Menu
Official-source-led manual for the TUI `custom` template.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
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-custom |
| description | Official-source-led manual for the TUI `custom` 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. |
customcustomPreset() (tui/internal/preset/preset.go:1242-1264) is a
user-supplied OpenAI-compatible template: model is empty until configured,
the key slot is LLM_API_KEY, and the endpoint is user-supplied. Its
vision capability inherits the configured LLM endpoint.
Whether images work is therefore unknown until the actual provider, model, protocol, and endpoint are identified. The vision tool still tries the current OpenAI-compatible endpoint, model, and credential by default instead of treating that uncertainty as setup-time manual-only.
Read the configured endpoint’s official documentation on demand. Useful protocol references are the OpenAI Chat API, Anthropic Messages API, or Gemini API, as applicable; none is a claim about an unspecified endpoint. No plan-level vision MCP can be asserted.
If direct vision fails, report the endpoint-specific limitation and let the agent choose an explicit skill. Do not guess credentials, switch providers, or auto-load/invoke an MCP. Verify all inherited fields in TUI source and inspect the saved manifest for the user’s actual configuration.
For base URL/API-compat/model/capability declaration shape versus
credentials, see reference/operations/endpoint-capabilities/SKILL.md.