一键导入
ralph-memory-dream
Consolidate Ralph/Codex handoffs and ledgers into reviewable memory candidates.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Consolidate Ralph/Codex handoffs and ledgers into reviewable memory candidates.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | ralph-memory-dream |
| description | Consolidate Ralph/Codex handoffs and ledgers into reviewable memory candidates. |
Use this skill when the user asks to consolidate, summarize, clean, dream over, or improve Ralph/Codex memory.
python3 scripts/memory/dream.py --dry-run.~/.ralph-codex/reports/memory/dream-latest.md.python3 scripts/memory/dream.py --auto-update-state when future Codex sessions should load high-confidence dream learnings through L4.python3 scripts/memory/dream.py --vault-inbox when a reviewable MiVault inbox digest is useful.python3 scripts/memory/dream-scheduler.py --catch-up --target-time 11:30 for the same non-blocking policy used by the SessionStart hook.The dream script is deterministic and offline. RED content must stay local, must not be printed, and must not be written into memory layers, reports, vault notes, or external tools. L4 is auto-usable session memory, not canonical memory. If candidate promotion is needed, use an approved patch flow and keep a rollback path.
Improve, audit, simplify, rewrite, or migrate prompts, tool descriptions, agent instructions, and prompt stacks for GPT-5.6 Sol or the GPT-5.6 family. Use for outcome-first prompt design, autonomy boundaries, tool routing, PTC, grounding, verbosity, reasoning effort, and prompt evals.
Apply a deep, design-minded engineering workflow for complex work that needs careful planning, iteration, and simplification.
Use when preparing or running a Claude CLI agentic engineering review through claude -p for repository audits, architecture analysis, system design, security review, large refactors, specs, RFCs, or evidence-grounded long-form engineering analysis.
Use when preparing or running a ZCode GLM-5.2 agentic builder workflow through zcode --prompt for fast implementation, iterative code generation, focused fixes, and validation on an existing repository.
Apply adversarial opposite-analysis to plans, specs, architecture, code changes, and claims. Use when the user asks for adversarial review, opposing analysis, contrarian review, red-team reasoning, or Z.ai and MiniMax cross-checks through the Ralph MCP router.
Review and adjudicate Bugbot, Cursor, Seer, and similar automated PR feedback with local evidence before accepting, fixing, or dismissing findings.