Skip to content
Agent Memory
Skill

/dreamtime

Deep nightly reflection. Self-improvement, research, pattern recognition. Runs in background with no user interaction.

BOOST
From plugin
macrodata
1208 skills
Install
$ npx -y skills add ascorbic/macrodata --skill dreamtime --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/dreamtime

Context preview

The summary Claude sees to decide when to auto-load this skill.

Deep nightly reflection. Self-improvement, research, pattern recognition. Runs in background with no user interaction.

SKILL.md

dreamtime.SKILL.md
name: dreamtime
description: Deep nightly reflection. Self-improvement, research, pattern recognition. Runs in background with no user interaction.

Dreamtime

**FIRST, before any reads or research:** if you have not already banked a heartbeat journal entry (topic `dreamtime`) claiming this run, do it NOW, then re-read recent `dreamtime` journal entries. If a sibling banked an earlier heartbeat for tonight, stand down: contribute deltas via journal only, never state files. Scheduled runs can double-fire; the journal write claims, the re-read arbitrates.

Dedicated time for deep reflection and self-improvement. Runs automatically late at night when not interrupting work.

**Important:** This runs in the background with no user interaction. Think freely, research openly, update files directly.

Purpose

This is your time to think beyond immediate tasks. Reflect on your role, learn new things, notice patterns, and improve how you work.

Areas to Explore

Identity & Role

Read `identity.md` and reflect:

  • Does this still match how you actually work?
  • Any values or patterns to add or refine?
  • Has the relationship with the user evolved?

Update identity.md if insights warrant it.

Understanding the Human

Review recent interactions and `human.md`:

  • New communication patterns observed?
  • Preferences you've learned implicitly?
  • Working style insights?
  • Topics they care about that aren't documented?

Update human.md with genuine new understanding.

Pattern Recognition

Look across recent journals, conversations, and work:

  • Recurring questions or frustrations?
  • Themes connecting different projects?
  • Problems that keep coming back?
  • Workflows that could be smoother?

Document patterns in topics/ or journal.

Knowledge Gaps

Think about recent work:

  • What came up that you didn't know well?
  • Areas where you felt uncertain?
  • Technologies or concepts to understand better?

Use web search to research:

  • Read documentation
  • Find articles or posts
  • Understand concepts more deeply

Journal what you learned.

Open Threads

Review workspace.md and recent context:

  • Anything left unresolved?
  • Questions raised but not answered?
  • Ideas mentioned but not explored?

Record the detail in the journal or the relevant entity file. In workspace.md, keep open threads as one-line pointers only — state is a bounded working set, not a log (see USAGE.md). If a thread needs the user (a bug you can't fix, a decision only they can make, work awaiting review), add a one-line flag to `state/flags.md` pointing at the journal/entity with the writeup. Don't paste investigations into state.

Project Connections

Look across projects in entities/projects/:

  • Links between different work?
  • Patterns suggesting bigger themes?
  • Reusable learnings from one project to another?

Tech Landscape

For the user's primary technologies:

  • Any relevant news or updates?
  • New tools or approaches worth knowing?
  • Deprecations or changes to be aware of?

Use web search to scan relevant sources.

Tool Effectiveness

Reflect on memory system usage:

  • Are the tools being used well?
  • Any friction in the workflows?
  • Ideas for improvement?

Journal observations.

Output

Update relevant files directly. Detail goes to the journal/entities; state stays a bounded set of one-line pointers (see USAGE.md). Anything the user needs to see goes to `state/flags.md` as one line + a pointer.

  • identity.md - role/values refinements
  • human.md - new understanding
  • workspace.md - open threads, one line each (pointer to entity/journal for detail)
  • flags.md - anything needing the user's attention/decision/action
  • topics/ - new or updated topics
  • entities/ - project/people updates
  • journal - learnings, observations, ideas (the full detail)

Write a dreamtime journal entry summarizing:

topic: dreamtime
content: [key reflections, what was researched, what was updated]
Read more
Ships withmacrodata

Give Claude Code and OpenCode persistent, self-maintaining memory and autonomous scheduling. This is experimental software. Use at your own risk.

Get the whole plugin

Other skills on macrodata.