dependency-graph
Generates a Mermaid dependency graph showing import relationships between modules. Use when analyzing coupling, finding circular deps, or planning refactors.
Works with
Agent Skills format with YAML frontmatter. Claude Code reads it as-is.
---
name: "dependency-graph"
description: "Generates a Mermaid dependency graph showing import relationships between modules. Use when analyzing coupling, finding circular deps, or planning refactors."
license: "MIT"
---
# Dependency Graph
Generate a Mermaid flowchart showing import and dependency
relationships between modules, packages, or plugins.
## When To Use
- Understanding what depends on what
- Finding circular dependencies
- Analyzing coupling between modules
- Planning refactoring by seeing dependency impact
- Answering "what breaks if I change this?"
## When NOT To Use
- Runtime call paths (use `cartograph:call-chain`)
- Type hierarchies (use `cartograph:class-diagram`)
## Workflow
### Step 1: Explore the Codebase
Dispatch the codebase explorer agent:
```
Agent(cartograph:codebase-explorer)
Prompt: Explore [scope] and return a structural model.
Focus on import statements and cross-module dependencies
for a dependency graph. Track both internal and external
imports.
```
### Step 2: Generate Mermaid Syntax
Transform the structural model into a Mermaid flowchart
with directed edges representing dependencies.
**Rules for dependency graphs**:
- Use `flowchart LR` (left-right) for dependency direction
- Each node is a module or package
- Edges point from dependent to dependency (A --> B means
"A depends on B")
- Color-code by dependency type:
- Default arrows for internal dependencies
- Dotted arrows (`-.->`) for external/optional deps
- Thick arrows (`==>`) for critical path dependencies
- Group into subgraphs by package/plugin
- If depth parameter given, limit transitive dependencies
- Highlight circular dependencies with red styling
**Example output**:
```mermaid
flowchart LR
subgraph sanctum[Sanctum]
commit[commit]
pr_prep[pr_prep]
workspace[workspace]
end
subgraph leyline[Leyline]
git[git_platform]
errors[error_patterns]
end
subgraph external[External]
subprocess[subprocess]
json[json]
end
commit --> git
commit --> json
pr_prep --> workspace
pr_prep --> git
workspace --> errors
workspace -.-> subprocess
```
### Step 3: Render via MCP
Call the Mermaid Chart MCP to render:
```
mcp__claude_ai_Mermaid_Chart__validate_and_render_mermaid_diagram
prompt: "Dependency graph of [scope]"
mermaidCode: [generated syntax]
diagramType: "flowchart"
clientName: "claude-code"
```
If rendering fails, fix syntax and retry (max 2 retries).
### Step 4: Present Results
Show the rendered diagram with analysis notes:
- Total modules and dependency count
- Most-depended-on modules (high fan-in)
- Modules with most dependencies (high fan-out)
- Circular dependencies if any detected
## Exit Criteria
- [ ] Mermaid `flowchart LR` syntax generated with directed edges
from dependent to dependency (A --> B means "A depends on B")
- [ ] `mcp__claude_ai_Mermaid_Chart__validate_and_render_mermaid_diagram`
called and returns without error
- [ ] Analysis notes include total module count, highest fan-in modules,
and highest fan-out modules
- [ ] Circular dependencies, if detected, are highlighted with red
styling and listed explicitly in the analysis notes
- [ ] External dependencies use dotted arrows (`-.->`) distinct from
internal dependency arrowsMore Refactoring skills
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.
analyze-project
lllllllama/rigorpilot-skills
Rigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrypoints, review configs and insertion points, or flag suspicious implementation patterns without modifying code or running heavy jobs. Do not use for active command execution, broad refactoring, speculative code adaptation, or automatic bug fixing.
request-refactor-plan
mattpocock/skills
Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.

