Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/huaweicloud/huaweicloud-skillsnpx agentmods add skills/huaweicloud/huaweicloud-skills/huawei-cloud-msmodelslim-model-adaptWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-msmodelslim-model-adapt)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-msmodelslim-model-adapt"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-msmodelslim-model-adapt/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-msmodelslim-model-adapt"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-msmodelslim-model-adapt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00176 | $0.01808 |
| Opus 5 | $0.00088 | $0.00904 |
| Sonnet 5 | $0.00035 | $0.00362 |
| Haiku 4.5 | $0.00018 | $0.00181 |
Grade A, and why
huawei-cloud-msmodelslim-model-adapt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud msModelSlim Model Adapter
Overview
This skill guides how to create basic adapters for new models to run W8A8/W4A16 quantization workflows in msModelSlim.
Architecture: Model Analysis -> Adapter Creation -> Registration -> Verification (4 Steps)
Related Skills:
huawei-cloud-msmodelslim-model-analysis- Model structure analysis before adapter implementationhuawei-cloud-ascend-profiler-db-explorer- Optional: Performance analysis after deployment
Scope
Supported:
- Decoder-only LLM
- Understanding VLM (text/LLM backbone only)
Not supported:
- Multimodal generation (Stable Diffusion/Flux/Wan)
- Encoder-only models
- Non-Transformers architectures
Architecture
┌─────────────────────────────────────────────────────────────┐
│ msModelSlim Model Adapter Skill │
├─────────────────────────────────────────────────────────────┤
│ ┌──────────────────┐ ┌──────────────────────────────┐ │
│ │ Model Analysis │───▶│ Adapter Creation │ │
│ │ - config.json │ │ - LLM Adapter Template │ │
│ │ - modeling_*.py│ │ - VLM Adapter Template │ │
│ └──────────────────┘ │ - Required Interfaces │ │
│ └──────────────────────────────┘ │
│ │ │
│ ▼ │
│ ┌──────────────────┐ │
│ │ Registration │ │
│ │ & Installation │ │
│ └──────────────────┘ │
│ │ │
│ ▼ │
│ ┌──────────────────────────────────────────────────────┐ │
│ │ Verification (4 Steps) │ │
│ │ 1. Generate Test Model → 2. Full Fallback Quant │ │
│ │ 3. Weight Verification → 4. Quant Description │ │
│ └──────────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────────┘
What ships with it
24 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/model_adapter_template.py 1.8 KB runs code
- assets/vlm_model_adapter_template.py 4.1 KB runs code
- references/acceptance-criteria.md 3.4 KB
- references/core_workflow.md 1023 B
- references/implementation_guide.md 9.3 KB
- references/interface_checklist.md 751 B
- references/interface_reference.md 2.9 KB
- references/llm/fallback_config.yaml 481 B
- references/llm/w8a8_dynamic_full_model.yaml 504 B
- references/llm/w8a8_static_full_model.yaml 504 B
- references/model_analysis.md 1.0 KB
- references/moe_unpacked_adapter_example.py 3.1 KB runs code
- references/moe_unpacked_module_example.py 3.3 KB runs code
- references/registration_guide.md 346 B
- references/troubleshooting.md 4.2 KB
- references/verification_guide.md 5.3 KB
- references/verification-method.md 4.0 KB
- references/vlm/fallback_config.yaml 570 B
- references/vlm/w8a8_dynamic_full_model.yaml 693 B
- references/vlm/w8a8_static_full_model.yaml 693 B
- scripts/step1_generate_test_model.py 3.6 KB runs code
- scripts/step2_run_quantization.py 2.7 KB runs code
- scripts/step3_verify_weights.py 2.1 KB runs code
- scripts/step4_verify_quant_description.py 5.8 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 208 lines · 176 tokens per session scan A f18a553fa409
huawei-cloud-msmodelslim-model-adapt is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (49 stars, last pushed yesterday), licensed MIT. It adds 176 tokens to every session and 1,808 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
optimize-for-gpu
GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS…
developing-genkit-python
Develop AI-powered applications using Genkit in Python. Use when the user asks about Genkit, AI agents, flows, or tools in Python, or when encountering Genkit errors, import issues, or API problems.
gptq
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.