Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lingtai-ai/vision
Nested swiss-knife reference for image understanding — a decision tree that routes between three paths depending on what the agent has access to: (1) the built-in `vision` tool if the LLM provider supports image input, (2) the sibling `minimax-cli` reference if a usable MiniMax preset/key slot is available, or (3) a local Hugging Face VLM via the bundled `scripts/describe.py` if neither — offline, free, slow. Read this when you need to describe, OCR, or critique an image and you're not sure whic
Passed 13 of 17 test cases with the skill, and 2 of 17 without it.
and 11 more in the full report
14 fixed3 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
You are running on a text-only LLM model and need to quickly analyze `./photo.jpg` in a single bash command using an installed MiniMax CLI. What command pattern should be executed?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies executing mmx vision from the shell | Missed | Passed |
The instructions your model reads when the skill loads.
Nested swiss-knife reference for image understanding. Three paths — pick the cheapest available.
Is `vision` tool in your tool list?
├── YES → use it directly, done.
└── NO → does the user have a MiniMax preset/key slot?
(read the sibling `../minimax-cli/SKILL.md`; scan ~/.lingtai-tui/presets/** without printing keys)
├── YES → use the `minimax-cli` reference for `mmx vision …` from the shell, or an already-registered MCP tool
└── NO → fall back to local VLM:
python3 <skill-path>/scripts/describe.py <image>
See reference/local-models.md.
vision ToolIf your LLM provider supports image input (MiniMax, Gemini, Anthropic, OpenAI, Zhipu), the kernel exposes a vision tool directly. Cheapest, lowest latency, no extra setup.
vision not in your tool list? Your LLM provider doesn't support image input — fall through to Path 2 or 3.
minimax-cli referenceFor text-only LLMs (DeepSeek, OpenRouter text-only, Codex) with a usable MiniMax preset/key slot. Two routes can exist:
mmx vision … via the official CLI. No MCP registration needed; just install + key. Best for ad-hoc one-shots in bash.mcp-manual (kernel mcp capability).Read the sibling minimax-cli reference (../minimax-cli/SKILL.md) before using the shell route. It owns the canonical MiniMax credential discovery flow: scan TUI presets recursively, pick the declared slot, export it without printing the key, and match the preset region/base URL. Do not assume a bare MINIMAX_API_KEY is the only valid slot.
For agents that need image analysis without a vision-capable LLM and without a MiniMax key. Or for batch jobs / privacy-sensitive content / unlimited quota.
Run a Hugging Face vision-language model locally:
python3 <skill-path>/scripts/describe.py <image-path> [--prompt PROMPT] [--model qwen2-vl-2b|moondream2|qwen2-vl-7b]
test cases passed, vs 2 / 17 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.