Prompt LLM Sim — AI skill for Claude Code
Prompt: LLM Serving Simulation & Observability — extends k8s-ai-observability.
How to install Prompt LLM Sim
Installs to ~/.claude/skills/chrisadkin8-k8s-ai-observability-prompt-llm-sim/SKILL.md
mkdir -p ~/.claude/skills/chrisadkin8-k8s-ai-observability-prompt-llm-sim && curl -fsSL https://raw.githubusercontent.com/ChrisAdkin8/k8s-ai-observability/HEAD/prompts/prompt-llm-sim.md -o ~/.claude/skills/chrisadkin8-k8s-ai-observability-prompt-llm-sim/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Prompt LLM Sim does
Prompt: LLM Serving Simulation & Observability — extends `k8s-ai-observability`
⚠️ SHIPPED — this is a RECORD, not a specification
The work below landed in **0.1.0 / 0.2.0**: the LLM simulator, its profiles and the vLLM board. Nothing here is outstanding, and nothing here should be acted on.
⚠️ **Its `Background / Facts` section describes the code BEFORE this work landed, and is therefore stale by construction.** Those `file:line` citations were true on the date stated and
Alternatives in AI
- Inference Serving — ai-research-skills vLLM, SGLang, TensorRT-LLM, llama.cpp 5.4k ★
- Manifest — Real-time cost observability for OpenClaw agents — track tokens, costs, messages, and model usage 4.1k ★
- 09 Query Engine — Prompt 09: Get the QueryEngine (Core LLM Loop) Functional 2.3k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Agent Skills Deep Dive
A Python implementation of the Claude Agent Skills system — a sophisticated prompt-based meta-tool architectur
Sim Plugin Starccm
Use AI coding agents with STAR-CCM+ via sim-cli: simulation setup, solver runs, scene/result inspection, repla
Sim Plugin Dymola
Use AI coding agents with Dymola/Modelica via sim-cli: model compilation, simulation runs, result inspection,
Sim Plugin Ltspice
Use AI coding agents with LTspice via sim-cli: run circuits, inspect waveforms/logs, and produce replayable si
ML Production
Use when shipping ML models (classical or LLM) to production - quantization (torch.ao.quantization, AWQ/GPTQ/A
Vibe Coder MCP
Vibe-Coder-MCP server extends AI assistants with specialized software development tools.
Related Agents
Sim Steward
Use proactively on a /loop schedule to autonomously monitor, heal, and maintain the entire Rappterbook world s
Sim Engineer
Use to write or fix sim.js, the pure simulation logic for the Monty Hall problem (3-door and N-door), after SP
Sim Reviewer
Review the simulation layer of Monte Carlo studies: DGP truth, estimands,