povvo/claudikins-github-readme-for-perfectionists/deep-dive

Claude Code and agent skill by povvo/claudikins-github-readme-for-perfectionists

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use when starting the README pipeline to extract technical facts from codebase. Identifies project type, tech stack, dependencies, entry points, CI configuration. Outputs Reality Report.

Install

npx vskill@latest install povvo/claudikins-github-readme-for-perfectionists/deep-dive

SKILL.md

The Deep Dive

Goal: Establish the ground truth of the codebase (what IS) before imagining what could be.

Workflow

Step 0: Load Intelligence Read references/what-to-extract.md for detailed extraction patterns.

  1. Scout Structure: List files/dirs to understand layout (bin, src, dist, docs).
  2. Identify Configuration: Read dependency files (package.json, Cargo.toml, pyproject.toml).
  3. Extract Entry Points: Find main exports, CLI commands, API routes.
  4. Context Extraction: Scan chat history for user struggles/intent (if available).
  5. Synthesize: Generate the "Codebase Reality Report".

1. Project Type Detection

Entry Point Analysis
Files PresentLikely Type
bin/, shebang in mainCLI tool
src/index.ts with exportsLibrary
src/main.ts or app.tsApplication
plugin.json, .claude-plugin/Plugin
src/server.ts, app.pyAPI/Server
Dockerfile onlyContainer
setup.py with console_scriptsPython CLI
Cargo.toml with [[bin]]Rust CLI
Package.json Indicators
json
{
"bin": { "cmd": "./dist/cli.js" }, // CLI
"main": "./dist/index.js", // Library
"exports": { ".": "./dist/index.js" }, // Modern library
"scripts": { "start": "node server.js" } // Application
}

2. Tech Stack Extraction

Dependency Files
FileEcosystem
package.jsonNode.js/JavaScript
requirements.txt, pyproject.tomlPython
Cargo.tomlRust
go.modGo
GemfileRuby
pom.xml, build.gradleJava
composer.jsonPHP
Framework Detection

JavaScript/TypeScript:

  • react, vue, angular - Frontend framework
  • express, fastify, koa - Backend framework
  • electron - Desktop app
  • react-native - Mobile app

Python:

  • fastapi, flask, django - Web framework
  • click, typer, argparse - CLI framework
  • pytorch, tensorflow - ML framework
Build Tool Detection
ToolFiles
TypeScripttsconfig.json
Webpackwebpack.config.js
Vitevite.config.ts
esbuildesbuild in scripts
Rolluprollup.config.js
Babel.babelrc, babel.config.js

3. Dependencies & Prerequisites

Runtime Requirements

From package.json:

json
{ "engines": { "node": ">=18.0.0", "npm": ">=9.0.0" } }

From pyproject.toml:

toml
[project]
requires-python = ">=3.10"

From Cargo.toml:

toml
[package]
rust-version = "1.70"
System Dependencies

Check these files:

  • Dockerfile - RUN apt-get install commands
  • .github/workflows/*.yml - setup steps
  • Makefile - prerequisite checks
  • INSTALL.md or docs/installation.md

Common system deps:

  • libssl-dev - cryptography
  • libpq-dev - PostgreSQL
  • ffmpeg - media processing
  • graphviz - diagram generation

4. Entry Points & API Surface

What does the project export/expose?

  • Main function/export in index file
  • CLI commands from bin directory
  • API routes from server files
  • Public methods from library exports

CLI help text extraction:

typescript
program
.name('my-tool')
.description('Process files with advanced filtering')
.version('1.0.0');

Value proposition sources:

  • package.json description field
  • Module-level docstrings
  • JSDoc on main exports
  • Existing README fragments

5. CI/Automation Detection

GitHub Actions

Badge sources from workflows:

  • Workflow status - Build badge
  • codecov/codecov-action - Coverage badge
  • Release workflow - Version badge
Other CI
ServiceConfig File
CircleCI.circleci/config.yml
Travis.travis.yml
GitLab CI.gitlab-ci.yml
JenkinsJenkinsfile

6. Chat History Context

Source: ~/.claude/history.jsonl

Filter entries where project matches the current project path.

Pattern Extraction

Repeated questions (knowledge gaps):

  • "How do I..." patterns
  • "Why isn't..." patterns
  • "What's the difference between..." patterns

Problem categories:

  • Configuration/Setup
  • Debugging/Errors
  • Feature implementation
  • Performance
  • Testing
  • Deployment
README Implications
Pattern FoundREADME Implication
Repeated config questionsDetailed configuration section
Debugging strugglesTroubleshooting section
"How do I test" questionsTesting section with examples
Performance questionsPerformance section
Deployment questionsDeployment guides

Output Format

markdown
# Deep Dive Findings
## Project Overview
-**Type:** [CLI/library/framework/plugin/app/API]
-**Tech Stack:** [languages, frameworks]
-**Value Proposition:** [1-2 sentence problem/solution]
-**Entry Point:** [main file/command]
## Dependencies
-**Runtime:** [Node 18+, Python 3.10+, etc.]
-**System:** [any system dependencies]
-**Dev:** [dev dependencies of note]
## Entry Points
-[file:line] - [what it does]
## CI/Automation
-**Build:** [workflow files]
-**Badge Sources:** [CI, coverage, package manager]
## User Context (from Chat History)
-**Common Struggles:** [repeated questions]
-**Decisions Made:** [key decisions from history]
-**Focus Areas:** [topics frequently discussed]
## Missing Information (Blockers)
-[ ] [List anything you need but couldn't find]

Important

  • Focus on FACTS, not improvements (that's crystal-ball's job)
  • Be specific with file:line references
  • Note confidence levels:
  • High: Extracted from config files
  • Medium: Inferred from patterns
  • Low: Guessed from structure

Handoff

After presenting the Reality Report:

  1. Ask: "Does this accurately represent the codebase? Any missing information we need to clarify?"
  2. Wait for user confirmation.
  3. Transition:
  • If changes needed: Refine the Deep Dive.
  • If approved: "Proceeding to crystal-ball to predict what this project COULD become."

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
3
Repository forks
1
7-day trend score
7

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/povvo/claudikins-github-readme-for-perfectionists/deep-dive/badge)](https://verified-skill.com/skills/povvo/claudikins-github-readme-for-perfectionists/deep-dive)

Something wrong with this skill or its page? Tell us.