# Arch Lens Development

> Create Development architecture diagram showing project structure, build tools, and quality gates. Development lens answering "How is it built and tested?

- **Type:** Skill
- **Install:** `agentstack add skill-talont-org-autoskillit-arch-lens-development`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [TalonT-Org](https://agentstack.voostack.com/s/talont-org)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [TalonT-Org](https://github.com/TalonT-Org)
- **Source:** https://github.com/TalonT-Org/AutoSkillit/tree/main/src/autoskillit/skills_extended/arch-lens-development

## Install

```sh
agentstack add skill-talont-org-autoskillit-arch-lens-development
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Development Architecture Lens

**Cognitive Mode:** Development
**Primary Question:** "How is it built and tested?"
**Focus:** Project Structure, Build Tools, Quality Gates, Test Framework

## When to Use

- Need to understand developer experience
- Documenting build and test infrastructure
- Analyzing code quality gates
- User invokes `/autoskillit:arch-lens-development` or `/autoskillit:make-arch-diag development`

## Critical Constraints

**NEVER:**
- Modify any source code files
- Include runtime architecture details
- Show business logic
- Run subagents in the background (`run_in_background: true` is prohibited)

**ALWAYS:**
- Focus on BUILD and TEST infrastructure
- Show quality gate pipeline
- Document test framework setup
- Include entry points
- BEFORE creating any diagram, LOAD the `/autoskillit:mermaid` skill using the Skill tool - this is MANDATORY
- If the Skill tool cannot be used (disable-model-invocation) or refuses this invocation, do NOT proceed with diagram creation. Abort this step and omit the diagram from output.
- After writing the diagram file, emit the **absolute path** as a structured output
  token as your final output. Resolve the relative `temp/arch-lens-development/...`
  save path to absolute by prepending the full CWD:
  ```
  diagram_path = /absolute/cwd/temp/arch-lens-development/{filename}.md
  ```
  This token is MANDATORY — the pipeline cannot proceed without it.

## Arguments

`/autoskillit:arch-lens-development [context_path]`

- **context_path** (optional) — Absolute path to a PR context file containing new files
  (★-prefixed) and modified files (●-prefixed) from the PR diff. When provided, read
  this file before beginning analysis and focus the diagram on the architectural areas
  affected by these specific files. When absent, explore the full CWD.

---

## Analysis Workflow

### Step 0: Read PR context (when provided)

If a `context_path` positional argument is present:
1. Read the file at `context_path`
2. Extract: new files list (★-prefixed), modified files list (●-prefixed)
3. Focus Step 1 exploration on the modules/components these files belong to
4. Apply ★ prefix on diagram nodes representing new files/components
5. Apply ● prefix on diagram nodes representing modified files/components

If no `context_path` is provided, skip this step and explore the full CWD in Step 1.

### Step 1: Launch Parallel Exploration Subagents

Spawn Explore subagents to investigate:

**Project Structure**
- Find top-level directory organization
- Identify module/package boundaries
- Look for: build configs, package definitions, project layout

**Build Tooling**
- Find build configuration
- Identify package manager and build backend
- Look for: build config files, makefiles, task runners, package managers

**Linting & Formatting**
- Find code quality tools
- Identify pre-commit hooks
- Look for: linter configs, formatter configs, pre-commit hooks, code quality tools

**Type Checking**
- Find type checking configuration
- Identify strictness level
- Look for: type checker configs, static analysis tools

**Test Framework**
- Find test configuration
- Identify test patterns and fixtures
- Look for: test configs, test directories, test runners, test fixtures

**CI/CD (if present)**
- Find CI configuration
- Identify workflow stages
- Look for: CI/CD configs, workflow definitions, pipeline configs

**Entry Points**
- Find CLI entry points
- Identify console scripts
- Look for: entry point definitions, command definitions, binary files

### Step 2: Map Quality Pipeline

Document the code quality pipeline:
```
Code -> Format -> Lint -> Type Check -> Test -> Commit
```

**CRITICAL - Analyze Read/Write Direction:**
For EVERY build/test component:
- **Inputs (reads)**: What files/config does this tool READ?
- **Outputs (writes)**: What does this tool WRITE (reports, modified files)?
- **Side effects**: Does it modify source files or just report?

Distinguish:
- Tools that READ and MODIFY code (formatters)
- Tools that READ and REPORT only (linters, type checkers)
- Tools that READ code and WRITE artifacts (test output files)
- Config files (READ by tools, not written by build process)

### Step 3: Count Project Metrics

| Metric | Value |
|--------|-------|
| Source Files | N |
| Test Files | N |
| Dependencies | N |
| Entry Points | N |

### Step 4: Create the Diagram

Use flowchart with:

**Direction:** `TB` for pipeline flow

**Subgraphs:**
- Project Structure (directories)
- Build Tools (packaging)
- Quality Gates (linting, types)
- Test Framework (test runner, etc)
- Entry Points (CLI commands)

**Node Styling:**
- `cli` class: Project structure, directories
- `phase` class: Build configuration
- `detector` class: Quality gates (linting, typing)
- `handler` class: Test framework
- `output` class: Entry points, outputs

**Show Pipeline Flow:**
- Code through quality gates
- Build to entry points

### Step 5: Write Output

Write the diagram to: `{{AUTOSKILLIT_TEMP}}/arch-lens-development/arch_diag_development_{YYYY-MM-DD_HHMMSS}.md` (relative to the current working directory)

After writing the diagram file, emit a structured output line:

> **IMPORTANT:** Emit the structured output tokens as **literal plain text with no
> markdown formatting on the token names**. Do not wrap token names in `**bold**`,
> `*italic*`, or any other markdown. The adjudicator performs a regex match on the
> exact token name — decorators cause match failure.

```
diagram_path = {absolute_path_to_diagram_file}
```

---

## Output Template

```markdown
# Development Diagram: {Project Name}

**Lens:** Development (Build & Test)
**Question:** How is it built and tested?
**Date:** {YYYY-MM-DD}
**Scope:** {What was analyzed}

## Project Metrics

| Metric | Value |
|--------|-------|
| Source Directories | {count} |
| Test Files | {count} |
| Dependencies | {count} |
| Entry Points | {count} |

## Development Diagram

```mermaid
%%{init: {'flowchart': {'nodeSpacing': 50, 'rankSpacing': 60, 'curve': 'basis'}}}%%
flowchart TB
    %% CLASS DEFINITIONS %%
    classDef cli fill:#1a237e,stroke:#7986cb,stroke-width:2px,color:#fff;
    classDef stateNode fill:#004d40,stroke:#4db6ac,stroke-width:2px,color:#fff;
    classDef handler fill:#e65100,stroke:#ffb74d,stroke-width:2px,color:#fff;
    classDef phase fill:#6a1b9a,stroke:#ba68c8,stroke-width:2px,color:#fff;
    classDef output fill:#00695c,stroke:#4db6ac,stroke-width:2px,color:#fff;
    classDef detector fill:#b71c1c,stroke:#ef5350,stroke-width:2px,color:#fff;

    subgraph Structure ["PROJECT STRUCTURE"]
        direction TB
        SRC["src/━━━━━━━━━━Source code"]
        TESTS["tests/━━━━━━━━━━Test suite"]
    end

    subgraph Build ["BUILD TOOLING"]
        direction TB
        CONFIG["Build Config━━━━━━━━━━Build system"]
        TASKFILE["Task Runner━━━━━━━━━━Task automation"]
    end

    subgraph Quality ["CODE QUALITY GATES"]
        direction TB
        FORMAT["Formatter━━━━━━━━━━Code style"]
        LINT["Linter━━━━━━━━━━Code quality"]
        TYPES["Type Checker━━━━━━━━━━Static analysis"]
    end

    subgraph Testing ["TEST FRAMEWORK"]
        direction TB
        TESTRUN["Test Runner━━━━━━━━━━Test execution"]
        FIXTURES["Fixtures━━━━━━━━━━Test setup"]
    end

    subgraph EntryPoints ["ENTRY POINTS"]
        direction LR
        EP1["cli-command"]
    end

    %% FLOW %%
    SRC --> CONFIG
    TESTS --> CONFIG
    CONFIG --> TASKFILE

    CONFIG --> FORMAT
    FORMAT --> LINT
    LINT --> TYPES

    TYPES --> TESTRUN
    TESTRUN --> FIXTURES

    CONFIG --> EP1

    %% CLASS ASSIGNMENTS %%
    class SRC,TESTS cli;
    class CONFIG,TASKFILE phase;
    class FORMAT,LINT,TYPES detector;
    class TESTRUN,FIXTURES handler;
    class EP1 output;
```

**Color Legend:**
| Color | Category | Description |
|-------|----------|-------------|
| Dark Blue | Structure | Project directories |
| Purple | Build | Configuration and automation |
| Red | Quality | Linters and type checkers |
| Orange | Testing | Test framework and fixtures |
| Dark Teal | Entry Points | CLI commands |

## Development Workflow

```
Code -> format -> lint -> type-check -> test -> commit
```

## Pre-commit Hooks

| Hook | Purpose |
|------|---------|
| {hook} | {purpose} |

## Entry Points

| Command | Module | Purpose |
|---------|--------|---------|
| {command} | {module} | {purpose} |
```

---

## Pre-Diagram Checklist

Before creating the diagram, verify:

- [ ] LOADED `/autoskillit:mermaid` skill using the Skill tool
- [ ] Using ONLY classDef styles from the mermaid skill (no invented colors)
- [ ] Diagram will include a color legend table

---

## Related Skills

- `/autoskillit:make-arch-diag` - Parent skill for lens selection
- `/autoskillit:mermaid` - MUST BE LOADED before creating diagram

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [TalonT-Org](https://github.com/TalonT-Org)
- **Source:** [TalonT-Org/AutoSkillit](https://github.com/TalonT-Org/AutoSkillit)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-talont-org-autoskillit-arch-lens-development
- Seller: https://agentstack.voostack.com/s/talont-org
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.