SKILLEMALL.ai
GitHub ↗ RU Sign in

AB huawei-cloud-cloudrobo-model-workflow

Model development orchestration Skill covering asset query, model training, inference deployment, and real-robot evaluation in any combination. Supports full end-to-end pipeline or partial stages (e.g., train+deploy only, deploy+eval only). When user requirements involve two or more stages, prefer this Skill over individual module Skills. Triggers include: "用XX机器人训练XX任务", "so101 插笔", "训练部署", "部署评测", "训练评测部署", "模型开发流程", "端到端训练", "训练推理评测", "只训练不评测", "训练完部署", "model workflow", "end-to-end training", "train and deploy", "deploy and eval".

ClawHub Agent Skills author: huaweicloud-skills-team v1.0.0 MIT-0 13 files body ≈ 6 792 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Model development orchestration Skill covering asset query, model training, inference deployment, and real-robot evaluation in any combination.

As a process B 65/100 · Nearly there — weak spots: result and completion, when it triggers, running it twice

ProcedureAI 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
A
90/100
safety, quality, tests
Safety 60%
94
Quality 40%
83
Run on models
none yet
Process rating
B
65/100
Nearly there
Progress reporting w 2
0
When it triggers w 12
20
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 6

✓ No critical or high findings

Medium and low: 6
  • low Secrets in code secret-high-entropy-token references/model-ext-metadata.md:139
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    > **Applicable condition**: Execute when the base model is OpenPI series (`Phys…ase`, `Phys…ase`). Skip for other models (e.g., LeRobot series).
    quoted
  • low Secrets in code secret-high-entropy-token references/openpi-rename-map.md:3
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    > **Applicable condition**: Execute this step when the base model is `Phys…ase` or `Phys…ase`. Skip for other models (e.g., LeRobot series).
    quoted
  • low Secrets in code secret-high-entropy-token references/pipeline-templates.md:12
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | User-specified OpenPI | `Phys…ase` | Requires mapping | Yes |
    table
  • low Secrets in code secret-high-entropy-token references/pipeline-templates.md:157
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    User input: "Train so101 pen insertion task with Phys…ase"
    quoted
  • low Secrets in code secret-high-entropy-token references/pipeline-templates.md:159
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    Stage 1 queries `Phys…ase`, extracts FFT algorithm info from its `actions`.
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:152
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    > **Applicable**: Execute when base model is `Phys…ase` or `Phys…ase`. Skip for other models.
    quoted

Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6792 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 65/100

  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 45 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 6792 tokens
  • 100Steps. 60 steps
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • low The response is described with custom markup (13 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 10 example trigger phrases
  • +3Description length 540: enough signal without eating the budget
  • +4Structure: 41 headings
  • +3Step-by-step instructions: 60 items
  • +4Has examples (22 code blocks)
  • +4Reference files are cited in the instructions (11 of 11)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

External checks

ClawHub: suspicious
This is a coherent CloudRobo workflow skill, but it needs review because it can change cloud resources, create robot credential bundles, and dispatch tasks to real robots with incomplete safety and credential-handling gates.
LLM: suspicious (high) · 10 Sept 2026