Menu
SkillsMP has collected 75 skills from Lingtai-AI/lingtai-kernel. Open a skill to review its source and details.
Showing 40 of 75 collected skills.
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…
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…
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.
Short router for runtime, lifecycle, identity, refresh transactions, presets, settings, update/mismatch diagnosis, LLM adapters, and operating procedures.
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.
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`,…
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.…
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…
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…
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…
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…
**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…
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.
Inventory and ownership map for the bundled Web external procedures, assets, and retained helper scripts.
Site-class and recovery routing for the external web procedures, including endpoint pointers and access limitations.
Compact recovery index for static-browse failures: choose one explicit PDF, API, extraction, browser, or external-search procedure.
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.
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.
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.
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.
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.
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`).
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.
Read before changing character/identity in `system/lingtai.md`, choosing forced versus self-evolve mode, or applying durable identity edits.
Read before editing the living Pad, pinning references, or preparing Pad state for rebuild/molt.
Deep reference for the separate `.rules` heartbeat signal: authorized atomic writes, consumption, replacement, persistence, verification, and boundaries.
Deep reference for Psyche's redacted settings SHOW, strict owner-document grammar, precedence, timing, rollback, and eight stable anchors.
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.
Read before creating or organizing private durable knowledge (`knowledge/<name>/KNOWLEDGE.md`) or cross-references; use it for local memory, not portable procedures.
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.
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…
Use the Vision schema directly for ordinary image analysis; route setup, borrowing, settings, and recovery to focused references.
Read when a Task Card needs a truthful renderer, lifecycle recovery, settings, or projection boundary; routine schema-sufficient calls can use the action directly.
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`.
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;…
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.
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…
Daemon footprint scope, reclaim persistence, and consent-gated cleanup of old artifacts.
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…
Nested daemon-manual reference for backend choice, native versus prompt-only MCP, CLI options, list/ask behavior, and per-backend live-help routes.