram
  • specs/docs/architecture/components.md exists with per-component detail (responsibility, dependencies, interfaces)
  • All integration points are cataloged (databases, external APIs, queues, caches, file systems)
  • Data flow between components is documented with a Mermaid sequence or flow diagram
  • Layer boundaries (if any) are identified (e.g., controller → service → repository)

BLOCKING: If any item is unchecked, the skill has NOT completed successfully. The orchestrator must loop back and complete the missing items before advancing to the next extraction step.

© EmeaAppGbb, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .github/skills/architecture-mapper of EmeaAppGbb/spec2cloud.

Open the folder on GitHubat commit 8e76618

Compare with similar skills

Architecture Mapper next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Architecture Mapper compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Architecture Mapper this skillEmeaAppGbb/spec2cloud100—~2.4kAutomated safety check: PassMIT
Code Refactoring Workflowluongnv89/claude-howto42k—~3.1kAutomated safety check: PassMIT
Convert Internal Package to TypeScriptTryGhost/Ghost55k—~1.2kAutomated safety check: PassMIT
jscpd Code Migration Trackerkucherenko/jscpd6.4k—~5kAutomated safety check: PassMIT
Directory Build Organizationmicrosoft/testfx1k1 repos~2.5kAutomated safety check: PassMIT
Rails Upgrade Assistantombulabs/claude-code_rails-upgrade-skill389—~2.7kAutomated safety check: PassMIT

Similar skills

  • Code Refactoring Workflow

    luongnv89/claude-howto

    Guides systematic, test-backed refactoring in the style of Martin Fowler, moving through research, planning and small incremental changes with your approval at each phase.

    42k GitHub stars~3.1k tokensUpdated 8 days ago
    DevelopmentAuto-check passed
  • Moves a legacy internal Ghost package from JavaScript and CommonJS to TypeScript and ESM in three focused commits that keep git file history intact.

    55k GitHub stars~1.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Measures a code port between languages or frameworks with jscpd's function-level comparison, porting tests before code and tracking what is left unmatched.

    6.4k GitHub stars~5k tokensUpdated today
    DevelopmentAuto-check passed
  • Official

    Guide for organizing MSBuild infrastructure with Directory.Build.props, Directory.Build.targets, Directory.Packages.props, and Directory.Build.rsp.

    1k GitHub starsUsed in 1 repo~2.5k tokens
    DevelopmentAuto-check passed
  • Rails Upgrade Assistant

    ombulabs/claude-code_rails-upgrade-skill

    Analyzes a Rails app and builds an upgrade report with breaking changes, deprecations and step-by-step migration guides, one version at a time from Rails 2.3 through 8.1.

    389 GitHub stars~2.7k tokensUpdated 7 days ago
    DevelopmentAuto-check passed
  • Msbuild Antipatterns

    runceel/ReactiveProperty

    Catalog of MSBuild anti-patterns with detection rules and fix recipes.

    944 GitHub stars~3.7k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from EmeaAppGbb/spec2cloud

All 38 skills in this repo
  • Azure Deployment

    EmeaAppGbb/spec2cloud

    Provision Azure infrastructure, deploy to Azure Container Apps, and verify via smoke tests.

    100 GitHub stars~1.8k tokensUpdated 5 mo ago
    Auto-check passed
  • Contract Generation

    EmeaAppGbb/spec2cloud

    Generate API contracts, shared TypeScript types, and infrastructure resource definitions from Gherkin scenarios and test files.

    100 GitHub stars~1.6k tokensUpdated 5 mo ago
    Auto-check passed
  • Ddd Modeling

    EmeaAppGbb/spec2cloud

    Create Domain-Driven Design proposals from product specs or brownfield extraction outputs.

    100 GitHub stars~2.4k tokensUpdated 5 mo ago
    Auto-check passed
  • Implementation

    EmeaAppGbb/spec2cloud

    Write application code to make failing tests pass using contract-driven, slice-based architecture.

    100 GitHub stars~2.8k tokensUpdated 5 mo ago
    Auto-check passed
  • Spec Refinement

    EmeaAppGbb/spec2cloud

    Review PRDs and FRDs through product and technical lenses. An agent skill from EmeaAppGbb/spec2cloud.

    100 GitHub stars~2.2k tokensUpdated 5 mo ago
    Auto-check passed
  • State Management

    EmeaAppGbb/spec2cloud

    Read, write, and maintain .spec2cloud/state.json across phases and increments.

    100 GitHub stars~1.5k tokensUpdated 5 mo ago
    Auto-check passed

Categories

Questions about Architecture Mapper

What does Architecture Mapper do?

Map application architecture — components, layers, data flow, and integration points. Architecture Mapper is an agent skill from EmeaAppGbb/spec2cloud. Map application architecture — components, layers, data flow, and integration points.

When should I use Architecture Mapper?

Architecture Mapper fits situations like: you need to understand and document an existing systems structure before any migration; modernization planning.

How do I install Architecture Mapper in Claude Code?

Run `npx skills add EmeaAppGbb/spec2cloud --skill architecture-mapper -a claude-code`. Or copy the skill folder (.github/skills/architecture-mapper in EmeaAppGbb/spec2cloud) into .claude/skills/architecture-mapper in your project. Claude Code loads it when a task matches its description.

How do I install Architecture Mapper in Codex?

Run `npx skills add EmeaAppGbb/spec2cloud --skill architecture-mapper -a codex`. Or copy the skill folder (.github/skills/architecture-mapper in EmeaAppGbb/spec2cloud) into .agents/skills/architecture-mapper in your project. Codex loads it when a task matches its description.

Can I use Architecture Mapper in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add EmeaAppGbb/spec2cloud --skill architecture-mapper -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/architecture-mapper, .gemini/skills/architecture-mapper, .github/skills/architecture-mapper and .opencode/skills/architecture-mapper in your project.

What does Architecture Mapper need to run?

SKILL.md names no scripts, command-line tools or credentials: Architecture Mapper is instructions for the agent only. Our summary lists: Node.js.

Does Architecture Mapper access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Architecture Mapper safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Architecture Mapper use?

Architecture Mapper is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Architecture Mapper use?

About 2.4k tokens (SKILL.md is roughly 9.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Architecture Mapper?

Skills that share tags, products or a category with Architecture Mapper: Code Refactoring Workflow (luongnv89/claude-howto, 42k stars), Convert Internal Package to TypeScript (TryGhost/Ghost, 55k stars), jscpd Code Migration Tracker (kucherenko/jscpd, 6.4k stars) and Directory Build Organization (microsoft/testfx, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Architecture Mapper?

EmeaAppGbb (a GitHub organization) maintains it in EmeaAppGbb/spec2cloud, which has 100 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on April 16, 2026.

Source: EmeaAppGbb/spec2cloud on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.