One shell script that makes a rooted LG webOS TV lighter and quieter:
Nothing is deleted and the root filesystem is never touched. It only edits
Inspiration: George Shrinks — Episode 1: "If It Ain't Broke" (https://www.youtube.com/watch?v=3_EOpF2RGBE)
Tech Stack: Blender (Python-scripted .glb 3D modeling & animation pipeline) + Three.js (Vite, Rapier3D / custom arcade physics, Web Audio API procedural swing/jazz soundtrack, custom Toon/Storybook shaders)
George Shrinks has a signature mid-century modern / 1940s–50s storybook aesthetic created by William Joyce:
| [VERIFY] USER ID: lucataco | |
| [VERIFY] Dry-run verification completed. | |
| [AGENT] USER ID: lucataco | |
| [AGENT] Target: Hac-Man (Misc) [challenge_id=2] | |
| [AGENT] Description: A partner challenge with our friends at Hac-Man CTF! There's a hungry maze-guardian waiting on the other end of this one, and it only responds to one thing: the magic word. You won't find it here — go see the Hac-Man challenge team to get it, then send it over in a chat message. | |
| [AGENT] Discovering available models... | |
| [AGENT] Using model (participant-selected): qwen3.6-35b-a3b | |
| [NGINX-SIDECAR] GET /llm/models → 200 | |
| [NGINX-SIDECAR] GET /llm/models → 200 | |
| [AGENT] Context window: 8192 tokens (guessed) -> MAX_OBSERVATION_CHARS=3276 |
| #!/usr/bin/env bash | |
| set -euo pipefail | |
| # Production GLM-5.2 Q4_K_XL launcher for this 4x RTX PRO 6000 Blackwell host. | |
| # | |
| # Current recommended production path: | |
| # - llama.cpp CUDA server | |
| # - 0xSero GLM-5.2 REAP Q4_K_XL GGUF | |
| # - layer split across 4 GPUs because this machine has no GPU P2P/NVLink | |
| # - 4 concurrent slots x 100k context each |
| name | replicat |
|---|---|
| description | Use when a user wants to search, compare, inspect, or run Replicate models for image, video, audio, text, OCR, lip sync, or multi-step creative generation workflows. |
| compatibility | opencode |
You are using Replicat-style Replicate model discovery and execution inside OpenCode.
Use when the user wants a short (~1-3 min) explainer or marketing video about a Cloudflare product, primitive, or developer-platform concept (Workers, Durable Objects, R2, Queues, AI Gateway, KV, Pages, Browser Rendering, Sandbox SDK, Access, etc.). Produces a polished MP4 that visually matches the Cloudflare "Let It Slide" slide-deck aesthetic at let-it-slide.sid7002.workers.dev: warm cream background, deep-brown body text, Cloudflare orange accent, rounded cards with dashed crop marks.
| name | replicate | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| description | Search, explore, and run ML models on Replicate (image gen, video, audio, text, etc.) | |||||||||||||
| homepage | https://replicate.com | |||||||||||||
| metadata |
|
Run state-of-the-art open-source and proprietary ML models via the Replicate cloud API.
| name | openclaw-introspect |
|---|---|
| description | Explore, understand, and reconfigure your own OpenClaw gateway, agent harness, and system prompt. Use when you need to inspect or change OpenClaw configuration (openclaw.json), understand how the system prompt is built, debug session/channel/model issues, navigate the docs or source code, or tune agent defaults (models, thinking, sandbox, tools, heartbeat, compaction, channels, skills, plugins, cron, hooks). Also use for questions about OpenClaw architecture, the agent loop, context window, or how any OpenClaw feature works internally. |
Explore and reconfigure your own harness. This skill gives you structured knowledge about the OpenClaw internals so you can inspect, debug, and tune the running gateway.
| #!/bin/bash | |
| # Update | |
| sudo apt-get update | |
| # Install tools | |
| sudo apt install nvidia-cuda-toolkit | |
| # Install cog | |
| sudo curl -o /usr/local/bin/cog -L "https://github.com/replicate/cog/releases/latest/download/cog_$(uname -s)_$(uname -m)" | |
| sudo chmod +x /usr/local/bin/cog |