memory by yonatangross/orchestkit
npx skills add https://github.com/yonatangross/orchestkit --skill memory统一的读取端记忆技能,包含搜索、加载、同步、历史记录和可视化子命令。
SUBCOMMAND = "$ARGUMENTS[0]" # 第一个标记:search, load, history, viz, status
QUERY = "$ARGUMENTS[1]" # 第二个标记及之后:搜索查询或标志
# $ARGUMENTS 是完整的字符串(CC 2.1.59 索引访问)
/ork:memory search <query> # 搜索知识图谱
/ork:memory load # 在会话开始时加载上下文
/ork:memory history # 查看决策时间线
/ork:memory viz # 可视化知识图谱
/ork:memory status # 显示记忆系统健康状态
如果调用时没有子命令,询问用户需要什么:
AskUserQuestion(
questions=[{
"question": "您需要什么记忆操作?",
"header": "操作",
"options": [
{"label": "search", "description": "在知识图谱中搜索决策和模式", "markdown": "```\n搜索知识图谱\n──────────────────────\n 查询 ──▶ mcp__memory ──▶ 结果\n\n 标志:\n --category 按类型过滤\n --agent 限定到特定代理\n --limit N 最大结果数\n --global 跨项目搜索\n```"},
{"label": "load", "description": "为此会话加载相关上下文", "markdown": "```\n加载会话上下文\n────────────────────\n 自动检测项目 ──▶\n ┌────────────────────┐\n │ 近期决策 │\n │ 活动模式 │\n │ 项目实体 │\n └────────────────────┘\n 标志:--project, --global\n```"},
{"label": "history", "description": "查看决策时间线", "markdown": "```\n决策时间线\n─────────────────\n ┌──── 2月28日 ────────────┐\n │ 使用 Postgres 而非 Mongo │\n ├──── 2月27日 ────────────┤\n │ 采用 MVC 模式 │\n ├──── 2月26日 ────────────┤\n │ 选择 JWT 而非会话 │\n └────────────────────────┘\n 标志:--since, --mermaid\n```"},
{"label": "viz", "description": "将知识图谱可视化为 Mermaid 图", "markdown": "```\n知识图谱可视化\n───────────────────\n 实体 ──▶ Mermaid 图表\n\n [项目] ──使用──▶ [Postgres]\n │ │\n └──拥有──▶ [认证] ──使用──▶ [JWT]\n\n 输出:Mermaid 代码块\n```"},
{"label": "status", "description": "检查记忆系统健康状态", "markdown": "```\n记忆健康检查\n───────────────────\n ┌─────────────────────┐\n │ MCP 服务器 ✓/✗ │\n │ 实体数量 N │\n │ 关系数量 N │\n │ 最后写入 日期 │\n │ 图谱大小 N KB │\n └─────────────────────┘\n```"}
],
"multiSelect": false
}]
)
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
加载详细信息:Read("${CLAUDE_SKILL_DIR}/references/memory-commands.md") 以获取每个子命令的完整用法、标志、输出格式和上下文感知结果限制。
| 子命令 | 用途 |
|---|---|
search | 搜索过去的决策、模式、实体。支持 --category(映射到 metadata.category)、--limit、--agent(按 agent_id 限定范围)、--global 过滤标志 |
load | 在会话开始时自动加载相关记忆。支持 --project、--global |
history | 决策时间线,支持表格、Mermaid 或 JSON 输出。支持 --since、--mermaid |
viz | 将知识图谱渲染为 Mermaid 图表。另请参阅 Read("${CLAUDE_SKILL_DIR}/references/mermaid-patterns.md") |
status | 记忆系统健康检查 |
提取第一个参数作为子命令
如果没有子命令 -> AskUserQuestion
验证子命令是其中之一:search, load, history, viz, status
解析剩余的标志
检查 --agent <agent-id> 标志 → agent_id: "ork:{agent-id}"
根据子命令路由到相应的处理程序。
根据操作类型格式化输出。
| 规则 | 影响 | 涵盖内容 |
|---|---|---|
entity-extraction-patterns (加载 ${CLAUDE_SKILL_DIR}/rules/entity-extraction-patterns.md) | 高 | 实体类型、关系类型、图谱查询语义 |
deduplication-strategy (加载 ${CLAUDE_SKILL_DIR}/rules/deduplication-strategy.md) | 高 | 编辑覆盖写入模式、基于锚点的插入、验证 |
加载详细信息:Read("${CLAUDE_SKILL_DIR}/references/session-resume-patterns.md") 以获取 CC 2.1.31 恢复提示、结束前的上下文捕获以及针对 PR、问题和实现的恢复工作流程。
ork:remember - 存储决策和模式(写入端)每周安装次数
135
代码仓库
GitHub 星标数
132
首次出现
2026年2月6日
安全审计
安装于
gemini-cli130
opencode130
codex127
github-copilot126
cursor125
kimi-cli122
Unified read-side memory skill with subcommands for searching, loading, syncing, history, and visualization.
SUBCOMMAND = "$ARGUMENTS[0]" # First token: search, load, history, viz, status
QUERY = "$ARGUMENTS[1]" # Second token onward: search query or flags
# $ARGUMENTS is the full string (CC 2.1.59 indexed access)
/ork:memory search <query> # Search knowledge graph
/ork:memory load # Load context at session start
/ork:memory history # View decision timeline
/ork:memory viz # Visualize knowledge graph
/ork:memory status # Show memory system health
If invoked without a subcommand, ask the user what they want:
AskUserQuestion(
questions=[{
"question": "What memory operation do you need?",
"header": "Operation",
"options": [
{"label": "search", "description": "Search decisions and patterns in knowledge graph", "markdown": "```\nSearch Knowledge Graph\n──────────────────────\n query ──▶ mcp__memory ──▶ results\n\n Flags:\n --category Filter by type\n --agent Scope to agent\n --limit N Max results\n --global Cross-project\n```"},
{"label": "load", "description": "Load relevant context for this session", "markdown": "```\nLoad Session Context\n────────────────────\n Auto-detect project ──▶\n ┌────────────────────┐\n │ Recent decisions │\n │ Active patterns │\n │ Project entities │\n └────────────────────┘\n Flags: --project, --global\n```"},
{"label": "history", "description": "View decision timeline", "markdown": "```\nDecision Timeline\n─────────────────\n ┌──── Feb 28 ────────────┐\n │ Used Postgres over Mongo│\n ├──── Feb 27 ────────────┤\n │ Adopted MVC pattern │\n ├──── Feb 26 ────────────┤\n │ Chose JWT over sessions │\n └────────────────────────┘\n Flags: --since, --mermaid\n```"},
{"label": "viz", "description": "Visualize knowledge graph as Mermaid", "markdown": "```\nKnowledge Graph Viz\n───────────────────\n Entities ──▶ Mermaid diagram\n\n [Project] ──uses──▶ [Postgres]\n │ │\n └──has──▶ [Auth] ──uses──▶ [JWT]\n\n Output: Mermaid code block\n```"},
{"label": "status", "description": "Check memory system health", "markdown": "```\nMemory Health Check\n───────────────────\n ┌─────────────────────┐\n │ MCP server ✓/✗ │\n │ Entity count N │\n │ Relation count N │\n │ Last write date │\n │ Graph size N KB │\n └─────────────────────┘\n```"}
],
"multiSelect": false
}]
)
Load details: Read("${CLAUDE_SKILL_DIR}/references/memory-commands.md") for full usage, flags, output formats, and context-aware result limits for each subcommand.
| Subcommand | Purpose |
|---|---|
search | Search past decisions, patterns, entities. Supports --category (maps to metadata.category), --limit, --agent (scopes by agent_id), --global filter flags |
load | Auto-load relevant memories at session start. Supports --project, --global |
history |
Extract first argument as subcommand
If no subcommand -> AskUserQuestion
Validate subcommand is one of: search, load, history, viz, status
Parse remaining flags
Check for --agent <agent-id> flag → agent_id: "ork:{agent-id}"
Route to appropriate handler based on subcommand.
Format output appropriate to the operation.
| Rule | Impact | What It Covers |
|---|---|---|
entity-extraction-patterns (load ${CLAUDE_SKILL_DIR}/rules/entity-extraction-patterns.md) | HIGH | Entity types, relation types, graph query semantics |
deduplication-strategy (load ${CLAUDE_SKILL_DIR}/rules/deduplication-strategy.md) | HIGH | Edit-over-Write pattern, anchor-based insertion, verification |
Load details: Read("${CLAUDE_SKILL_DIR}/references/session-resume-patterns.md") for CC 2.1.31 resume hints, context capture before ending, and resume workflows for PRs, issues, and implementations.
ork:remember - Store decisions and patterns (write-side)Weekly Installs
135
Repository
GitHub Stars
132
First Seen
Feb 6, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
gemini-cli130
opencode130
codex127
github-copilot126
cursor125
kimi-cli122
AI 代码实施计划编写技能 | 自动化开发任务分解与 TDD 流程规划工具
47,700 周安装
Decision timeline with table, Mermaid, or JSON output. Supports --since, --mermaid |
viz | Render knowledge graph as Mermaid diagram. See also Read("${CLAUDE_SKILL_DIR}/references/mermaid-patterns.md") |
status | Memory system health check |