nanika

Schedules and runs cron jobs and the nanika publishing pipeline via scheduler CLI. Use when scheduling jobs, managing cron tasks, running the daemon, checking job history, or setting up the daily publishing pipeline.

Obsidian vault CLI — read, write, search, capture, triage, enrich, and ingest into the vault at ~/.alluka/vault/. Prefer this CLI over the Write tool for vault paths so the search index, frontmatter schema, and triage hooks stay in sync — plain Write still works and the memory system reads any valid markdown at the canonical paths regardless of how it was produced. Use when user asks about notes, vault, captures, inbox triage, note search, or importing scout/learnings data.

Full article pipeline — from topic research to Substack draft. Scouts trending intel, writes or selects an article, generates intaglio art via Google Flow, creates manifest, and cross-posts to Substack. Use when creating, illustrating, or publishing articles.

Telegram and Discord channel integration for the orchestrator. Handles inbound messages as orchestrator commands and pushes mission lifecycle events back.

Handles inbound Telegram messages as orchestrator commands when running with --channels plugin:telegram@claude-plugins-official

Send native voice messages and text to Discord channels via the discord CLI. Use when sending audio as a Discord voice message or checking channel config.

Send voice messages and text to Telegram chats via the telegram CLI. Use when sending audio as a Telegram voice message or checking chat config.

Compiled symbolic memory CLI for AI agents. Use when the user wants to store durable facts, update entity state, search prior notes without embeddings, or inspect the current known state of an entity.

MCP server for the nen ability system. Exposes nanika's internal state — findings, learnings, missions, proposals, ko verdicts, scheduler jobs, and tracker issues — as Claude-callable tools via the Model Context Protocol.

Local issue tracker with hierarchical relationships, blocking links, and priority-based ready detection. Use when managing project tasks, creating actionable work items, or visualizing issue dependencies.

Mission decomposition skill — breaks complex tasks into dependency-aware PHASE lines that the orchestrator executes directly, bypassing its internal LLM decomposer. Use when planning missions, creating mission files, or decomposing complex tasks.