BC huawei-cloud-ascend-models-deploy
Huawei Cloud Ascend model deployment and testing skill for large language models on Ascend DevServer (910B series). Supports single-machine and dual-machine deployment for LLM, VL (vision-language), Embedding, and Rerank models. Provides model inference testing, deployment log viewing, and status monitoring with automated model matching and deployment script generation. Use this skill when the user wants to: (1) deploy a model on Ascend DevServer, (2) test model inference, (3) view deployment logs or status, (4) list supported models, (5) check deployment prerequisites. Trigger: deploy, test, model list, deployment log, Ascend, DevServer, 910B, ModelArts, LLM, VL, Embedding, Rerank, multimodal, inference, model catalog, 昇腾, 部署模型, 测试模型, 模型列表, 部署日志, 模型部署, 推理测试
Huawei Cloud Ascend model deployment and testing skill for large language models on Ascend DevServer (910B series).
As a process C 60/100 · Has gaps — weak spots: result and completion, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 13
✓ No critical or high findings
Medium and low: 13
-
low Secrets in code
secret-high-entropy-tokenreferences/model-catalog.md:12High-entropy token-like string (may be an id, hash or a credential)| Qwen…507 | 16 | /v1/chat/completions |
-
low Secrets in code
secret-high-entropy-tokenreferences/model-catalog.md:13High-entropy token-like string (may be an id, hash or a credential)| Qwen…507 | 16 | /v1/chat/completions |
-
low Secrets in code
secret-high-entropy-tokenreferences/model-catalog.md:14High-entropy token-like string (may be an id, hash or a credential)| Deep…70B | 4 | /v1/chat/completions |
-
low Secrets in code
secret-high-entropy-tokenreferences/model-catalog.md:23High-entropy token-like string (may be an id, hash or a credential)| Qwen…8A8 | 8 | Yes |
-
low Secrets in code
secret-high-entropy-tokenscripts/deploy_helper.py:40High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"Qwen…507": {quoted -
low Secrets in code
secret-high-entropy-tokenscripts/deploy_helper.py:46High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"Qwen…507": {quoted -
low Secrets in code
secret-high-entropy-tokenscripts/deploy_helper.py:52High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"Deep…70B": {quoted -
low Secrets in code
secret-high-entropy-tokenscripts/deploy_helper.py:84High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"Qwen…8A8": {quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:166High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)- "qwen3-235b" → Multiple matches, prefer Instruct version (Qwen…507), or ask user
detector -
low Secrets in code
secret-high-entropy-tokenSKILL.md:248High-entropy token-like string (may be an id, hash or a credential)| Qwen…507 | 16 |
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:249High-entropy token-like string (may be an id, hash or a credential)| Qwen…507 | 16 |
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:250High-entropy token-like string (may be an id, hash or a credential)| Deep…70B | 4 |
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:258High-entropy token-like string (may be an id, hash or a credential)| Qwen…8A8 | 8 |
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7021 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 89 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7021 tokens
- 85Steps. 86 steps, 3 vague phrases
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
- low The response is described with custom markup (5 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 768: enough signal without eating the budget
- +4Structure: 46 headings
- +3Step-by-step instructions: 86 items
- +4Has examples (22 code blocks)
- +4Reference files are cited in the instructions (7 of 8)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.