Generate human-readable package documentation by analyzing code structure and extracting key information.
Generates comprehensive package documentation by analyzing code structure, dependencies, and data flows. Activates when users request package explanations or documentation using phrases like "explain this package" or "document this package".
/plugin marketplace add pietgk/vivief/plugin install devac@viviefThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Generate human-readable package documentation by analyzing code structure and extracting key information.
This skill activates when users ask about:
Creates a comprehensive docs/package-explained.md file with:
Uses DevAC's code graph to understand:
# Get package symbols
devac file-symbols <package-path>/src/
# Get package effects (Store, Retrieve, Send operations)
devac effects list -p <package-path>
# Get external dependencies
devac query "SELECT DISTINCT target FROM edges WHERE source_file LIKE '<package>%' AND edge_type = 'IMPORTS'"
# Get database operations
devac query "SELECT * FROM effects WHERE type IN ('Store', 'Retrieve') AND file_path LIKE '<package>%'"
# Get external service calls
devac query "SELECT * FROM effects WHERE type = 'Send' AND file_path LIKE '<package>%'"
Create docs/package-explained.md with the following structure:
# {Package Name}
## Purpose
{One paragraph describing what the package does}
## Responsibilities
- {Responsibility 1}
- {Responsibility 2}
- {Responsibility 3}
## Key Components
- **{ComponentName}** - {Description}
- **{ServiceName}** - {Description}
## Dependencies
### Internal
- **{Package}** - {What it's used for}
### External (Third-Party)
- **{Service}** - {What it's used for}
## Data Stores
- **{Database/Cache}** - {What data is stored}
## API Endpoints
| Method | Route | Description |
|--------|-------|-------------|
| GET | /path | Description |
devac effects listList all effects in a package to understand its behaviors.
devac effects list -p packages/user-service
devac file-symbolsGet all symbols to understand the code structure.
devac file-symbols packages/user-service/src/
devac queryQuery the code graph for specific patterns.
devac query "SELECT DISTINCT callee FROM effects WHERE file_path LIKE 'packages/user-service%'"
User: "Explain the user-service package"
Response approach:
devac file-symbols to get all symbols in the packagedevac effects list to understand data flows and external callsdocs/package-explained.md fileThe skill creates or updates docs/package-explained.md in the package directory.
devac analyze)devac effects init has discovered effect patterns/define-effects skillThis 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.