This is a structured workflow for documenting code entry points with dependency mapping to depth 3 and mermaid diagrams. You point it at a file, folder, function, or API, and it validates the target, searches existing knowledge first, analyzes dependencies while avoiding loops, then writes a markdown doc following a fixed template in docs/ai/implementation/. It optionally generates a standalone HTML artifact with a card based layout if you ask for one, though the markdown is the source of truth. The hard rule is no documentation gets written until validation and analysis finish. It's opinionated about stopping you from skipping the discovery phase, which is probably the right trade off if you've ever documented code in a hurry and regretted it later.

GitHub stars
1.3K
last updated
Jun 11, 2026

Install

$ npx -y skills add codeaholicguy/ai-devkit --skill document-code --agent claude-code

Installs into .claude/skills of the current project.

Files

Code Documentation Assistant

Build structured understanding of code entry points with an analysis-first workflow.

Hard Rule

  • Do not create documentation until the entry point is validated and analysis is complete.

Workflow

  1. Gather & Validate
  • Confirm entry point (file, folder, function, API), purpose, and desired depth.
  • Verify it exists; resolve ambiguity or suggest alternatives if not found.
  • Search for existing knowledge before analyzing: npx ai-devkit@latest memory search --query "<entry point name or purpose>"
  1. Collect Source Context
  • Summarize purpose, exports, key patterns.
  • Folders: list structure, highlight key modules.
  • Functions/APIs: capture signature, parameters, return values, error handling.
  1. Analyze Dependencies
  • Build dependency view up to depth 3, track visited nodes to avoid loops.
  • Categorize: imports, function calls, services, external packages.
  • Exclude external systems or generated code.
  1. Synthesize
  • Overview (purpose, language, high-level behavior).
  • Core logic, execution flow, patterns.
  • Error handling, performance, security considerations.
  • Improvements or risks discovered during analysis.

Sponsors

Details

Repository
github.com/codeaholicguy/ai-devkit
Categories
Backend & APIs, Documentation, AI & Agent Building
First seen
Jun 11, 2026

More from codeaholicguy/ai-devkit

All 12
1codeaholicguy avatartechnical-writercodeaholicguy/ai-devkitAI DevKit · Review and improve documentation for novice users. Use when users ask to review docs, improve documentation, audit README files, evaluate API docs, 0skills.sh installs
2daffy0208 avatarKnowledge Graph Builderdaffy0208/ai-dev-standardsDesign and build knowledge graphs. Use when modeling complex relationships, building semantic search, or creating knowledge bases. Covers schema design, entity 0skills.sh installs
3davila7 avatarAWS Penetration Testingdavila7/claude-code-templatesThis skill should be used when the user asks to "pentest AWS", "test AWS security", "enumerate IAM", "exploit cloud infrastructure", "AWS privilege escalation",0skills.sh installs
4davila7 avatarBurp Suite Web Application Testingdavila7/claude-code-templatesThis skill should be used when the user asks to "intercept HTTP traffic", "modify web requests", "use Burp Suite for testing", "perform web vulnerability scanni0skills.sh installs
5davila7 avatarHook Developmentdavila7/claude-code-templatesThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", 0skills.sh installs
6davila7 avatarNetwork 101davila7/claude-code-templatesThis skill should be used when the user asks to "set up a web server", "configure HTTP or HTTPS", "perform SNMP enumeration", "configure SMB shares", "test netw0skills.sh installs