SKILLEMALL.ai
GitHub ↗ RU Sign in

BD IMA Studio Image Generation

Use for AI image generation via IMA Open API. Supports text-to-image and image-to-image. IMPORTANT — Default model selection rule: always recommend the NEWEST and most POPULAR model, NOT the cheapest. Default for text_to_image: SeeDream 4.5 (doubao-seedream-4.5, 5pts) — latest doubao flagship, balanced choice. Budget option: Nano Banana2 (gemini-3.1-flash-image, 4pts) — fastest and cheapest. Premium: Nano Banana Pro (gemini-3-pro-image, 10-18pts) — premium quality with size options (1K/2K/4K). NEW: Midjourney (midjourney, 8-10pts) — artist-level aesthetics. Default for image_to_image: SeeDream 4.5 (doubao-seedream-4.5, 5pts, attribute_id 1611). Production environment has 4 available models. All text_to_image models (4): SeeDream 4.5 (5pts), Nano Banana2 (4pts), Nano Banana Pro (10/10/18pts for 1K/2K/4K), Midjourney (8-10pts for 480p/720p). All image_to_image models (4): SeeDream 4.5 (5pts), Nano Banana2 (4pts), Nano Banana Pro (10pts), Midjourney (8-10pts). Requires an ima_* API key.

modbender/skill-library-mcp Claude Code author: modbender MIT 9 files body ≈ 13 783 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Use for AI image generation via IMA Open API.

As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

GeneratorDiscordAI and agentsSoftware developmentWriting and documentstype 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
77/100
safety, quality, tests
Safety 60%
85
Quality 40%
66
Run on models
none yet
Process rating
D
41/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
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.

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. 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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Dangerous commands cmd-shell-rc INSTALL.md:42
    Writes to a shell startup file
    echo 'export IMA_API_KEY=ima_your_key_here' >> ~/.bashrc
  • medium Dangerous commands cmd-shell-rc INSTALL.md:335
    Writes to a shell startup file
    echo 'export IMA_API_KEY=ima_your_key_here' >> ~/.bashrc
  • medium Exfiltration net-redirectable-api-key scripts/ima_image_create.py:960
    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

Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning body-long SKILL.md body ≈ 13783 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "keywords"

Process rating: all ten parameters 41/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 48 mutating operations with no state check
  • 40Consistency. Frontmatter name (IMA Studio Image Generation) differs from the folder (ima-image-ai)
  • 40Execution cost. Instruction body is 13783 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
  • 60Steps. 129 steps, 5 vague phrases
  • 100Failures and branches. 3 branches, has a failure section
  • 100Progress reporting. Reports progress
  • 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 998: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -294 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +4Structure: 42 headings
  • +3Step-by-step instructions: 129 items
  • +4Has examples (36 code blocks)
  • +3All 2 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.