Real Skill packageSource verifiedClawHub registry

huawei-cloud-cloudrobo-model-adapt-workflow

One-stop workflow for adapting models on the CloudRobo platform. Chains 4 sub-skills: huawei-cloud-cloudrobo-npu-patcher (PyTorch VLA → Ascend NPU adaptation), huawei-cloud-cloudrobo-weight-layout (standard checkpoint layout), huawei-cloud-cloudrobo-train-metrics (Octopus training metric reporting), and huawei-cloud-cloudrobo-inference-adapter (target-protocol inference interface adaptation), covering the full pipeline of "model code → trainable on NPU → weights produced in standard layout → platform metric visual…

Identity and source

Publisher attributionhuaweicloudskillregistry owner unverified by skillvetai
Functional categoryData, Spreadsheets & Analyticsautomatically inferred · 59% rule confidence
Package forminstruction with code30 recorded files
Canonical sourceClawHub registryclawhub:huaweicloudskill:huawei-cloud-cloudrobo-model-adapt-workflow
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 · 11/5/2026.claude/skills/huawei-cloud-cloudrobo-model-adapt-workflow
1 structural issue
  • error: description exceeds the 1,024-character Agent Skills limit. 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 · 11/5/2026.agents/skills/huawei-cloud-cloudrobo-model-adapt-workflow
1 structural issue
  • error: description exceeds the 1,024-character Agent Skills limit. 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 · 11/5/2026skills/huawei-cloud-cloudrobo-model-adapt-workflow
1 structural issue
  • error: description exceeds the 1,024-character Agent Skills limit. 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-cloudrobo-model-adapt-workflow
clawhub inspect @huaweicloudskill/huawei-cloud-cloudrobo-model-adapt-workflow --version 1.0.0

Security evidence

SkillVetAI static result: no findings detected

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
30 / 30 inspected as text
Checked
11/5/2026, 8:01:08 PM
Scanner
0.1.3
Policy
1.0.3
4 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
2 dependency and API indicators
  • api: clawhub.ai
  • api: www.hiascend.com
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
11/5/2026, 9:44:50 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:aeab5f70e828feb1ad5f3f320123a99e39fc30a04ccf476699637a546c7cb986
Show up to 30 recorded paths
  • references/acceptance-criteria.md
  • references/iam-policies.md
  • references/verification-method.md
  • scripts/checks/__init__.py
  • scripts/checks/build.py
  • scripts/checks/common.py
  • scripts/checks/dataload.py
  • scripts/checks/pipeline.py
  • scripts/checks/runtime.py
  • scripts/config.py
  • scripts/patterns.py
  • scripts/progress.py
  • scripts/runtime_patches.py
  • scripts/scan.py
  • scripts/scanners/__init__.py
  • scripts/scanners/device.py
  • scripts/scanners/framework.py
  • scripts/scanners/helpers.py
  • scripts/scanners/operator.py
  • scripts/scanners/semantic.py
  • scripts/scanners/structure.py
  • scripts/test_client.py
  • scripts/utils.py
  • scripts/verify_adapter.py
  • scripts/verify.py
  • skill-card.md
  • SKILL.md
  • templates/migrate_to_cloudrobo/env_npu.sh
  • templates/migrate_to_cloudrobo/runtime_patches.py
  • templates/migrate_to_cloudrobo/train.sh

Source changelog

Introduces a unified end-to-end CloudRobo model adaptation workflow. - Chains NPU adaptation, standard checkpoint layout, training metric reporting, and inference protocol adaptation. - Adds input confirmation, prerequisites, and gates between workflow stages. - Separates code verification from training; training starts only after NPU adaptation and training-side setup pass. - Carries training outputs into inference adaptation and a unified workflow summary.