SKILLEMALL.ai
RU Sign in

BC huawei-cloud-optv-evolve-management

Huawei Cloud algorithm auto-design (LLM4AD) skill. Performs the full lifecycle through KooCLI (command-line entry `hcloud`): algorithm project management, file upload, evolve task CRUD, status polling, result retrieval, and log inspection; also uses KooCLI's `hcloud IAM` subcommand to create the trust agency and grant algorithm design module bucket permissions. Trigger words: code evolution, evolve task, LLM4AD, algorithm optimization, upload algorithm file, create evolve task, start evolve task, fetch evolve result, evolve log, 代码演化, 演化任务, LLM4AD, code evolution, 算法优化, 上传算法文件, 创建演化任务, 启动演化任务, 拉取演化结果, 演化日志

ClawHub Agent Skills author: huaweicloud-skills-team v1.0.0 MIT-0 28 files · 2 scripts body ≈ 9 454 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Huawei Cloud algorithm auto-design (LLM4AD) skill.

As a process C 61/100 · Has gaps — weak spots: when it triggers, execution cost, progress reporting

ProcedureSoftware developmentAI 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
85/100
safety, quality, tests
Safety 60%
90
Quality 40%
78
Run on models
none yet
Process rating
C
61/100
Has gaps
Progress reporting w 2
0
When it triggers w 12
20
Execution cost w 6
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.

Dangerous commands 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 contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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
  • medium Dangerous commands cmd-privilege references/cli-installation-guide.md:22
    Privilege escalation / world-writable permissions
    sudo mv /tmp/hcloud /usr/local/bin/hcloud
  • low Secrets in code secret-high-entropy-token references/algorithm-workflow.md:43
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    --name="Algo…000" \
    quoted
  • low Secrets in code secret-high-entropy-token references/api-mapping.md:151
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | List attached policies | `hcloud IAM List…sV5` | GET |
    table
  • low Secrets in code secret-high-entropy-token references/troubleshooting.md:64
    High-entropy token-like string (may be an id, hash or a credential)
    hcloud IAM List…sV5 \
  • low Secrets in code secret-high-entropy-token references/verification-method.md:64
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - [ ] (upload scenario) Custom policy `poli…4ad` is attached to the agency (`List…sV5`)
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:307
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    --name="Algo…000" --lang="c++" --description="…" \
    quoted

Files scanned: 28. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 9454 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 61/100

  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Execution cost. Instruction body is 9454 tokens: crowds the task out of the window
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 62 steps, 3 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 top-level sections: this looks like several domains in one skill
  • 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -213 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 614: enough signal without eating the budget
  • +4Structure: 49 headings
  • +3Step-by-step instructions: 62 items
  • +3Output format is stated explicitly
  • +4Has examples (13 code blocks)
  • +4Reference files are cited in the instructions (16 of 16)
  • +3All 5 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.

External checks

ClawHub: suspicious
The skill has a clear Huawei Cloud OptVerse purpose, but it includes overbroad persistent cloud delegation and unsafe credential/state guidance that users should review before installing.
LLM: suspicious (high) · 9 Sept 2026