skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
athola/claude-night-market83 installs

code-communities

Detects architectural clusters and coupling boundaries via community detection on the code graph. Use when identifying module groupings or refactoring targets.

How do I install this agent skill?

npx skills add https://github.com/athola/claude-night-market --skill code-communities
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    This skill identifies code modules and architectural boundaries using standard local analysis tools. It identifies module structures through directory layouts and import statements, optionally leveraging a local plugin for graph-based analysis. No security risks, unauthorized network access, or malicious patterns were identified.

  • Socketpass

    No alerts

  • Snykpass

    Risk: LOW · No issues

What does this agent skill do?

Code Community Detection

Identify architectural clusters and module boundaries in the codebase.

When NOT To Use

  • One module's imports (use cartograph:dependency-graph)
  • Rendering an architecture already decided (use cartograph:architecture-diagram)

Prerequisites

This skill requires the gauntlet plugin for graph data. Discover it:

GRAPH_QUERY=$(find ~/.claude/plugins -name "graph_query.py" -path "*/gauntlet/*" 2>/dev/null | head -1)

If gauntlet is not installed: Fall back to directory structure analysis. Group files by directory and use import statements to identify module boundaries. Generate a Mermaid diagram from directory-level relationships.

If installed but no graph.db: Tell the user to run /gauntlet-graph build.

Steps

  1. Run community detection (requires gauntlet):

    python3 "$GRAPH_QUERY" --action communities
    

    Fallback (no gauntlet): Analyze directory structure and cross-directory imports:

    # Directory-level grouping
    find . -name "*.py" -not -path "*/node_modules/*" | \
        sed 's|/[^/]*$||' | sort | uniq -c | sort -rn
    
    # Cross-directory imports (rg preferred, grep fallback)
    if command -v rg &>/dev/null; then
      rg "^from |^import " --type py -l . | \
        xargs -I{} rg "^from \w+ import|^import \w+" {} --no-filename
    else
      grep -rh "^from \|^import " --include="*.py" .
    fi | sort | uniq -c | sort -rn | head -20
    

    Group by top-level directories and count cross-directory imports to estimate coupling.

  2. Display clusters:

    Community         | Nodes | Cohesion | Description
    auth              |    12 |    0.85  | Authentication module
    db                |     8 |    0.92  | Database access layer
    api/handlers      |    15 |    0.71  | API request handlers
    utils             |     6 |    0.45  | Shared utilities
    
  3. Show coupling warnings: If communities have

    10 cross-boundary edges, highlight them:

    WARNING: High coupling between 'auth' and 'api/handlers'
    (23 cross-community edges, severity: high)
    
  4. Generate Mermaid diagram:

    flowchart TB
      subgraph auth[Auth Module - cohesion 0.85]
        verify_token
        check_permissions
      end
      subgraph db[DB Layer - cohesion 0.92]
        execute_query
        connection_pool
      end
      auth -->|"23 edges"| api
      db -->|"5 edges"| api
    
  5. Suggest improvements:

    • Low cohesion (<0.5): "Consider splitting this module into more focused components"
    • High coupling (>20 edges): "Consider introducing an interface to reduce direct dependencies"

Algorithm

Uses the Leiden algorithm (when igraph is available) with edge-type-specific weights. Falls back to file-based grouping otherwise.

Edge TypeWeight
CALLS1.0
INHERITS0.8
IMPLEMENTS0.7
IMPORTS_FROM0.5
TESTED_BY0.4
CONTAINS0.3

Exit Criteria

  • Community table rendered with columns Community, Nodes, Cohesion, and Description for each detected cluster
  • Coupling warning surfaced for any pair of communities with more than 10 cross-boundary edges, labelled with severity
  • Mermaid flowchart TB generated with one subgraph per community showing cohesion score in the subgraph label
  • Improvement suggestions provided for any community with cohesion < 0.5 or coupling > 20 cross-community edges
  • If gauntlet is not installed, directory-structure fallback runs and absence of graph data is stated to the user

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/athola/claude-night-market/code-communities">View code-communities on skillZs</a>