clawql-composed-mcp-workflows
Apply proven end-to-end recipes combining search/execute, memory, notify, schedule, and optional tools.
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
Apply proven end-to-end recipes combining search/execute, memory, notify, schedule, and optional tools.
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
Persist durable session outcomes with memory_ingest using stable titles, append threading, and wikilinks.
Deep ClawQL Obsidian vault workflows using memory_ingest and memory_recall MCP tools—structured insights, wikilink graphs, session threading, verbatim captures, and recall queries. Use when persisting important context, building a knowledge graph, starting tasks that may depend on prior vault notes, or when the user mentions Obsidian, the vault, memory, or long-running project context.
Workflow recipes for the ClawQL MCP audit tool. The audit tool is ClawQL Core (always registered — no CLAWQL_ENABLE_AUDIT); this skill is optional guidance for append/list/clear patterns during multi-step runs.
Deep ClawQL Obsidian vault workflows using memory_ingest and memory_recall MCP tools—structured insights, wikilink graphs, session threading, verbatim captures, and recall queries. Use when persisting important context, building a knowledge graph, starting tasks that may depend on prior vault notes, or when the user mentions Obsidian, the vault, memory, or long-running project context.
Use the cache MCP tool (ClawQL Core, always on) as ephemeral scratch state during active sessions.
Run isolated code snippets via sandbox_exec with safe persistence/session patterns.
| name | clawql-composed-mcp-workflows |
| description | Apply proven end-to-end recipes combining search/execute, memory, notify, schedule, and optional tools. |
search -> execute(read) -> execute(write) -> execute(read) -> memory_ingest.memory_recall -> search/execute -> audit -> notify -> memory_ingest.knowledge_search_onyx -> execute -> memory_ingest -> notify.schedule(create/trigger dry_run) -> notify -> memory_ingest.docs/recipes/README.md