Menü
Reads all memory, rules, docs, and the codebase to rebuild a fresh mental model of the project, then updates the memory files to reflect actual current state. Use when starting a new session or when memory feels stale.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | refresh-memory |
| description | Reads all memory, rules, docs, and the codebase to rebuild a fresh mental model of the project, then updates the memory files to reflect actual current state. Use when starting a new session or when memory feels stale. |
This skill rebuilds the agent's mental model of the project by reading deterministic state, exploring the actual codebase, and updating the heuristic memory files to reflect current reality.
/hyper-refresh-memory.Read Baseline State
spec/compiled/architecture.yml (the Hypergraph).spec/compiled/SuperPRD.md and all MiniPRD_*.md files..agents/memory/ and .agents/rules/.Explore the Current Codebase
src/, tests/, etc.).Synthesize Findings
Refresh the Memory Files
activeContext.md: Update with the current development focus, recent changes, and immediate next steps.systemPatterns.md: Update with new recurring patterns. Remove replaced ones. Document the actual architecture.productContext.md: Update if product goals have evolved or features have changed.Sync Documentation
.agents/memory/systemPatterns.md or the relevant .agents/rules/ file.architecture.yml. If the Hypergraph is out of sync with reality, instruct the user to run /hyper-discover or /hyper-audit to deterministically reconcile it.Verify Consistency
Updates all project documentation after code or skill changes. Always reads actual implementation before writing. Covers README, CHANGELOG, docs/, AGENTS.md, memory files, and skills-info.md. Use after completing any feature, fix, refactor, or skill update.
Compacts the current conversation into a handoff document so a fresh agent can continue the work. Saves to the OS temp directory, not the workspace. Pass an optional argument describing what the next session will focus on.
Documents the process, methodology, and decisions of the current session as a reproducible narrative. Saves to spec/process/ in the workspace so the journey can be understood and recreated by others.
Scaffolds a new project by conducting an interview to collect metadata and generating standard repository documentation files from the framework templates. Use when setting up a new repository.
Run this after /hyper-tutorial-run to turn tutorial failures into a structured, constraint-aware goal prompt. Interviews the user about their goal and what may/may not be changed, then generates a paste-ready prompt for a new Claude Code fix session. Does NOT re-run tutorial commands.
Generates a markdown tutorial from an integration test or user-provided files through iterative LLM + human collaboration. Tutorials are saved to tutorials/<name>/ with organized supporting files.