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。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/majiayu000/claude-skill-registry --skill mem0-sync命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
LLM token logprobs and calibration. Per-decision confidence, ECE, Brier, reliability diagrams, low-confidence triage.
Analyze LLM token logprobs and calibration. Use for per-decision confidence, ECE, Brier scores, reliability diagrams, and low-confidence triage.
回顾最近 N 天的 Claude Code 使用记录——扫描原始会话数据,按主题分组汇总"我都做了什么",并从个人操作系统视角输出模式、风险与增删建议。当用户说 /recap、"看看我这几天做了什么"、"回顾一下我最近的会话"、"这两天我用 claude 干了啥"、"活动回顾" 时使用。
基于 SOC 职业分类
正在显示 SKILL.md
| name | mem0-sync |
| description | Auto-sync session context, decisions, and patterns to Mem0 for cross-session continuity |
| tags | ["mem0","sync","session","memory","continuity","persistence"] |
| user-invocable | true |
| auto-invoke | session-end |
| context | inherit |
Automatically synchronize session context to Mem0 for seamless cross-session continuity. This skill executes MCP calls to persist decisions, patterns, and session summaries.
mem0-pre-compaction-sync.sh hook/mem0-sync to force sync mid-sessionExecute these MCP calls based on the sync context provided:
mcp__mem0__add_memory({
text: "Session Summary: {task_summary}",
user_id: "{project}-continuity",
metadata: {
type: "session_summary",
status: "{status}",
has_blockers: {has_blockers},
has_next_steps: {has_next_steps}
},
enable_graph: true
})
For each decision in the decision log that hasn't been synced:
mcp__mem0__add_memory({
text: "{decision_content}",
user_id: "{project}-decisions",
metadata: {
category: "{category}",
outcome: "success"
},
enable_graph: true
})
For each agent pattern that was learned:
mcp__mem0__add_memory({
text: "{pattern_description}",
user_id: "{project}-agents",
agent_id: "skf:{agent_type}",
metadata: {
category: "{category}",
outcome: "{success|failed}"
},
enable_graph: true
})
For patterns that apply across projects:
mcp__mem0__add_memory({
text: "{best_practice}",
user_id: "skillforge-global-best-practices",
metadata: {
project: "{project}",
category: "{category}",
outcome: "success"
},
enable_graph: true
})
.claude/coordination/.decision-sync-state.jsonenable_graph: true for relationship extraction{project}-continuity: Session summaries{project}-decisions: Architectural decisions{project}-agents: Agent-specific patternsskillforge-global-best-practices: Cross-project patternsrecall - Search and retrieve from Mem0context-compression - Compress context before syncbrainstorming - Generate decisions worth syncing