SKILLEMALL.ai
GitHub ↗ RU Sign in

BB huawei-cloud-msmodelslim-model-adapt

Create basic Transformers model adapters for msModelSlim. Implements required interfaces and completes a four-step verification workflow: generate test model -> full fallback quantization -> weight verification -> quantization description validation. Use this skill when the user wants to: (1) create msModelSlim adapters for decoder-only LLM, (2) adapt understanding VLM text backbones for quantization, (3) implement W8A8/W4A16 quantization workflow for new models. Trigger: user mentions "msModelSlim", "adapter", "model adapter","quantization", "W8A8","W4A16", "transformers", "LLM", "VLM", "adapter creation", "适配器","模型适配", "量化", "模型适配器", "LLM量化"

ClawHub Agent Skills author: huaweicloud-skills-team v1.0.0 MIT-0 26 files body ≈ 1 698 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Create basic Transformers model adapters for msModelSlim.

As a process B 75/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting

GeneratorAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
88/100
safety, quality, tests
Safety 60%
82
Quality 40%
96
Run on models
none yet
Process rating
B
75/100
Nearly there
Progress reporting w 2
0
Running it twice w 4
30
Result and completion w 14
40
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 14

    ✓ No critical or high findings

    Medium and low: 14
    • medium Broad scope meta-broad-allowed-tools SKILL.md:1
      Broad tool permissions pre-approved: bash
      allowed-tools: python3 bash
    • low Secrets in code secret-high-entropy-token assets/model_adapter_template.py:21
      High-entropy token-like string (may be an id, hash or a credential)
      Mode…eV1
    • low Secrets in code secret-high-entropy-token assets/model_adapter_template.py:29
      High-entropy token-like string (may be an id, hash or a credential)
      Mode…eV1):
    • low Secrets in code secret-high-entropy-token assets/model_adapter_template.py:38
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      # ==================== Mode…eV1 ====================
      detector
    • low Secrets in code secret-high-entropy-token assets/vlm_model_adapter_template.py:19
      High-entropy token-like string (may be an id, hash or a credential)
      from msmodelslim.model.interface_hub import Mode…eV1
    • low Secrets in code secret-high-entropy-token assets/vlm_model_adapter_template.py:29
      High-entropy token-like string (may be an id, hash or a credential)
      Mode…eV1,
    • low Secrets in code secret-high-entropy-token assets/vlm_model_adapter_template.py:44
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      # ==================== Mode…eV1 ====================
      detector
    • low Secrets in code secret-high-entropy-token references/acceptance-criteria.md:44
      High-entropy token-like string (may be an id, hash or a credential)
      class MyModelAdapter(TransformersModel, Mode…eV1):
    • low Secrets in code secret-high-entropy-token references/implementation_guide.md:34
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - **pushrecommendcontinueadmit**: `TransformersModel + Mode…eV1` (`ModelInfoInterface` canselectbutSuggest)
      quoted
    • low Secrets in code secret-high-entropy-token references/implementation_guide.md:40
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - **pushrecommendcontinueadmit**: `VLMBaseModelAdapter + Mode…eV1` (`ModelInfoInterface` canselectbutSuggest)
      quoted
    • low Secrets in code secret-high-entropy-token references/interface_reference.md:29
      High-entropy token-like string (may be an id, hash or a credential)
      ## 2) Mode…eV1 (mustneed)
    • low Secrets in code secret-high-entropy-token references/interface_reference.md:76
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - oughtInterfacethroughoftenand `TransformersModel + Mode…eV1` groupmatchUsage.
      quoted
    • low Secrets in code secret-high-entropy-token references/interface_reference.md:86
      High-entropy token-like string (may be an id, hash or a credential)
      Mode…eV1):
    • low Secrets in code secret-high-entropy-token references/interface_reference.md:90
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      ifwhenpreviousScenariosnotrequiresModelinformationinformationabilityforce, cansavestrategy `ModelInfoInterface`, but `Mode…eV1` notcansavestrategy.
      quoted

    Files scanned: 26. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 75/100

    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 6 mutating operations with no state check
    • 40Result and completion. Does not say what the result is
    • 50Failures and branches. 0 branches, has a failure section
    • 70When it triggers. States when to use, but not when not to
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 47 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1698 tokens
    • low 12 top-level sections: this looks like several domains in one skill
    • low The response is described with custom markup (3 tags): a typed call is more reliable

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 6 example trigger phrases
    • +3Description length 651: enough signal without eating the budget
    • +4Structure: 19 headings
    • +3Step-by-step instructions: 47 items
    • +4Has examples (3 code blocks)
    • +4Reference files are cited in the instructions (8 of 10)
    • +3All 4 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.

    External checks

    ClawHub: suspicious
    This skill is mostly a coherent msModelSlim adapter workflow, but it normalizes unsafe model loading that can run code from model artifacts without clear warnings or opt-in.
    LLM: suspicious (high) · 21 Jul 2026