daturkel

find-convo

A CLI tool to search your Claude Code conversation history across all projects. Solves the problem of "I know I discussed this somewhere but can't remember which repo/session" without manually grepping through ~/.claude/projects/.

It indexes every local Claude Code session transcript (including subagent/Task-tool transcripts) into a local SQLite FTS5 full-text index, then lets you search by keyword, exact phrase, or required terms — optionally filtered by project and date, with relevance ranking that also weighs recency.

Setup

1. Requires uv (used to auto-manage the script's Python environment — no separate pip install needed) and Python 3.11+.
2. Save the find-convo file from this gist into ~/.local/bin/find-convo, then make it executable:

daturkel

#!/usr/bin/env python3
# /// script
# requires-python = ">=3.10"
# ///
"""Collapse a shell command with line-continuation backslashes into a single line."""

import re
import sys

daturkel

Ray Serve on KubeRay: A Practical Overview

A guide to understanding the core concepts behind Ray Serve — from clusters to deployments to autoscaling — so you can build and configure production applications with confidence.

---

Table of Contents

daturkel

system: | You are a summarization assistant. Always begin responses with the summary itself, never with meta-commentary about what you're doing.

First you SILENTLY use a tool-call to fetch the article, then you respond with the summary.

You do NOT say "i'll fetch the article and summarize it." You do not say "based on the webpage content..." You just go straight into the summary.

Example format: input: http://news.com/an-article-about-ukraine output:

daturkel

Fragments

"Fragments" are text you can inject into a conversation. You can start a conversation with a fragment with -f <fragment> or insert one during a chat with !fragment <fragment>.

The site-text fragment pulls a website as markdown and injects it into the prompt.

$ llm install llm-fragments-site-text
$ llm -f site:https://hinge.co/mission "What's Hinge all about?"

daturkel

llm -T get_collections -T get_relevant_documents "how do i find similar documents based on embeddings in llm" --tools-debug

To find similar documents based on embeddings in an LLM, I'll need to help you use the embedding database tools available. Let me show you how to do this.

First, let's see what collections are available in the embeddings database:

Tool call: get_collections({})
  ["documentation"]

daturkel

import matplotlib.pyplot as plt

%config InlineBackend.figure_format = 'retina'

daturkel

Todo.rb

Todo.rb is a simple command-line tool for managing todos. It's minimal, straightforward, and you can use it with your favorite text editor.

Getting Started

Todo.rb doesn't require any third-party gems so you can copy the file anywhere and use it as long as it's executable: