dreamingCreative exploration during quiet hours. Turns idle heartbeat time into freeform thinking — hypotheticals, future scenarios, reflections, unexpected connecti...
Install via ClawdBot CLI:
clawdbot install briancolinger/dreamingCreative, exploratory thinking during quiet hours. Not task-oriented work — freeform associative exploration that gets captured for later review.
Edit scripts/should-dream.sh to customize:
mkdir -p data memory/dreams
Add this section to your heartbeat routine (during quiet hours):
## Dream Mode (Quiet Hours Only)
Check if it's time to dream:
\`\`\`bash
DREAM_TOPIC=$(./scripts/should-dream.sh 2>/dev/null) && echo "DREAM:$DREAM_TOPIC" || echo "NO_DREAM"
\`\`\`
**If DREAM_TOPIC is set:**
1. Parse the topic (format: `category:prompt`)
2. Write a thoughtful exploration to `memory/dreams/YYYY-MM-DD.md`
3. Keep it genuine — not filler. If the well is dry, skip it.
4. Append to the file if multiple dreams that night
The should-dream.sh script acts as a gate:
State tracked in data/dream-state.json:
{
"lastDreamDate": "2026-02-03",
"dreamsTonight": 1,
"maxDreamsPerNight": 1,
"dreamChance": 1.0
}
When the script returns a topic, write to memory/dreams/YYYY-MM-DD.md:
# Dreams — 2026-02-04
## 01:23 — The Future of X (category-name)
[Your exploration here. Be genuine. Think freely. Make connections.
This isn't a report — it's thinking out loud, captured.]
Guidelines:
Option A: Config file (recommended) — Create data/dream-config.json:
{
"topics": [
"future:What could this project become?",
"creative:A wild idea worth exploring",
"reflection:Looking back at recent work"
]
}
This keeps your customizations outside the skill directory (safe for skill updates).
Option B: Edit script directly — Modify the DEFAULT_TOPICS array in should-dream.sh. Format: category:prompt
Default categories:
future — What could [thing] become?tangent — Interesting technology or concepts worth exploringstrategy — Long-term thinkingcreative — Wild ideas that might be crazy or brilliantreflection — Looking back at recent workhypothetical — What-if scenariosconnection — Unexpected links between domainsAdd domain-specific topics relevant to your work. The prompt should spark genuine exploration, not busywork.
In data/dream-state.json:
Add domain-specific topics relevant to your work. The prompt should spark genuine exploration, not busywork.
In data/dream-state.json:
Lower dreamChance for more sporadic dreaming. Raise maxDreamsPerNight for more prolific nights.
Generated Mar 1, 2026
A creative agency uses Dreaming during overnight hours to generate innovative campaign ideas and unexpected connections between client brands and cultural trends. The AI explores hypothetical scenarios and creative concepts, capturing them for morning review by strategists to spark brainstorming sessions.
A scientific research lab employs Dreaming to explore tangential ideas and future implications of ongoing experiments during low-activity periods. The AI reflects on recent data and generates hypothetical connections between domains, providing researchers with novel insights for further investigation.
A tech startup uses Dreaming to contemplate long-term product evolution and user experience improvements during quiet hours. The AI explores future scenarios and strategic reflections, outputting ideas that inform roadmap planning and feature prioritization in team meetings.
An online education platform leverages Dreaming to generate creative lesson ideas and interdisciplinary connections during off-peak hours. The AI explores hypothetical teaching methods and reflection topics, producing content drafts for educators to refine into engaging course materials.
A healthcare organization implements Dreaming to ponder future medical technologies and patient care strategies during nighttime. The AI explores hypothetical advancements and reflections on recent cases, offering insights that support innovation workshops and policy development.
Offer Dreaming as a premium feature within an AI agent platform, charging monthly fees for enhanced creative exploration and output storage. Revenue comes from tiered subscriptions based on dream frequency, topic customization, and integration depth with other tools.
Provide bespoke Dreaming setups for enterprises, including tailored topic configurations, integration with existing workflows, and training for teams. Revenue is generated through project-based fees and ongoing support contracts for optimizing dream outputs.
Monetize the creative outputs from Dreaming by licensing generated ideas, scenarios, and reflections to content creators, researchers, or media companies. Revenue streams include one-time licensing fees or royalties based on usage of the AI-generated dream content.
💬 Integration Tip
Start by configuring quiet hours to match low-activity periods in your workflow, and use the config file for topics to easily update prompts without modifying core scripts.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection