← ClaudeAtlas

sort-me-outlisted

Load when the user says "sort me out", "what am I missing", "what did I forget", "what's pending", "I'm all over the place", "ordéname", "qué me falta", "qué se me pasó", or asks for a full picture of everything open across projects, chats, clients and notes. The agent studies every source it can reach (notes, logs, task lists, memory, recent conversations, project files, live systems), then gives ONE ordered list: what is pending, what was promised and never done, what fell through the cracks, what is blocked and on whom, ranked by urgency and money at stake. For people who juggle many things and lose track.
RabbitDesigns22/claude-skills · ★ 0 · AI & Automation · score 75
Install: claude install-skill RabbitDesigns22/claude-skills
# Sort me out The user is juggling too much and things fall through the cracks between conversations: a promise made on Tuesday, a "send me that later" nobody sent, a task blocked on a third person who was never reminded. Your job is to be their memory and hand back **one clear, ordered list**, not a pile of notes. ## 1. Gather: read everything you can reach (silently) Look in every source available to you, newest first: - project notes, logs, changelogs, to-do files, decision records; - the agent's memory and the user's own instructions file; - recent conversations and other agents' reports you can access; - task lists, issue trackers, calendars, inboxes you are allowed to read; - live systems when a check is cheap (is the service up, did the payment arrive, is the item still "pending"). For each open item, write one line for yourself: **what, for whom, who must act, since when, what happens if it waits.** Mark the source. ## 2. Verify before listing - If a note says "pending" but you can check it now (status page, API, file), check it. Done items do not go on the list; items that broke since do. - Merge duplicates (the same task written three ways in three places). - Separate what you **checked** from what you only **read** in a note. ## 3. Hunt for what was forgotten Explicitly look for: - promises the user (or the agent) made: "I'll send it", "tomorrow", "after lunch"; - things started and never finished: half-done setups, drafts, unpublished work; - items waiting