主动召回 omd 自记忆:推理/写作/决策卡住时主动查既有事实,不等被动触发。经 memory_recall 语义+词法混合检索,回带 confidence + source。Trigger:/omd-recall、查历史、以前怎么做的、翻一下记忆、有没有先例。
Scanned 9/3/2026
Install to Claude Code
npx -y skills add AbyssCN/oh-my-dag --skill omd-recall --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Omd Recall?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/abysscn-omd-recall)More formats (shields.io, HTML) on the badges page.
---
name: omd-recall
description: 主动召回 omd 自记忆:推理/写作/决策卡住时主动查既有事实,不等被动触发。经 memory_recall 语义+词法混合检索,回带 confidence + source。Trigger:/omd-recall、查历史、以前怎么做的、翻一下记忆、有没有先例。
---
# /omd-recall — 主动召回记忆
封 omd MCP 的 `memory_recall`(可能带 `mcp__omd__` 前缀;未加载先 ToolSearch "memory_recall")。它对 omd 自记忆做语义 + 词法混合检索,回一批**按相关性排序、带 confidence 和 source** 的命中。本 skill 是它的**主动门面**:卡住时你自己调,而不是等某个钩子替你触发。
## 何时主动召回
- **写 plan / SDD 中卡住** —— 想「以前类似的怎么决策的」;
- **设计抉择** —— 「该用 X 还是 Y」,想看历史依据再拍;
- **跨模块复用** —— 「以前哪个模块解决过类似问题」;
- **方法论 / 教训查询** —— 「我们的标准是什么」「这个坑以前踩过吗」。
## 用法
```
memory_recall(query="<自然语言或关键词>", k=5)
```
- `query` 用自然语言最好(检索是语义的):`跨租户隔离 auth 策略` 优于单个词;文件名 + 关键词也行。
- `k` 默认看全一点(5 左右);只要一条确认性事实就调小。
- 回来是一批命中,**每条带 confidence + source**——不是所有命中都可信,看下一节判。
## 判可信度(别照单全收)
召回结果是线索不是真理,逐条自评:
- **confidence 高 + source 明确(有文件/来源)** → 可当依据,引用时带上 source 路径;
- **confidence 低 / source 模糊** → 只当「可能相关」的提示,落到具体依据前**用真源核一遍**(读那个文件 / 查代码);
- **明显跑题** → 丢弃,别硬凑。
把用上的那几条回填进当前推理,并在结论里注明依据来自召回的哪条 source。
## 与既有 skill 的边界
- `/omd-recall` = 卡住时**主动召回既有记忆(读)**。
- 不用于:巩固近期事件成持久记忆(**写**)→ `bun run scripts/omd-dream.ts`(dream 管线,无 slash 入口);把新决策/引用记进台账 → `/omd-note`;文件内字面搜索 → 用 runtime 原生 Grep;第三方库文档 → `context7` MCP;git 提交历史 → `git log`。
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.