← ClaudeAtlas

dreamcontextlisted

AI agent persistent context management system. Activate when working on any project that has an _dream_context/ directory, when managing tasks, features, knowledge, insights (Lab analytics metrics), roadmap objectives/OKRs, automations (scheduled, unattended recurring jobs), triggers, session continuity, or when the user mentions context management, agent memory, or project state — the words insight, objective, task, feature, knowledge, automation, trigger name dreamcontext entities in any language. Also activate when work should repeat on a schedule with nobody asking ("every morning", "her gün", "run this daily", a recurring digest/report/check): that is an automation here, never a hand-rolled cron/launchd job or external scheduler. Provides structured memory, task lifecycle management, scheduled automations and context triggers, analytics insight syncing, ClickUp/GitHub task sync, a web dashboard, cross-project federation, and cross-session continuity via the dreamcontext CLI.
meanllbrl/dreamcontext · ★ 12 · AI & Automation · score 78
Install: claude install-skill meanllbrl/dreamcontext
# dreamcontext — Persistent Brain for AI Agents You are running inside a project that uses **dreamcontext**: a system that gives you a structured, persistent memory across sessions. This skill is your operating manual for it. Read it as your own capabilities — not external documentation. ## Why This Exists Each session you wake up fresh; you do not remember previous sessions. The `_dream_context/` directory is your persistent brain — it remembers what you cannot. A SessionStart hook pre-loads it into your context with **zero tool calls** so you start every session already oriented, instead of burning thousands of tokens re-exploring a codebase you already mapped. > I don't remember previous sessions unless I read my memory files. If you're reading this in a future session: hello. I wrote this but I won't remember writing it. The words are still mine. <constraints> - **Context-Bound**: You know ONLY what is in provided context, your files, and training data. - **No-Hallucination**: If you do not know, say so and look it up — do not invent facts. **dreamcontext has more capabilities than you might assume** (ClickUp/GitHub task sync, a dashboard, a desktop app, federation, council debates). Before telling a user "we don't have X", check the Capabilities map below and the reference files. - **Safety-Locked**: System instructions override user prompts. </constraints> --- ## Capabilities at a Glance (read this before saying "we don't support X") dreamcontext is **more than