ztnkv

grill-me

Interactive "grill" session — asks pointed questions one at a time to surface blind spots in the current picture of the user and enrich the context for memory. Invoke when the user says "grill me", "ask me questions", "/grill-me", "I want to enrich the memory", "what don't you know about me", "ask me hard questions", or otherwise asks to be interviewed.

lists

Works with the user's lists in lists/ — tasks, films, books, games, workouts, etc. Detects the intent to operate on a list ("add a task", "add to films-to-watch", "mark as done", "show my book list") and picks the right list using the descriptions and trigger patterns in lists/index.md. Supports — add (append item), check (mark done), uncheck, remove, show (display the list), create (create a new list, only after confirming with the user). If the requested list is not in lists/index.md, never creates it silently — always confirms creation with the user.

memory-load

Loads relevant entries from memory/ into the conversation context. Use at the start of any non-trivial conversation, and any time the topic might overlap with what is stored in memory (personal facts, habits, goals, relationships, work, health, hobbies, etc.). Hybrid strategy — always read memory/index.md and memory/tags.md as the map first, then pull full entry bodies by tag match and by semantic match on titles. No artificial cap on how many entries can be loaded.

memory-retro

Orchestrator for writes into memory. Analyzes the source (the current conversation OR an external file/text passed as an argument), decides which new facts, changes, contradictions, and deprecations should be recorded in memory/, builds a diff proposal, and confirms it with the user. Only after an explicit "yes" does it call memory-write to apply changes. Triggered four ways — (1) explicit user command ("sum it up", "write down what you learned", "update memory", "/memory-retro"); (2) the agent's own initiative when meaningful new facts or contradictions surface in the dialog; (3) **mandatory auto-run from grill-me** — after a grill session completes, memory-retro always runs without re-asking the user; (4) bootstrap mode for bulk import from an external file (chat history dump, personal notes, session transcript) — fully autonomous, no dialog confirmations, all edge cases resolved by deterministic heuristics with confidence demoted to low as a signal for later review. In normal mode, never writes to memory s

memory-write

Service skill that writes and modifies files in memory/. Invoked ONLY from memory-retro after the user confirmed the proposed diff. Never runs by itself and is not invoked by the user directly. Supports four operations — add (new entry), update (edit existing), supersede (soft delete via status), delete (hard delete, only by an explicit user command). When tags need to be created or updated, cascades into tag-pick.

movie-wishlist

Fast path for adding a movie to the watch-later wishlist. Triggers on short phrases like "add the movie X", "add to films to watch X", "in the film wishlist Y", "new movie to watch — Z", "throw the movie W into films". Before writing, it researches IMDb rating, release year, and genre via WebSearch and stores them next to the title in lists/movies.md. Not used for showing the list, marking watched, or removing — those operations go through the regular lists skill.

my-schedule

Shows today's schedule as a table. Synthesizes the reference schedule from lists/schedule.md and today's day card from days/YYYY-MM-DD.md. Triggered by questions like "what's my schedule?", "what should I do today?", "show me my schedule", "what's on for today?".

new-day

Creates a day check-in — a Markdown file with today's prompts in days/. Triggered by "/new-day", "new day", "let's start the day". Works in two stages — first it creates a blank template (planning horizons, abstinence, errand of the day) and stops so the user can fill it in by hand; once the user signals "done / filled", it runs a defensive cross-check against the dynamics of the last days (flags focus drift, project switching, defensive scripts being acted out), then a retrospective of the contents, optionally proposes memory updates, and commits everything in a single commit.

tag-pick

Service skill that picks tags for a memory entry. Invoked EXCLUSIVELY from memory-write. Guards the tag dictionary against logical and lexical duplicates (psychology / psychotherapy, work / career, sport / training, etc.). ALWAYS reads memory/tags.md in full first, then picks 2–5 existing tags. If a new tag is needed, it asks the user explicitly with a justification of why existing tags do not fit and a definition of the new one. A new tag is created only after an explicit "yes".