查看 omd pathfinder 当前地图前沿票,并拉取已落地的 AFK research 结果(pull 回流 + 预算内自续)。Trigger:/omd-tickets、前沿、看票、研究结果回来了吗。
Scanned 9/3/2026
Install to Claude Code
npx -y skills add AbyssCN/oh-my-dag --skill omd-tickets --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Omd Tickets?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/abysscn-omd-tickets)More formats (shields.io, HTML) on the badges page.
---
name: omd-tickets
description: 查看 omd pathfinder 当前地图前沿票,并拉取已落地的 AFK research 结果(pull 回流 + 预算内自续)。Trigger:/omd-tickets、前沿、看票、研究结果回来了吗。
---
# /omd-tickets — 前沿与回流
调 omd MCP server 的 `map_tickets` 工具(可能带前缀 `mcp__omd__`;未加载先 ToolSearch "map_tickets")。多张开放地图时带 `slug` 参数。
这个工具做三件事,输出直接转述给用户:
1. **回流**:把已落地的 AFK research 结果折进地图(母票自动裁决,`## children` 段孵出子票);
2. **自续**:新孵的 research 子票在预算内(`OMD_PATH_RESEARCH_BUDGET`,默认 12,跨 session 计数)自动续派后台;预算耗尽会提示——转告用户可调预算或用 `map_prefetch` 显式追加;
3. **前沿**:列出当前可动的票 + 状态计数;若区域散尽(全部 task 票已裁且编译通过)会提示可 `/omd-deliver`。
AFK research 是 detached 子进程,对话期间它在后台跑;用户问"研究跑完了吗"就调一次这个工具拉结果。前沿里的 grill/task 票需要 owner 裁决——列出来并给出你的推荐裁决,等 owner 用 /omd-rule 定夺。
## gh 后端的折入语义(与 md 等价,来源不同)
后端是 GitHub Issues 时,回流从 md 落盘文件换成 issue 状态,语义不变:
- **research-done 评论回流**:AFK 研究在 GitHub Actions 上跑完,结果作为 bot 评论落到 research 票上并打 `research-done` label;`map_tickets` 折入时读这条评论(md 则读 `.omd/pathfinder/results/` 落盘文件)。
- **children 挂母票 sub-issue**:结果里 `## children` 段孵出的子票经原生 sub-issue 挂在母票下(血缘 = sub-issue,前沿依赖 = blocked-by);子票默认 blockedBy 母票。
- **警告不 ack、下轮重试**:评论缺失 / 解析失败 → 票标注警告(输出里 `⚠ … 未折入`)、**不摘 `research-done` label**(即不 ack),下次 `map_tickets` 重试;绝不静默跳过、也不造假占位裁决。成功折入才摘 label(幂等锚点)。
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.