Skip to content

Instantly share code, notes, and snippets.

@samkeen
Last active January 6, 2026 22:02
Show Gist options
  • Select an option

  • Save samkeen/cbf7c29958fae7442f4c940ce5cecb20 to your computer and use it in GitHub Desktop.

Select an option

Save samkeen/cbf7c29958fae7442f4c940ce5cecb20 to your computer and use it in GitHub Desktop.
AC research: Dev journal response from Claude Code , in this case with system prompt + use of a custom built API

Dev Journal: January 3-6, 2026

A productive 4-day stretch focused on three main projects. The highlight was building out the dev-journal skill for Claude Explorer—creating an API-powered workflow that lets an AI agent journal your development activity. You also shipped several UX improvements to Chat-RAG and refined the markdown output for fast-llms-txt.


Monday, January 6

Claude Explorer - Dev journal skill and API refinements

  • Crafted a system prompt for an LLM agent to generate developer journals from the Claude Explorer API
  • Built an API proxy script to work around sandbox restrictions
  • Updated the dev-journal skill with the new workflow
  • Debugged an issue with empty message content in the API responses

Chat-RAG - UI styling and GitHub issue fix

  • Addressed GitHub issue #8
  • Refined CSS styling and HTML templates for the chat explorer interface

fast-llms-txt - Schema formatting improvements

  • Standardized schema extraction with dollar sign prefix convention ($Session, $Message, etc.)
  • Moved all named schemas to a definitions section for consistency

Saturday, January 4

Chat-RAG - Server startup and UX fixes

  • Added automatic port retry logic (tries port+1 up to 5 times if the default is in use)
  • Fixed the collection selector not resetting after "Test Connection" click
  • Improved logging output to show the running address in the startup banner

Friday, January 3

Claude Explorer - Activity API enhancements

  • Modified 11 files across the API routes and frontend
  • Updated activity.py, correlated.py, and projects.py routes
  • Refined the API spec and TypeScript client

fast-llms-txt - OpenAPI-to-markdown generator improvements

  • Improved markdown output formatting with H3 headings using backticks
  • Changed descriptions to blockquotes below headings
  • Renamed "Parameters" → "Request Parameters" and "Response" → "Returns"

Would you like any changes or additions?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment