adhishthite

autoexp — Autonomous Experimentation Loop

Generalized from Karpathy's autoresearch. Same loop, any domain.

---

The Idea

An AI agent runs an infinite hill-climbing loop: modify → run → measure → keep or revert → repeat. No human in the loop. Wake up to a TSV of completed experiments.

adhishthite

#!/usr/bin/env bash
# ============================================================================
# bws-env-push.sh — Push .env secrets INTO Bitwarden Secrets Manager
#
# Usage:
#   ./bws-env-push.sh <.env path> <BWS project-id> [prefix]
#
# Examples:
#   ./bws-env-push.sh .env 9a8b7c6d-1234-5678-abcd-ef0123456789
#   ./bws-env-push.sh .env 9a8b7c6d-1234-5678-abcd-ef0123456789 ELASTICGPT_ANALYTICS_

adhishthite

#!/usr/bin/env bash
set -euo pipefail

# ============================================================================
# OpenClaw Migration Script
# Exports or imports your OpenClaw setup between machines.
# Usage:
#   ./openclaw-migrate.sh export              # Create migration bundle
#   ./openclaw-migrate.sh import <bundle>     # Restore from bundle
#   ./openclaw-migrate.sh verify              # Check current installation

adhishthite

ClawHub Skill Publishing Checklist

Learned the hard way with Jina AI (v1.0.0 → v1.0.6). Follow this BEFORE uploading.

---

SKILL.md Frontmatter

---

adhishthite

description	Interview user about themselves and their project idea, then scaffold it with best practices and proper documentation
allowed-tools	Bash, Read, Write, Edit, Glob, Grep, AskUserQuestion, Task, TodoWrite
model	opus

Project Onboarding Wizard

You are a dedicated software architect and engineer helping onboard a new project. Your job is to understand the person first, then the project, then scaffold a production-ready codebase.

adhishthite

description	Interactively explore edge cases from a user/product perspective, then document them
argument-hint	feature-or-file
allowed-tools	Read, Write, Edit, AskUserQuestion, TodoWrite
model	opus

Edge Case Explorer

You are a product-minded QA specialist and devil's advocate. Your job is to find ways that users, systems, or the real world could break the product - NOT technical implementation bugs.

adhishthite

import time
import numpy as np
from elasticsearch import Elasticsearch
from typing import List, Dict
from tabulate import tabulate

# === CONFIGURATION SECTION ===

# Your Elasticsearch deployment details
ES_HOST = "PUT_HOST_HERE"       # Replace with your Elastic Cloud endpoint

adhishthite

// 🎮 Game vibe-coded by Adhish Thite <adhish.thite@gmail.com>
// 🤖 Entirely generated using Gemini 2.5 (Experimental) on March 26, 2025
// 🚀 Paste this code into https://editor.p5js.org to play the game and enjoy the vibe!

// ==================================
// ==      GAME CONFIGURATION      ==
// ==================================
const INITIAL_GAME_SPEED = 6;
const GAME_SPEED_INCREMENT = 0.003;
const GRAVITY = 0.7;

adhishthite

"""
(c) 2023, Adhish Thite.
"""

# The following code installs the required Python packages for the script.
# Faker is a Python package for creating fake data.
# tqdm is a Python library used for printing progress bars.
# bloom-filter2 is a Python implementation of bloom filters, a probabilistic data structure.

!pip install Faker

adhishthite

Keybase proof

I hereby claim:

• I am adhishthite on github.
• I am adhisht (https://keybase.io/adhisht) on keybase.
• I have a public key ASCn3Hal9BnMTnBffIQc_oiqG2tvaF4C5QD0T1M6LIpg9wo

To claim this, I am signing this object: