lingtai-ai

@lingtai-ai source repo

153 skills
0 followers
6 hours ago last updated

▌
Lingtai Root Router · lingtai-ai bundle
Stable root catalog for LingTai skill domains.

0
installs
▌
Lingtai Help Router · lingtai-ai bundle
Route LingTai help requests to stable, product-owned child skills.

0
installs
▌
Lingtai Migration Router · lingtai-ai bundle
Route LingTai TUI and kernel release migrations to their product-owned tag histories.

0
installs
▌
Lingtai Installation · lingtai-ai bundle
Route ordinary installation, removal, and explicit installation maintenance assets.

0
installs
▌
Lingtai Kernel Dev · lingtai-ai
Mandatory repository-local development guide for LingTai's Python kernel and runtime. Use this before changing code, architecture documents, tests, packaging, capabilities, adapters, or developer documentation in lingtai-kernel. Routes each task through the exact baseline, the distributed ANATOMY/CONTRACT systems, focused validation, and pull-request safety gates.

0
installs
▌
Imap MCP Manual · lingtai-ai bundle
Progressive-disclosure usage manual for the IMAP/SMTP email MCP. Read this router for unfamiliar or consequential workflows and deeper detail on real-mail side effects, external-reply policy, account selection, compound email IDs, attachments, mailbox mutations, contacts, or settings. Pull the full body with action='manual'; do not guess provider or account details.

0
installs
▌
Shell Manual · lingtai-ai
**Read before running a long-lived agent/coding CLI as a shell subprocess**, or before setting up cron/launchd/systemd timers or scheduled reminders. Routes shell-side async+poll supervision, host-scheduler setup, LingTai wake-by-mailbox-drop, one-shot reminders, and safe cleanup. Per-backend CLI operational detail (command shapes, flags, env contracts) for daemon-backed CLIs lives in `daemon-manual` → `reference/cli-backends/SKILL.md`.

0
installs
▌
File Manual · lingtai-ai
Read/write/edit/glob/grep guide for LingTai's `file` tool: safe overwrite/edit discipline, explicit non-UTF-8 routing, SHOW-only policy, and pagination recovery.

0
installs
▌
Soul Manual · lingtai-ai bundle
Read before calling `flow`, making consequential or unfamiliar Soul config/voice changes, or recovering a disabled/ongoing flow; routine inquiry, dismiss, and settings calls are schema-sufficient.

0
installs
▌
Feishu MCP Manual · lingtai-ai bundle
Concise progressive-disclosure usage manual for the Feishu (Lark) MCP. Ordinary schema-sufficient calls can start here; unfamiliar setup, cards, callbacks, compound replies, partial delivery, and recovery route to one focused reference. It covers the strict action envelope, recipient/account checks, and the no-fallback/no-blind-retry safety boundary.

0
installs
▌
Wechat MCP Manual · lingtai-ai bundle
Progressive-disclosure usage manual for WeChat/iLink: first safe read, exact IDs, external send/reply, media partials, and standalone poller/setup hazards. Use the schema for routine calls; load this manual for media details, unfamiliar results, setup, or recovery.

0
installs
▌
Email Manual · lingtai-ai
Internal LingTai mail: send/read/dismiss/reply, bare-path addressing, delayed self-send time capsules, and full-body persistent notifications. Not internet email (see `mcp-manual`) or recurring schedules (see `shell-manual`).

0
installs
▌
Avatar Manual · lingtai-ai bundle
Use for an unfamiliar or consequential Avatar spawn, shallow/deep choice, detached lifecycle, recovery, or footprint review. Routine schema-sufficient spawns can use the tool directly.

0
installs
▌
Daemon Manual · lingtai-ai
Use for unfamiliar daemon delegation, backend-specific work, stalled or failed runs, completion checks, or consent-gated cleanup. Routine calls can start from the advertised schema.

0
installs
▌
Plugin Manual · lingtai-ai bundle
Read-only Agent Plugins v1.0.0 catalog: registered versus discovered, authorized registration refresh, containment, and skipped-component diagnosis. Use for unfamiliar or consequential plugin work; routine schema-sufficient calls can go straight to `info`.

0
installs
▌
Skills Manual · lingtai-ai bundle
Read before authoring, installing, or sharing a skill in `.library/custom/<name>/`, adding configured skill roots, or diagnosing a catalog entry; this teaches the Skills system, not bundled skill procedures.

0
installs
▌
Vision Manual · lingtai-ai bundle
Use the Vision schema directly for ordinary image analysis; route setup, borrowing, settings, and recovery to focused references.

0
installs
▌
Telegram MCP Manual · lingtai-ai bundle
Progressive-disclosure usage manual for the Telegram MCP tool. The resident schema carries safe first-use guidance; call `manual` for the action map, inbound-first/reply routing, channel/media/rendering rules, settings, Task Card projection, and error handling.

0
installs
▌
Whatsapp MCP Manual · lingtai-ai bundle
Progressive-disclosure usage manual for the personal-account WhatsApp MCP tool. Read this when you need detail beyond the concise action description: the single-session whatsapp-web.js bridge and QR pairing, strict send/reply/react semantics, opaque message IDs, check/read/search and local contacts, bridge media and the absence of inbound downloads, LICC wake/replay/allowlist behavior, read-only redacted settings, external side effects, and ToS/ban risk. Pulled on demand via action='manual'; you do not need to call it before every send.

0
installs
▌
Context Manual · lingtai-ai bundle
Use for an unfamiliar or consequential context operation, session journaling, handoff, or context-loss recovery; routine calls can follow the schema.

0
installs
▌
Cloud Mail MCP Manual · lingtai-ai bundle
Progressive-disclosure usage manual for Cloud Mail REST email actions. Read it when action filters/ids, setup/authentication, polling/settings, or side-effect detail is needed. Returned by action='manual'; nested references are packaged but not embedded. Calls use the strict LTP-v2 envelope.

0
installs
▌
Knowledge Manual · lingtai-ai
Read before creating or organizing private durable knowledge (`knowledge/<name>/KNOWLEDGE.md`) or cross-references; use it for local memory, not portable procedures.

0
installs
▌
Task Card Manual · lingtai-ai bundle
Read when a Task Card needs a truthful renderer, lifecycle recovery, settings, or projection boundary; routine schema-sufficient calls can use the action directly.

0
installs
▌
Web Manual · lingtai-ai bundle
First-call search→browse route for the single web capability; exact settings, complete-output, provider, and public-URL hazards are retained here or routed to one focused reference.

0
installs
▌
Notification Manual · lingtai-ai
Entry manual for the standalone `notification` tool and its `.notification` mirrors. Routine check uses the schema; read a reference for unfamiliar payload, producer, dismissal, delay, or settings detail. Large-result compaction belongs to `context-manual`, not here.

0
installs
▌
Pad Manual · lingtai-ai
Read before editing the living Pad, pinning references, or preparing Pad state for rebuild/molt.

0
installs
▌
MCP Manual · lingtai-ai bundle
Read-only MCP status router: distinguish catalog, registered, and active servers; inspect effective settings safely; and route authorized setup or recovery to the exact provider and runtime references. Routine info/settings/manual calls need no ritual manual reading. This is not an MCP protocol guide.

0
installs
▌
Read Manual · lingtai-ai
File pagination, truncation and long-line recovery: `next_offset` continuation, `line_truncated`, default/hard-cap limits, and when to switch to bash/grep/sed instead. Use when ordinary `file.read` cannot expose complete content.

0
installs
▌
Psyche Manual · lingtai-ai
Compact router for Psyche's four durable domains (pad, lingtai, knowledge, skills), the shared file→rebuild model, redacted settings, and the separate `.rules` heartbeat reference.

0
installs
▌
System Manual · lingtai-ai
Short router for runtime, lifecycle, identity, Agent/Project relocation, refresh transactions, presets, settings, update/mismatch diagnosis, LLM adapters, and operating procedures.

0
installs
▌
Telegram Task Card Projection Notice · lingtai-ai bundle
Shipped retained-legacy/projection notice for Telegram Task Card files. The public `task_card` tool is intrinsic and documented at src/lingtai/tools/task_card/manual/SKILL.md; Telegram only projects the intrinsic taskcard/status + taskcard/taskcard.md artifact read-only.

0
installs
▌
Lingtai Doctor · lingtai-ai bundle
Read-only health diagnostics when an agent looks dead but the evidence is mixed, or a migration may have left stale MCP/addon paths; run before deciding to mail, refresh, CPR, or edit persistent configuration. Includes a bundled read-only `doctor.py`.

0
installs
▌
Lingtai Manual · lingtai-ai
Read before changing character/identity in `system/lingtai.md`, choosing forced versus self-evolve mode, or applying durable identity edits.

0
installs
▌
Daemon Cleanup · lingtai-ai
Daemon footprint scope, reclaim persistence, and consent-gated cleanup of old artifacts.

0
installs
▌
Bash Async Jobs · lingtai-ai
Nested shell-manual reference for durable asynchronous shell jobs: detached daemon routing, reminder/completion wakeups, relaunch-safe polling, cancellation, and shell-side coding-CLI supervision.

0
installs
▌
Lingtai Kernel Anatomy · lingtai-ai bundle
Enter the Python kernel Anatomy/Contract graph before source navigation or maintaining architecture maps; explains how the ANATOMY.md and CONTRACT.md graphs pair, and what to do when code and navigation disagree.

0
installs
▌
Daemon Forensics · lingtai-ai
Nested daemon-manual reference for durable run artifacts, state/result inspection, transcripts, token ledgers, and interpreting exit 143/SIGTERM.

0
installs
▌
Telegram Rate Limits · lingtai-ai
Current official Telegram Bot API flood-control guidance: published quotas, `retry_after` semantics, documented unknowns, and safe client policy. Read before changing Telegram send cadence, programmable Task Card cadence, or 429 recovery behavior.

0
installs
▌
Bash Scheduled Work · lingtai-ai
Nested shell-manual reference for recurring, time-driven work: host scheduler choice, LingTai wake-by-mailbox-drop, short prompts, script hygiene, macOS launchd, Linux systemd timers, crontab, and process-tree hazards.

0
installs
▌
Daemon CLI Backends · lingtai-ai
Nested daemon-manual reference for backend choice, native versus prompt-only MCP, CLI options, list/ask behavior, and per-backend live-help routes.

0
installs
▌
Bash Debugging Cleanup · lingtai-ai
Nested shell-manual reference for debugging silent scheduled jobs and retiring schedulers safely: scheduler, script, work, wake, launchd, cleanup, and shell work-footprint checks.

0
installs
▌
Daemon Dispatch Ledger · lingtai-ai
Nested daemon-manual reference for append-order ledger warnings and non-repair diagnostics.

0
installs
▌
Summarize Manual · lingtai-ai
Operational guide for recording tool-result summaries, applying them with a full rebuild, recovering raw evidence, and choosing summarize versus molt.

0
installs
▌
Email Manual Settings Reference · lingtai-ai
Focused Email settings reference for the five SHOW rows, installed limits, manifest subscription source, redaction, precedence, timing, and the read-only boundary. Read when interpreting settings rows.

0
installs
▌
Email Manual Actions And Storage · lingtai-ai
Focused Email reference for action inputs, folders, check filters, delivery, self-send/time capsules, contacts, attachments, and mailbox persistence. Read when the schema and first-call map are not enough.

0
installs
▌
Psyche Settings Reference · lingtai-ai
Deep reference for Psyche's redacted settings SHOW, strict owner-document grammar, precedence, timing, rollback, and eight stable anchors.

0
installs
▌
Notification Manual Channel Model · lingtai-ai
Notification payload, mirror, allowlist, hook, delivery, delay, and block-cap reference. Read after notification-manual when interpreting current channel state or diagnosing delivery; dismissal policy belongs to dismissal-safety.

0
installs
▌
Web Manual Tier Quick Refs · lingtai-ai
Compact recovery index for static-browse failures: choose one explicit PDF, API, extraction, browser, or external-search procedure.

0
installs
▌
Hello Lingtai · lingtai-ai
The example Agent Plugin's one skill. Reach for it only to confirm that plugin registration worked: if this skill is in your skills catalog with a location inside docs/examples/agent-plugins/hello-lingtai/, then the kernel mounted a declared plugin's skills/ directory correctly. It teaches nothing else and covers no real task.

0
installs
▌
Bash Notification Reminders · lingtai-ai
Nested shell-manual reference for one-shot wakeup reminders using `.notification/cron.json`: payload, atomic writer, shell example, and the rest checklist for pending work.

0
installs
▌
Email Manual Addressing And Replies · lingtai-ai
Focused Email reference for bare-path addressing, peer/abs resolution, safe same-channel replies, sender identity display, and local mailbox-ID privacy. Read when routing or answering internal mail.

0
installs
▌
Web Manual Routing And Sites · lingtai-ai
Site-class and recovery routing for the external web procedures, including endpoint pointers and access limitations.

0
installs
▌
Goal Manual · lingtai-ai
Goal notification manual: `.notification/goal.json` source-of-truth, fields, instructions, idle reminders, protected dismiss behavior, and cancellation or completion semantics.

0
installs
▌
Notification Manual Dismissal Safety · lingtai-ai
Safe notification dismissal reference: producer-owned state, atomic targets, stale versions, force, protected channels, post-molt acknowledgement, hooks, and legacy large-result reminders. Read after notification-manual before a clear or when one is refused; compaction belongs to summarize-manual.

0
installs
▌
LLM Adapters · lingtai-ai
Nested system-manual reference for the built-in LLM adapters: what each named adapter is, how it is configured and dispatched, its special transport or protocol behaviors, and the environment variables that control it.

0
installs
▌
Web Manual Maintenance Bundles · lingtai-ai
Inventory and ownership map for the bundled Web external procedures, assets, and retained helper scripts.

0
installs
▌
Psyche Network Rules Reference · lingtai-ai
Deep reference for the separate `.rules` heartbeat signal: authorized atomic writes, consumption, replacement, persistence, verification, and boundaries.

0
installs
▌
Email Manual Notifications And Delivery · lingtai-ai
Focused Email reference for daemon delivery, heartbeat/liveness, bounce recovery, unread payloads, persistent bodies, overflow, and read-state refresh. Read when delivery or notices need diagnosis.

0
installs
▌
Migration Guide · lingtai-ai bundle
Canonical system-manual migration guide for authorizing and verifying a mechanical Agent workdir/address or whole-Project path move. Runtime/source migration routes outward; the bundled helper is only a narrow POSIX option.

0
installs
▌
Refresh Precheck · lingtai-ai
Nested system-manual reference and single owner for a refresh transaction: select same-runtime reload, source/venv cutover, or failure recovery; run only triggered owner checks; issue exactly one refresh; capture one targeted receipt.

0
installs
▌
Sqlite Log Query · lingtai-ai bundle
Nested system-manual reference for the additive SQLite/`log.sqlite` sidecar over LingTai's JSONL runtime traces. Read it when you need `lingtai-agent log doctor|query|rebuild`, read-only SQL safety and WAL/rebuild caveats, the events/chat_entries/token_entries schema, quick-start snippets, SQL recipes (`tool_call_id` lifecycle, tool result stats and percentiles, spilled/large tool results), gotchas, or the redaction rules. Runtime trace forensics start here; trajectory mining is the sibling `trajectory-mining`.

0
installs
▌
Substrate Manual · lingtai-ai
Nested system-manual reference: the expanded form of the resident substrate prompt — body/extensions, lifecycle states, the `system` tool in practice, communication and memory layers, collaboration topology, MCP/addon ownership, and (§11) the canonical `init.json` composition and preset runtime model. Route via `system-manual` when it is unclear whether this is the right node.

0
installs
▌
Procedures Manual · lingtai-ai
Nested system-manual reference: the expanded form of the resident procedures prompt — progressive disclosure, responsiveness and side-effect authorization, the daemon workflow methodology, depositing work, idle/lifecycle, skill routing, deliverables, artifact sharing, and issue reporting. Route via `system-manual` when it is unclear whether this is the right node.

0
installs
▌
Trajectory Mining · lingtai-ai
Nested system-manual reference for trajectory mining — turning LingTai runtime event streams into validated, actionable improvement candidates. Read this after `reference/sqlite-log-query/SKILL.md` has given you the data access layer: manifest policy, cheap-model/daemon strategy, prompt templates, the finding schema and confidence rubric, the digest template, output routing, and periodic mode.

0
installs
▌
System Settings Inventory Reference · lingtai-ai
Exact read-only System catch-all settings inventory: ownership, effective sources, defaults, accepted values, invalid behavior, redaction, timing, authorized change procedures, and explicit non-settings.

0
installs
▌
Tool Plugin Settings Reference · lingtai-ai
Developer reference for opting one tool family into bounded, read-only settings discovery without changing other families.

0
installs
▌
Environment Variables · lingtai-ai
Progressive-disclosure route to the root canonical environment-variable registry. Use the registry for names, defaults, behavior, ownership, and security notes.

0
installs
▌
Runtime Update Checks · lingtai-ai
Nested system-manual reference for update, source, install, nudge, and runtime-mismatch diagnosis. Owns interpreter/provenance evidence and the source/venv cutover handoff; routes refresh sequencing to refresh-precheck.

0
installs
▌
External Attach Diagnostic · lingtai-ai bundle
Guarded macOS-only external attach diagnostic: verifies a live LingTai PID and incarnation against an exact agent directory, captures bounded /usr/bin/sample stacks plus content-free runtime facts, and optionally performs one controlled external mcp.* burst without exercising NotificationStore locking.

0
installs
▌
Daemon Backend Codex · lingtai-ai
Nested daemon-cli-backends reference for the Codex daemon backend's flag surface. Read this when a daemon task needs Codex-specific CLI flags (model selection, reasoning effort, config overrides) or the operational core folded in from the retired bash reference guide: install, auth/config, and the Codex-vs-Claude style axis. It routes you to the installed CLI's live help via shell and shows how to translate that help into the generic `backend_options` mechanism. It is not a flag catalog.

0
installs
▌
Daemon Backend Cursor · lingtai-ai
Nested daemon-cli-backends reference for the Cursor daemon backend's flag surface. Read this only when a daemon task needs Cursor-specific CLI flags (model selection, output/tooling switches): it routes you to the installed CLI's live help via shell and shows how to translate that help into the generic `backend_options` mechanism. It is not a flag catalog.

0
installs
▌
Daemon Backend Lingtai · lingtai-ai
Nested daemon-cli-backends reference for the built-in `lingtai` daemon backend (the in-process ChatSession default). Read this when routing a daemon task to the built-in backend: it has no external CLI and no `backend_options` flag surface; this page routes you to the live authorities for preset selection/inspection, lingtai/tools/skills/MCP inheritance, and the daemon completion contract. It is not a rules catalog.

0
installs
▌
Daemon Backend Claude P · lingtai-ai
Nested daemon-cli-backends reference for the claude-p (alias claude-code) daemon backend's flag surface. Read this only when a daemon task needs Claude Code-specific CLI flags (model selection, fallback model, tool restrictions): it routes you to the installed CLI's live help via shell and shows how to translate that help into the generic `backend_options` mechanism. Also owns Claude Code's operational core: the `env -u` auth hygiene wrapper, weekly-limit smoke test, stale-token diagnosis, and the budget/timeout/print-mode background caveats. It is not a flag catalog.

0
installs
▌
Daemon Backend Deepseek · lingtai-ai
Nested daemon-cli-backends reference for the DeepSeek Harness daemon backend's flag surface. Read this only when a daemon task needs DeepSeek-specific launcher flags (`--patch` overlays): it routes you to the installed CLI's live help via shell and shows how to translate that help into the generic `backend_options` mechanism. It is not a flag catalog.

0
installs
▌
Daemon Backend Kimicode · lingtai-ai
Nested daemon-cli-backends reference for the Kimi Code daemon backend's flag surface. Read this only when a daemon task needs Kimi-specific CLI flags (model selection, skills/workspace directories): it routes you to the installed CLI's live help via shell and shows how to translate that help into the generic `backend_options` mechanism. It is not a flag catalog.

0
installs
▌
Daemon Backend Mimocode · lingtai-ai
Nested daemon-cli-backends reference for the MiMo Code (`mimocode` / `mimo`) daemon backend's flag surface. Read this only when a daemon task needs MiMo-specific CLI flags (model selection, provider switches): it routes you to the installed CLI's live help via shell and shows how to translate that help into the generic `backend_options` mechanism. It is not a flag catalog.

0
installs
▌
Daemon Backend Oh My Pi · lingtai-ai
Nested daemon-cli-backends reference for the Oh-My-Pi (`omp`) daemon backend's flag surface. Read this only when a daemon task needs Oh-My-Pi-specific CLI flags (model selection, tool or provider switches): it routes you to the installed CLI's live help via shell and shows how to translate that help into the generic `backend_options` mechanism. It is not a flag catalog.

0
installs
▌
Daemon Backend Opencode · lingtai-ai
Nested daemon-cli-backends reference for the OpenCode daemon backend's flag surface and operational setup (install, auth, run flags, warm server, custom agents). Read this when a daemon task needs OpenCode-specific CLI flags (model selection, provider-specific reasoning variants, agent choice) or OpenCode install/auth preparation: it routes you to the installed CLI's live help via shell and shows how to translate that help into the generic `backend_options` mechanism. It is not a flag catalog.

0
installs
▌
Daemon Backend Qwen Code · lingtai-ai
Nested daemon-cli-backends reference for the Qwen Code (`qwen-code` / `qwen`) daemon backend's flag surface. Read this only when a daemon task needs Qwen-specific CLI flags (model selection, provider tunables): it routes you to the installed CLI's live help via shell and shows how to translate that help into the generic `backend_options` mechanism. It is not a flag catalog.

0
installs
▌
Lingtai Tui Dev · lingtai-ai
Mandatory repository-local development guide for LingTai's Go repository — the two binaries lingtai-tui and lingtai-portal plus the install pipeline. Use this before changing code, architecture documents, tests, packaging, capabilities, adapters, or developer documentation in this repository. Routes each task through the exact baseline, the distributed ANATOMY/CONTRACT systems, focused validation, and pull-request safety gates.

0
installs
▌
Tui · lingtai-ai bundle
SKILL.md — Preset model lists & provider integration

0
installs
▌
Swiss Knife · lingtai-ai
Umbrella router for small, focused CLI tools: minimax-cli for MiniMax media/TTS/vision; vision for image OCR/critique; listen for local audio transcription and music analysis; academic-research for papers, citation networks, and LaTeX; dj for music generation; token-usage for token/cost and API-call trend reports; html-report for standalone browser deliverables; xiaomi-mimo and zhipu-coding-plan for provider discovery; headless-bot for provisioning fresh LingTai bot projects (e.g. Telegram); find-something-to-do for idle curiosity; preset-health for read-only saved-preset health checks. Each nested reference is self-contained under `reference/<name>/SKILL.md`.

0
installs
▌
Lingtai Recipe · lingtai-ai bundle
Menu manual (not a tool) for recipes — the named payload that shapes an orchestrator's greeting, ongoing behaviour, and shipped library; every LingTai project uses one. Routes to `reference/recipe-format/SKILL.md` (authoring/customising) and `reference/export-recipe/SKILL.md` (publishing for new networks), and warns about the three different recipe-shaped artifacts that can co-exist in one project — easy to conflate. Do NOT use for one-off exports of a single agent (that's just `cp -r`), or for in-network behaviour edits to the live system.

0
installs
▌
Lingtai Update · lingtai-ai
Use when installing, updating, building, or debugging lingtai-tui or lingtai-portal — Homebrew, source builds, install-method detection, or mainland-China connectivity.

0
installs
▌
Lingtai Tui Help · lingtai-ai bundle
Anything you need to know about LingTai TUI. Read this first for the stable mental model, feature map, interface/slash-command help, or the right source/manual route for a TUI question. Exact command prose lives in the localized help assets, Go structure lives in `lingtai-tui-anatomy`, and presets, Portal, tutorials, updates, and addons keep their own top-level skills.

0
installs
▌
Lingtai Dev Guide · lingtai-ai
Router for contributing to LingTai. Use when changing code or docs, setting up a dev environment, navigating the TUI/portal repo or Python kernel, developing MCP addons, troubleshooting a running network, auditing security, running a runtime self-check, prepping a PR review, or stewarding a new skill. For developers and contributors; for end-user lessons, use tutorial-guide.

0
installs
▌
Lingtai Tui Anatomy · lingtai-ai
Source-navigation guide for the LingTai Go monorepo that ships `lingtai-tui` and `lingtai-portal`. Read this for TUI/Portal structure, runtime-boundary evidence, exact Go ownership, or when updating an `ANATOMY.md`. The repository-root `ANATOMY.md` is normative; this skill routes into that graph without duplicating it. Kernel internals remain owned by `lingtai-kernel-anatomy`.

0
installs
▌
Lingtai Issue Report · lingtai-ai
Protocol router for reporting bugs, stale info, missing capabilities, or design issues in any LingTai skill, capability, preset, or system behavior. Enter through this router, then load the one nested reference you need — evidence-checklist, report-template, or filing-flow. You always assemble a structured report and ask the human for permission before filing.

0
installs
▌
Lingtai Portal Guide · lingtai-ai
Reference router for lingtai-portal internals — startup/opening, .portal/ files, topology/replay APIs, network response shape, and lifecycle/recording. Use when the human asks about visualization, network history, or the portal.

0
installs
▌
Lingtai Preset Skill · lingtai-ai
Use when asking about built-in TUI presets or their shared operations.

0
installs
▌
Textbook Distillation · lingtai-ai bundle
Turn a textbook or long-form source into a self-paced learning track: chapter map, lesson plan, then self-contained HTML lecture notes (styled as the human specifies) with worked examples, exercises, and checkpoint questions. Read this for "lecture notes" / "study notes" / "course" / "syllabus" requests from a textbook or PDF. Do NOT use to reproduce or redistribute a copyrighted book verbatim, to "summarize so I don't have to buy it," or for one-off factual lookups (just answer those directly).

0
installs
▌
Tutorial Guide · lingtai-ai
The 12-lesson curriculum for teaching a human how LingTai works — 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.

0
installs
▌
Dj · lingtai-ai
Nested swiss-knife reference for composing one music track that resonates with a project journal entry, on demand. Walks the user's saved presets to find a usable media-creation provider (MiniMax, etc.), reads the journal at ~/.lingtai-tui/brief/projects/<hash>/journal.md, picks a genre that fits the day, generates the audio, and saves it next to the journal under music/ with an index entry. Read this when the user asks for music for a journal day, a project's vibe, session mood, or a specific generated genre — decline honestly when no usable provider is configured.

0
installs
▌
Listen · lingtai-ai bundle
Nested swiss-knife reference for local audio analysis — transcribe speech with Whisper, or extract musical features (tempo, key, dynamics, spectral profile) with librosa. Both run on the user's machine with no API key. Read this when the human asks you to transcribe a voice note, extract lyrics from singing, critique generated music, or analyze audio characteristics. For *creating* music or audio, use the sibling `minimax-cli` reference (or `dj` for journal-inspired music) instead.

0
installs
▌
Vision · lingtai-ai bundle
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 which path applies.

0
installs
▌
Lingtai Update Install · lingtai-ai
Use when installing or building the lingtai-tui and lingtai-portal binaries.

0
installs
▌
Dev Guide Setup · lingtai-ai
Nested lingtai-dev-guide reference for local developer environment setup: cloning repos, building TUI/portal, dev-mode symlinks, editable kernel install, MCP addon setup, and verification.

0
installs
▌
Lingtai Update Homebrew · lingtai-ai
Use when updating through or exploring the Lingtai Homebrew tap.

0
installs
▌
HTML Report · lingtai-ai bundle
Nested swiss-knife reference for standalone HTML deliverables. Produce polished, self-contained HTML deliverables (research memos, literature maps, dashboards, audit reports, side-by-side comparisons) that humans open in a browser or receive as Telegram/email attachments. Covers a standalone HTML skeleton, math rendering with MathJax (LaTeX in `<pre>`/`<code>` will NOT render), artifact hygiene, and a validation checklist. Read when the human asks for an HTML report, HTML memo, HTML deliverable, or any standalone .html artifact — especially anything containing equations.

0
installs
▌
Minimax CLI · lingtai-ai
Nested swiss-knife reference for the MiniMax `mmx` CLI and the canonical MiniMax CLI procedure shipped with the TUI: install `mmx-cli`, discover the correct TUI-managed MiniMax preset/key slot without leaking secrets, match mainland vs international regions, and route image/video/music/TTS generation or one-shot shell vision.

0
installs

153 published skills · page 1 of 2