llm-benchmark SKILL.md skillB
llm-benchmark from kerberosclaw/kc_ai_skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kerberosclaw/kc_ai_skills/llm-benchmark@v1.1.0Pins v1.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kerberosclaw/kc_ai_skills
- Path
llm-benchmark/SKILL.md- Versions recorded
- 5
- Latest version
- v1.1.0, committed Jul 30, 2026
- First version recorded
- Mar 18, 2026
- Size
- 7,010 bytes
- Repository stars
- 79
- License
- MIT
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.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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
…Read the whole file at its exact version.
How to install
mdr add kerberosclaw/kc_ai_skills/llm-benchmark@sha256:2fa1a6b9e496179bThe line at the top of this page pins the label v1.1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_yde2a22n22tlev7t)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Mar 18, 2026 and Jul 30, 2026, about one every 33 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1.0 latest | 2026-07-30 | d4fda1a | 7,010 B | B | view · diff |
| v1.0.1 | 2026-07-15 | 38420bb | 6,346 B | B | view · diff |
| v1.0.0 | 2026-07-14 | 7facb13 | 5,833 B | B | view · diff |
| v1.0.0 | 2026-07-14 | a933fb9 | 5,633 B | B | view · diff |
| v1.0.0 | 2026-03-18 | e5617a3 | 5,504 B | B | view |
Audit of the latest version
- fail: No curl or wget piped into a shell (matched: curl -fsSL https://ollama.com/install.sh | sh)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7010 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
kerberosclaw/kc_ai_skills · 79 stars · license MIT · pushed 2026-10-16 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_yde2a22n22tlev7t GET https://markdownregistry.com/api/v1/resolve?ref=kerberosclaw/kc_ai_skills/llm-benchmark GET https://markdownregistry.com/api/v1/blob/2fa1a6b9e496179bc654b31658de5f8af3e775d9741d7b6f4bbf145d386d1af6
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.