SKILLEMALL.ai
GitHub ↗ RU Sign in

BC ernie-image-radeon

FREE ERNIE-Image text-to-image generation powered by AMD Radeon Cloud. No API key required. Generate AI images via ERNIE-Image and ERNIE-Image-Turbo models running on AMD Radeon hardware. 中文：支持文生图、AI绘图、图片生成、 免费生图、批量生图、AI画画、文本生成图片。English: free text-to-image, AI art generation, create image, generate image, AMD Radeon, Radeon Cloud image generation, AI picture, image creator. 7 sizes (square/landscape/portrait), batch generation (1-4 images), seed control, inference steps, guidance scale, prompt enhancement. Chinese prompts excel — specializes in Chinese ink wash painting, cyberpunk, oil painting, watercolor, photorealistic styles. Triggers: 文生图, 免费生图, AI绘图, 生成图片, ERNIE生图, AMD生图, Radeon生图, ernie image, radeon image, free image generation, generate image, create image, AI art, text-to-image, image generation, make a picture, draw, AI画图, 画画, 出图.

ClawHub Agent Skills author: AIwork4me v1.0.1 MIT-0 4 files body ≈ 1 395 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 63/100 · Has gaps — weak spots: result and completion, running it twice, progress reporting

GeneratorAI and agentsInfrastructuretype 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
87/100
safety, quality, tests
Safety 60%
94
Quality 40%
76
Run on models
none yet
Process rating
C
63/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
Running it twice w 4
30
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Exfiltration net-redirectable-api-key scripts/generate.py:205
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • low Dangerous commands cmd-pipe-to-shell-known-host references/api-guide.md:182
    Pipe-to-shell installer from a well-known host (still executes remote code) (detector / deny-list definition; documentation table row)
    | `uv run` fails | uv not installed or Python < 3.11 | Install uv: `curl -LsSf https://astral.sh/uv/install.sh \| sh` |
    detectortable

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 63/100

  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 1 mutating operations with no state check
  • 55Failures and branches. 1 branches
  • 60Tools and files. Uses tools (python) 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
  • 100Steps. 19 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1395 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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)
  • +3Description length 854: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 19 items
  • +4Has examples (6 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.

External checks

ClawHub: clean
This is a disclosed image-generation skill that sends prompts to an external ERNIE/Radeon endpoint and saves generated images locally, with clear warnings about sensitive prompts.
LLM: benign (high) · VirusTotal: · 29 May 2026