Keldron Agent

GPU monitoring with risk intelligence. Local + cloud fleet monitoring, health tracking, proactive alerts, and AI-powered fleet analytics.

6 starsAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add keldron-ai/keldron-agent --skill keldron-agent

Manual install

git clone --depth 1 https://github.com/keldron-ai/keldron-agent.git /tmp/keldron-agent
mkdir -p ~/.claude/skills
cp -r /tmp/keldron-agent/. ~/.claude/skills/keldron-agent

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Keldron Agent — GPU Monitoring with Risk Intelligence

## 1. Overview

Keldron Agent is a vendor-neutral GPU monitoring agent that runs locally and exposes real-time telemetry and risk scores via a Prometheus endpoint. It supports Apple Silicon (M1–M5), NVIDIA consumer GPUs (RTX 3090/4090/5090), NVIDIA datacenter (H100/B200), AMD GPUs, and any Linux machine.

**Dual mode:** Use the **local agent** on `localhost:9100` for fast, real-time, single-device queries (works offline). Use **Keldron Cloud** (`https://api.keldron.ai`) for fleet overview, historical telemetry, analytics, and proactive fleet monitoring when an API key is configured.

**No sudo required on any platform** for the agent binary. On Linux, Docker may require `sudo` or membership in the `docker` group — see [Docker post-install](https://docs.docker.com/engine/install/linux-postinstall/) or rootless Docker if you hit permission errors.

Use this skill when the user wants to:

- Monitor GPU temperature, power, utilization, or memory
- Get risk assessments for their GPU
- Track power costs
- Set up alerts or watch a fleet (via cloud polling)
- Open the real dashboard (local or cloud)
- Ask fleet, history, or analytics questions

### Mode detection (run at the start of an interaction)

Field names **differ by endpoint** — see [Cloud API field names](#cloud-api-field-names-jq-reference) before writing `jq` filters.

Read the full skill on GitHub

Details

Skill name: keldron-agent
Repository: keldron-ai/keldron-agent
License: Apache-2.0
Repo updated: 6 April 2026

FAQ

What does the Keldron Agent skill do?

GPU monitoring with risk intelligence. Local + cloud fleet monitoring, health tracking, proactive alerts, and AI-powered fleet analytics.

How do I install the Keldron Agent skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add keldron-ai/keldron-agent --skill keldron-agent. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Keldron Agent popular?

It lives in keldron-ai/keldron-agent, which has 6 GitHub stars and 0 forks.

Related skills

Life Role Inventory

gala-rong/life-role-inventory

生涯與生活角色盤點——用結構化訪談清點你正在扮演的所有角色（工作只是其中之一：父母、伴侶、朋友、興趣、信仰都算），收斂成一張可驗證的現況地圖與錨點句，並可延伸為 AI 協作分工建議。當使用者說「盤點我的角色」「生涯盤點」「人生盤點」「生活盤點」「幫我整理最近生活的各條線」「我該聚焦什麼」「深度訪談我」時使用（無論第幾次，一律跑同一套單次流程）。純方法論 skill：不含任何受訪者個人資料；訪談內容一律寫在受訪者自管的筆記檔，不進入任何記憶或其他 skill。多檔結構：口語技巧庫、判例集、製作參考收於 references/，依檔案地圖按需載入。

AI, LLMs & Agents

Imp

Arabianaischool/prompt-action

Improve and enhance any prompt or request before executing it. Use this skill whenever the user's message starts with "/imp" or when the user asks to "improve my prompt", "enhance this request", "optimize this prompt", or wants Claude to apply prompt engineering techniques before executing a task. The skill rewrites the user's raw request using best practices (clarity, XML structure, examples, context, role-setting), then executes the improved prompt and shows both the improved version and the result.

AI, LLMs & Agents

Logseq Outline

kerim/logseq-outline-skill

Format any content as a Logseq-compatible outline using nested bullets (no markdown headers, no bold). Works in both Claude Code and Claude Desktop.

AI, LLMs & Agents

Humanizer Ko

IsaacEryn/humanizer-ko

한국어 텍스트에서 AI 생성 글의 티를 찾아 제거한다. 글을 자연스러운 사람의 문장으로 다듬거나 검토할 때 사용. Remove signs of AI-generated writing from Korean text (humanize Korean text). 의의 부풀리기, 홍보성 언어, 연결어미 부가절, AI 어휘, 이중 피동, 번역투, 문체 혼용, 대구 연쇄, 결산 공식, 연결어미 뒤 쉼표, 줄표 남용, 상투적 마무리 등 37개 패턴을 탐지하고 고친다. 논문 초록 과적재·단서 누적·삼중 요약 같은 학술 원고 티와 발표 대본 티는 장르 참고 파일로 따로 본다.

AI, LLMs & Agents

Minimax H3 Prompt

kuronzzhan-droid/minimax-h3-prompt-skill

按 MiniMax-H3 的两种有效格式撰写视频生成提示词（时间轴风格 / 官方结构化风格），覆盖 T2VA 文生视频、I2VA·FL2VA·L2VA 首尾帧、full-reference 参考生视频 R2V。只要用户想用本地 ComfyUI 的 H3 出视频、要求写或改 H3 提示词、提到 MiniMax H3 / ref2va / fl2va、给参考图或音色让角色说话唱歌、或抱怨 H3 出片"角色不像/台词乱语/声音不对/动作没跟上节拍"，都应使用本技能——它带官方规范原文、两种风格的实战范例和本机显存实测约束。

AI, LLMs & Agents

Hubspot AI Context

chadstamm/claude-skill-hubspot-ai-context

Fill HubSpot's AI Context page (Business tab + Customers tab — ICPs and Personas) by crawling a client website, researching competitors and brand reputation (positive + negative), and generating click-to-copy paste-sheet HTML. Use when setting up a new client in HubSpot's AI/Breeze Intelligence layer or when refreshing existing context. Triggers — "fill out AI context", "set up HubSpot ICPs", "create paste sheet for [client]", "generate Breeze Intelligence context", "research competitors for [client]".

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.