当用户需要根据本机 ax 会话证据,复盘某个已交付功能、提交、日期或成果是如何完成时使用。
Scanned 9/1/2026
Install to Claude Code
npx -y skills add YangsonHung/awesome-agent-skills --skill ax-extract-workflow-cn --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Ax Extract Workflow Cn?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/yangsonhung-ax-extract-workflow-cn)More formats (shields.io, HTML) on the badges page.
---
name: ax-extract-workflow-cn
description: 当用户需要根据本机 ax 会话证据,复盘某个已交付功能、提交、日期或成果是如何完成时使用。
---
# ax 工作流复盘
## Overview
从本机 ax 数据中重建一个已交付成果背后的工作流。先确定锚点,再找到相关会话,查看对话、工具、技能、提交和子代理委派记录,最后写出一份紧凑、可追溯的复盘。
本技能假设已经安装 `ax`,相关会话已经完成 ingest,并且本机 ax 数据库可访问。
## 何时使用
当用户有以下需求时使用本技能:
- 想知道某个功能、PR、演示或成果是怎么交付的
- 想复盘某个结果为什么成功
- 想查看某个日期、提交、主题或仓库事件附近的工作流
- 想找出哪些会话、工具、技能或关键决策促成了某个成果
- 想把过去一次有效的 agent 工作整理成可复用做法
## 不要使用
以下场景不应使用本技能:
- 只是查看最近做了什么
- 尚未查看历史证据就开始写新的实施计划
- 与具体成果、日期或提交无关的项目状态汇报
- 本机没有可用 ax 数据,却要求复盘细节
## 使用说明
1. 确定锚点:
- 提交 SHA:直接使用该提交。
- 日期:查看该日期前后的短窗口。
- 主题或成果名称:先搜索相关提交。
- 当前仓库的近期工作:查看当前仓库最近会话。
2. 查找候选会话:
```bash
ax recall "<topic>" --sources=commit --json
ax sessions near <sha> --json
ax sessions around <date> --days=3 --json
ax sessions here --days=14 --json
```
3. 选择最多五个会话。优先选择回合数较多、匹配提交、涉及相关文件,或有相关工具和技能使用记录的会话。
4. 查看每个选中的会话:
```bash
ax sessions show <id> --json
ax sessions show <id> --by-role
ax sessions show <id> --expand=<subagent-uuid>
```
5. 如果 ax 无法连接数据库,告诉用户先启动 ax 服务,然后停止。不要编造证据。
6. 基于证据写复盘:
- 有序工作流:先做了什么,接着做了什么,最后如何收尾。
- 技能和工具作用:说明关键技能或工具各自产出了什么。
- 关键决策:记录用户引导、取舍或改变方向的节点。
- 可复用做法:总结下一次如何复现类似流程。
## 输出
输出 Markdown,包含:
- 一段摘要
- 按顺序排列的工作流时间线
- 带会话 id、提交或命令的关键证据
- 证据足够时,给出简短可复用流程
语气保持事实化。引用本机证据。无法确认的地方明确标注未知。
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!
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.
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', ...
**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. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.