Create and maintain architecture documentation using standard formats
Generates architecture documentation including ADRs, C4 diagrams, and technical specs. Use when you need to create standardized architecture docs from system context or decisions.
/plugin marketplace add pluginagentmarketplace/custom-plugin-software-architect/plugin install software-architect-assistant@pluginagentmarketplace-software-architectThis skill inherits all available tools. When active, it can use any tool Claude has access to.
assets/config.yamlassets/schema.jsonreferences/GUIDE.mdreferences/PATTERNS.mdscripts/validate.pyGenerate architecture documentation in standard formats including ADRs, C4 diagrams, and technical specifications with consistent structure and quality.
| Parameter | Type | Required | Validation | Default |
|---|---|---|---|---|
doc_type | enum | ✅ | adr|c4|sequence|overview | - |
context | string | ✅ | min: 20 chars | - |
format | enum | ⚪ | markdown|mermaid|plantuml | markdown |
audience | enum | ⚪ | technical|executive|mixed | technical |
detail_level | enum | ⚪ | overview|detailed | detailed |
┌──────────────────────────────────────────────────────────┐
│ 1. VALIDATE: Check doc_type and context │
│ 2. SELECT: Choose appropriate template │
│ 3. GATHER: Extract relevant information │
│ 4. GENERATE: Create documentation content │
│ 5. FORMAT: Apply output format (Mermaid, etc.) │
│ 6. VALIDATE: Check completeness and consistency │
│ 7. RETURN: Deliver formatted document │
└──────────────────────────────────────────────────────────┘
| Error | Retry | Backoff | Max Attempts |
|---|---|---|---|
TEMPLATE_ERROR | Yes | 1s | 2 |
VALIDATION_FAILED | No | - | 1 |
FORMAT_ERROR | Yes | 500ms | 3 |
log_points:
- event: doc_generation_started
level: info
data: [doc_type, format]
- event: doc_generation_complete
level: info
data: [doc_type, size_bytes, completeness_score]
- event: validation_warning
level: warn
data: [missing_sections]
metrics:
- name: docs_generated
type: counter
labels: [doc_type]
- name: generation_time_ms
type: histogram
- name: completeness_score
type: gauge
| Error Code | Description | Recovery |
|---|---|---|
E101 | Missing context | Request system/decision context |
E102 | Invalid doc_type | Show available doc types |
E103 | Inconsistent content | Flag for review |
E104 | Diagram syntax error | Validate and fix Mermaid/PlantUML |
test_cases:
- name: "Generate ADR"
input:
doc_type: "adr"
context: "Choosing PostgreSQL for user data"
format: "markdown"
expected:
contains: ["## Status", "## Decision", "## Consequences"]
valid_markdown: true
- name: "Generate C4 Container Diagram"
input:
doc_type: "c4"
context: "E-commerce platform with React, Node.js, PostgreSQL"
format: "mermaid"
expected:
contains: ["C4Container", "Container(", "Rel("]
valid_mermaid: true
- name: "Invalid doc_type"
input:
doc_type: "invalid"
expected:
error_code: "E102"
| Symptom | Root Cause | Resolution |
|---|---|---|
| Incomplete ADR | Missing decision context | Add context, alternatives |
| Diagram won't render | Syntax error | Validate Mermaid syntax |
| Wrong audience level | Mismatched detail | Adjust detail_level param |
□ Is doc_type supported?
□ Is context sufficient for doc type?
□ Is format appropriate for target?
□ Are all required sections present?
□ Is Mermaid/PlantUML syntax valid?
# ADR-{NUMBER}: {TITLE}
## Status
{Proposed | Accepted | Deprecated | Superseded}
## Context
{Problem description}
## Decision
{What was decided}
## Consequences
### Positive
- {Benefit}
### Negative
- {Trade-off}
C4Container
title {System Name}
Person(user, "User")
Container(app, "Application", "Technology")
ContainerDb(db, "Database", "Technology")
Rel(user, app, "Uses")
Rel(app, db, "Reads/Writes")
| Component | Trigger | Data Flow |
|---|---|---|
| Agent 02 | Doc request | Receives context, returns formatted doc |
| Agent 01 | ADR trigger | Receives decision for documentation |
| Version | Date | Changes |
|---|---|---|
| 2.0.0 | 2025-01 | Production-grade: templates, tests, validation |
| 1.0.0 | 2024-12 | Initial release |
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.