Key Findings

Discovered Topics

๐Ÿ”จ
Project Structure
Build commands, package managers, and dependency setup
commit
0.4422
doc
0.3521
cargo
0.3495
behavior
0.3439
repository
0.3275
git
0.3242
bun
0.3167
command
0.3045
release
0.2923
package
0.2908

This topic represents a cluster of related terms discovered through topic modeling analysis. The word weights indicate how strongly each term is associated with this theme across the analyzed repositories.

๐Ÿงช
Nextjs & Training
Test runners, linting, and validation workflows
nextjs
0.7007
training
0.6466
writing
0.6351
breaking
0.5735
know
0.567
apis
0.5039
read
0.4566
guide
0.4565
relevant
0.4487
version
0.3975

This topic represents a cluster of related terms discovered through topic modeling analysis. The word weights indicate how strongly each term is associated with this theme across the analyzed repositories.

โœ๏ธ
Frontend Development
Code style, formatting conventions, and naming rules
npm
1.4675
frontend
0.2597
react
0.2502
typescript
0.2281
lint
0.2023
dev
0.1866
component
0.179
api
0.1468
vitest
0.1392
bash
0.1314

Frontend-focused CLAUDE.md files are among the most detailed. The prevalence of "npm," "typescript," and "react" reflects the dominance of the React/TypeScript ecosystem in projects using Claude Code. These files typically specify component patterns, state management, and build tooling.

๐Ÿ›๏ธ
Tool & Import
Project architecture, modules, and directory structure
tool
0.507
import
0.3127
model
0.2968
type
0.2865
return
0.2796
function
0.2521
const
0.236
error
0.2312
data
0.2054
api
0.2004

This topic represents a cluster of related terms discovered through topic modeling analysis. The word weights indicate how strongly each term is associated with this theme across the analyzed repositories.

โ›”
Project Structure
Constraints, prohibitions, and agent guardrails
skill
1.1252
project
0.3694
readmemd
0.2939
swift
0.288
guidance
0.2818
para
0.2235
agentsmd
0.1849
manager
0.1819
read
0.1708
general
0.1673

This topic represents a cluster of related terms discovered through topic modeling analysis. The word weights indicate how strongly each term is associated with this theme across the analyzed repositories.