Real Skill packageSource verifiedClawHub registry

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", "m…

Identity and source

Publisher attributionhuaweicloudskillregistry owner unverified by skillvetai
Functional categorySoftware Developmentautomatically inferred · 58% rule confidence
Package forminstruction with code26 recorded files
Canonical sourceClawHub registryclawhub:huaweicloudskill:huawei-cloud-msmodelslim-model-adapt
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codeissues found
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/23/2026.claude/skills/huawei-cloud-msmodelslim-model-adapt
1 structural issue
  • error: compatibility must be a string of at most 500 characters. SKILL.md

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexissues found
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/23/2026.agents/skills/huawei-cloud-msmodelslim-model-adapt
2 structural issues
  • error: compatibility must be a string of at most 500 characters. SKILL.md
  • warning: Codex portability follows Agent Skills, where allowed-tools is a space-separated string. SKILL.md

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawissues found
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 9/23/2026skills/huawei-cloud-msmodelslim-model-adapt
2 structural issues
  • error: compatibility must be a string of at most 500 characters. SKILL.md
  • warning: OpenClaw portability follows Agent Skills, where allowed-tools is a space-separated string. SKILL.md

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @huaweicloudskill/huawei-cloud-msmodelslim-model-adapt
clawhub inspect @huaweicloudskill/huawei-cloud-msmodelslim-model-adapt --version 1.0.1

Security evidence

SkillVetAI static result: high signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
26 / 26 inspected as text
Checked
9/23/2026, 1:28:05 PM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
highDynamic code or shell execution is presentreferences/implementation_guide.md:75 · confidence 78%eval(
1 High/Critical review queue entry
STATIC_DYNAMIC_CODE_EXECUTIONpending
Open human review queue →
4 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
1 dependency and API indicators
  • api: clawhub.ai
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
9/21/2026, 6:59:00 AM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:ee555a3f74f4c814b8d773ad6e09384c932ffa021b49a7225634bcf48d5d7526
Show up to 26 recorded paths
  • assets/model_adapter_template.py
  • assets/vlm_model_adapter_template.py
  • references/acceptance-criteria.md
  • references/core_workflow.md
  • references/implementation_guide.md
  • references/interface_checklist.md
  • references/interface_reference.md
  • references/llm/fallback_config.yaml
  • references/llm/w8a8_dynamic_full_model.yaml
  • references/llm/w8a8_static_full_model.yaml
  • references/model_analysis.md
  • references/moe_unpacked_adapter_example.py
  • references/moe_unpacked_module_example.py
  • references/registration_guide.md
  • references/troubleshooting.md
  • references/verification_guide.md
  • references/verification-method.md
  • references/vlm/fallback_config.yaml
  • references/vlm/w8a8_dynamic_full_model.yaml
  • references/vlm/w8a8_static_full_model.yaml
  • scripts/step1_generate_test_model.py
  • scripts/step2_run_quantization.py
  • scripts/step3_verify_weights.py
  • scripts/step4_verify_quant_description.py
  • skill-card.md
  • SKILL.md

Source changelog

- Added concise documentation and step-by-step workflow for creating basic Transformers model adapters for msModelSlim, including four-step verification. - Clarified supported/unsupported model types, target use cases (decoder-only LLM, VLM text backbones), and quantization workflows (W8A8, W4A16). - Included template usage instructions, required Python environment/prerequisites, and command examples. - Provided reference links for model analysis, implementation, registration, and verification guides. - Outlined troubleshooting resources and acceptance criteria for adapter integration and validation.