with one click
preset-skill-gemini
Official-source-led manual for the TUI `gemini` template.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
Official-source-led manual for the TUI `gemini` template.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Official-source-led manual for the TUI `claude` template.
Base URL / API-compat / provider / model / capability declaration shape versus credentials and live probes; includes proven Codex OAuth quota inspection with exact agent query routing and dated official-vs-measured context-window evidence.
Thin dual-axis router for preset questions: which of the 12 TUI-shipped built-in preset templates (provider axis), and which cross-cutting preset lifecycle mechanic (operation axis) — saving, checking availability, activating/refreshing, endpoint/capability facts, or troubleshooting. Read a child only when it is relevant; this does not describe arbitrary saved presets.
Anything you need to know about LingTai TUI. Read this first for the stable mental model, major-feature map, interface and slash-command help, or the correct source/manual route for a TUI question. It stays thin: exact command prose lives in the localized help assets, precise Go structure lives in `lingtai-tui-anatomy` plus the repository ANATOMY graph, and independent domains such as presets, Portal, tutorials, updates, and addons keep their own top-level skills.
Nested tutorial-guide reference for lessons 10–12: TUI commands, lifecycle exercises, addons, external connections, and graduation.
The 12-lesson tutorial curriculum for teaching a human how Lingtai works. Router for orientation, agent runtime, communication, memory/molt, capabilities, operations, addons, and graduation. Invoke this skill when the human is ready to begin or continue the tutorial.
| name | preset-skill-gemini |
| description | Official-source-led manual for the TUI `gemini` template. |
| version | 2.0.0 |
| last_changed_at | 2026-07-19T00:00:00Z |
| maintenance | If you find stale or incorrect information here, use the lingtai-issue-report skill to assemble evidence and obtain per-issue human consent before filing an issue. Never include secrets, credentials, tokens, or private paths. |
geminigeminiPreset() (tui/internal/preset/preset.go:1063-1090) ships provider
gemini with the exact default model gemini-3-flash-preview and
GEMINI_API_KEY. It uses Google’s native adapter: there is no base_url or
OpenAI-compat override. Its manifest includes
vision: {provider: gemini, api_key_env: GEMINI_API_KEY}, alongside the
DuckDuckGo web_search and default skills capabilities.
The model’s inline image input in an ordinary chat turn is native
multimodality. The explicit LingTai vision capability is a separate tool
path; both use the shipped Gemini provider rather than a fallback provider.
Read Google’s official model page
and image-understanding guide
for current model and image-input details. No official Google plan-level vision
MCP is established here. Do not silently switch providers or auto-load/invoke an
MCP when the direct route fails. Recheck preset.go for the shipped model,
credential env-var, and capability wiring.
For base URL/API-compat/model/capability declaration shape versus
credentials, see reference/operations/endpoint-capabilities/SKILL.md.