analyze

Audit code quality, dead code, and architecture using OCXP graph intelligence.

Updated May 12, 2026
One-click install
npx skills add https://github.com/contexthub-md/marketplace --skill analyze-contexthub-md
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: analyze
Source: https://github.com/contexthub-md/marketplace/tree/main/contexthub/skills/analyze
Command: npx skills add https://github.com/contexthub-md/marketplace --skill analyze-contexthub-md

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually auditing a large codebase for dead code, anti-patterns, and architectural violations is slow and error-prone. This Skill runs deterministic, graph-based analysis through ContextHub's OCXP engine to surface prioritized findings with confidence scores and file locations. ## Core Features & Use Cases - Code Quality Audits: Detect dead code, legacy patterns, anti-patterns, and infrastructure security issues via ch_ocxp_analyze, with confidence filtering and path scoping. - Architecture & Gap Analysis: Discover naming conventions, module boundary violations, research gaps, orphan entities, and subsystem communities using pure graph analysis with no LLM cost. - Use Case: Before a major refactor, run a full analysis on src/api/ to find dead code in hot paths, check which subsystems are most affected via community detection, and triage findings by priority. ## Quick Start Ask the assistant to analyze dead code and architecture violations in the src/api directory using the ContextHub analyze skill.

Frequently Asked Questions about analyze

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I find dead code in a large codebase?

Run the analyze skill with the dead_code category, which uses OCXP graph analysis to detect unreferenced entities and dead subgraphs. Use path_filter to scope results to a directory and min_confidence to reduce noise.

How to check architecture violations in a project?

Use the ch_ocxp_constraints tool through this skill to discover naming conventions, semantic suffix patterns, and module boundary violations. Results are derived from structural codebase patterns, not manual rule configuration.

Does this code analysis require an LLM or extra cost?

No, all analysis is deterministic and based on structural graph properties of the indexed codebase. Gap analysis runs in roughly 5ms with pure graph computation and no LLM involvement.

Why does the analysis return OCXP_UNAVAILABLE or NO_PROJECT errors?

These errors mean no active project with indexed repositories exists. Run the contexthub connect skill first to set up a workspace, then verify index freshness with ch_get_index_status before analyzing.

Can I limit analysis to a specific directory?

Yes, pass a path_filter parameter such as src/api/ to scope analysis to a specific directory. You can also use output_mode summary for initial triage on large codebases to prevent result overflow.