LLM Benchmark

Use when the user wants to test, compare, or choose local Ollama models for their machine. Checks Ollama/GPU state, recommends model sizes from available VRAM, preserves existing benchmark records, pulls only approved models, runs repeatable benchmarks, restores stopped services, and writes a markdown comparison report. NOT for hosted API model evaluation or subjective chat-quality judging without local benchmark commands.

80 stars 13 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add KerberosClaw/kc_ai_skills --skill llm-benchmark
Manual install
git clone --depth 1 https://github.com/KerberosClaw/kc_ai_skills.git /tmp/kc_ai_skills
mkdir -p ~/.claude/skills
cp -r /tmp/kc_ai_skills/llm-benchmark ~/.claude/skills/llm-benchmark

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

From the SKILL.md

# LLM Benchmark Skill

You are a local LLM benchmarking specialist. 你負責用可重現的命令測 Ollama 模型效能,保護使用者現有服務狀態,並把推薦和限制講清楚。

## 不適用

- 不評測雲端 API 模型。
- 不用單次主觀聊天感覺取代 benchmark。
- 不在未確認硬體與服務狀態前直接 pull 大模型或重啟服務。

執行以下完整流程:

## Step 0:環境檢查

```bash
# 確認 Ollama 是否安裝並運行
curl -s http://localhost:11434/api/version 2>/dev/null || echo "NOT_RUNNING"
which ollama 2>/dev/null || echo "NOT_INSTALLED"
```

- 若 **未安裝**:執行 `curl -fsSL https://ollama.com/install.sh | sh`,再啟動服務
- 若 **未運行**:執行 `ollama serve &` 或 `systemctl start ollama`
- 確認成功後繼續

## Step 0.5:VRAM 清空(benchmark 前必做)

### 1. 停止其他吃 GPU / RAM 的本地 LLM 服務(若有且正在運行)

```bash
# 檢查是否有 LLM gateway 類容器正在運行(例:OpenClaw、LM 代理服務)
LLM_GATEWAY="your-llm-gateway"   # 換成你的服務名,例:openclaw
docker ps --format '{{.Names}}' | grep -i "$LLM_GATEWAY"
```

- 若有相關容器正在運行 → 停止它:
  ```bash
  LLM_STACK_DIR="$HOME/your-llm-stack"   # 換成你的 compose 目錄
  GATEWAY_SERVICE="gateway"              # 換成你的服務名
  cd "$LLM_STACK_DIR" && docker compose stop "$GATEWAY_SERVICE"
  ```
- 若無相關容器,或容器已停止 → 跳過此步驟

記錄該服務是否原本是啟動的,**benchmark 完成後需還原狀態**。

### 2. 重啟 Ollama 清除 VRAM(必做)

```bash
sudo systemctl restart ollama
sleep 5
```

### 3. 確認 VRAM 已釋放

```bash
nvidia-smi --query-gpu=memory.used,memory.free --format=csv,noheader,nounits
```

確認 `memory.used` 降到 ~1500 MB 以下再繼續。若仍偏高,再等 5 秒重確認。

### 4. Benchmark 完成後還原服務

若步驟 1 有停止服務,benchmark 全部完成後執行:
```bash
cd "$LLM_STACK_DIR" && docker compose start "$GATEWAY_SERVICE"
```

---

## Step 1:取得 GPU/VRAM 資訊
Read the full skill on GitHub

Details

Skill name
llm-benchmark
Path
llm-benchmark/SKILL.md
License
MIT
Repo updated
14 November 2026

FAQ

What does the LLM Benchmark skill do?

Use when the user wants to test, compare, or choose local Ollama models for their machine. Checks Ollama/GPU state, recommends model sizes from available VRAM, preserves existing benchmark records, pulls only approved models, runs repeatable benchmarks, restores stopped services, and writes a markdown comparison report. NOT for hosted API model evaluation or subjective chat-quality judging without local benchmark commands.

How do I install the LLM Benchmark skill?

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

Is LLM Benchmark popular?

It lives in KerberosClaw/kc_ai_skills, which has 80 GitHub stars and 13 forks, and is included in 1 curated skill list.

Related skills

Adr

80

KerberosClaw/kc_ai_skills

Use when a durable technical decision was just made in conversation and should be recorded, or when user asks to write/record an ADR (開 ADR / 記個決策 / 這要不要 ADR). Runs a three-gate check FIRST and actively talks the user out of writing one when the decision doesn't qualify — then writes a lightweight (title + 1-3 sentences) ADR following the repo's own ADR conventions if any exist. Repo conventions always override this skill's defaults. NOT for requirement specs (spec / prd-create) or rewriting historical decisions; preserve their text, allow evidence-backed current-state notes, and record change

Writing & ContentIn 1 list13

Align

80

KerberosClaw/kc_ai_skills

Reconcile existing repository documentation with the current implementation, especially after verified hotfixes or after QA in an unattended task. A manual run first asks whether to align only the docs a specific change touched (trigger scope) or rescan the whole repo; unattended runs use the scope the dispatch states and default to the whole repo. Follow cross-repo references for evidence; edit only documentation in the authorized repo, annotating conflicting historical records. Not for fixing code, deploying, inventing requirements, or building a new documentation suite.

Writing & ContentIn 1 list13

Character Lora

80

KerberosClaw/kc_ai_skills

Use when the user wants to build a consistent-identity LoRA for an original character — defining the character, generating a face/body-consistent multi-angle dataset (via the gpt-image-gen skill for codex image generation), captioning it, doing base-specific homework, training on a chosen base (Pony / Z-Image / others) on a local GPU, and producing a usable LoRA. This skill ORCHESTRATES the end-to-end pipeline and gates every expensive/irreversible step; it delegates actual image generation to gpt-image-gen and never improvises training settings from memory.

Images, Video & AudioIn 1 list13

LLM Wiki Lint

80

KerberosClaw/kc_ai_skills

Use when the user wants to lint a repo following the Karpathy LLM Wiki pattern (raw/ + wiki/ + SCHEMA.md / index.md / log.md). The skill detects path, scans wiki pages + schema layer, reports frontmatter gaps, broken in-body links, source traceability breaks, stale claims, orphan pages, index synopsis contradictions, and SCHEMA-vs-reality drift. Phase 1 is read-only report; Phase 2 (fix + log.md LINT entry) only runs after the user explicitly approves.

AI, LLMs & AgentsIn 1 list13

H3

46

heavy3-ai/code-audit

Heavy3 Code Audit - Multi-model code review for coding agents (Sponsored by Heavy3.ai)

AI, LLMs & Agents15

Skill Check

45

olgasafonova/SkillCheck-Free

Validate Claude Code skills against Anthropic guidelines. Use when user says "check skill", "skillcheck", "validate SKILL.md", or asks to find issues in skill definitions. Covers structural and semantic validation. Do NOT use for anti-slop detection, security scanning, token analysis, enterprise checks, or Eval Kit generation; use skill-check-pro for those. Do NOT use for LinkedIn skill engagement; use skillcheck-engage for that.

AI, LLMs & AgentsIn 1 list

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