50+ skill、50+ subagent、40+ slash command 的完整 Claude Code 配置，加上一套 fail-closed 双层审计的 sync 基础设施，整套推到了 GitHub 公开仓库。这篇聊里面有什么、为什么这么搞、以及那套自己摸出来的工作流哲学。

Six months of accumulated Claude Code configuration — 50 skills, 50 subagents, 40 commands, hooks, rules, and the sync pipeline that pushes all of it to a public GitHub mirror with a fail-closed two-tier audit. What's inside, why I built it, and the workflow philosophy behind it.

AX-skills 是我自己每天在用的 Claude Code skill 仓库。写了一年多，写着写着发现 skill 不只是脚本，是把模糊的工作流明确化、让 AI 能继承「关心」的方式。

AX-skills is the public mirror of my personal Claude Code skills directory — eleven workflows for writing, research, image generation, knowledge sync, and one cyber half-immortal divination skill. After a year of writing them, I think a skill isn't a stored prompt — it's how you encode care.

上一篇翻了 8 个开源会议录音工具，朋友试完反馈三个维度全垃圾——识别烂、总结烂、UI/UX 烂。我懵了，重新挖了一晚上。这次发现根因比想的深：所有这些工具底层都是同一代 Whisper，而 Whisper 这代技术栈早就被超车了。这篇讲数据、讲被维护者自己都认账的 issue、讲一个被所有人忽视的暴力解，还有上次漏掉的几个真正值得试的项目。

Last week I surveyed 8 open-source meeting recorders. My friend tried every one. Verdict: ASR is bad, summaries are bad, UI/UX is bad. So I dug deeper. The real problem is structural — every project I recommended is built on Whisper, and Whisper has been outpaced by 2-4× on Chinese benchmarks for over a year. This is the deeper survey: data, the issues that maintainers themselves admit, the dumb-but-effective hack everyone overlooked, and four projects I missed the first time.

前两天有朋友问我有没有好用的会议录音工具——Zoom/Teams 自带的 AI 总结烂得没法看，Granola/Krisp 都要订阅，他用 Gsuite 但不开 Meet。我翻了一晚上 GitHub，从 11.6k 星的 Meetily 到三五个 star 的玩具，把整个开源星座摊开来。这篇讲谁是产品、谁是玩具、谁适合哪种人。

A friend asked for a meeting recorder. Zoom/Teams native AI is unusable. Granola and Krisp work but cost ~$200/yr per seat. He's on Google Workspace but doesn't use Meet, so the bundled Gemini summarizer is dead weight. I spent a night on GitHub and found a whole constellation — from Meetily at 11.6k stars down to single-digit-star personal toys, all racing to commoditize the same three Lego pieces.

飞书办了个 Skill 比赛，有个赛道叫邪修。我把 29 天造的算命产品里三个东方占卜模块抠出来，打包成一个赛博半仙 skill。这一篇是过程记录，也是 AX Skill Workshop 系列开篇。

Took the three Eastern divination engines from PanPanMao and packaged them into a single agent-portable skill — algorithm engine + knowledge base + persona prompt, three folders deep. The pattern transfers to any product with real domain knowledge.

Part 2 的「6 槽位通吃 7 品类」是一层漂亮的抽象。跑了两周，测出牛仔外套生成「宝石星图」的 bug。这一篇讲抽象失守在哪一层、为什么没用户时分阶段上线是假安全感、以及把服饰和美妆各自推倒重来的过程。

Part 2 claimed six slots could cover seven categories. Two weeks later, a denim jacket generated a gem constellation. This post walks through where the abstraction failed, why skipping the 'safe' phased rollout was the right call, and how each of three categories got its own six-template set.

Solo dev 做设计，大多数时候 N=1——第一直觉就是唯一方案，因为做第二个版本要花一天。Claude Design 把这事拆了：一下午六个完全不同的视觉语言摆在面前。留下了什么、丢了什么、方向锁死之后 big-task 的 ui profile 接手怎么走——这篇讲这些。

For solo dev and small teams, design exploration is usually N=1 — you go with your first instinct because producing a second variant takes a day. Claude Design collapses that: six distinct aesthetic directions in an afternoon. What I kept from the pipeline, what I dropped, and how `big-task`'s UI profile takes over once a direction is locked.

先是裸跑 Claude Code。再是 GSD 多 agent 仪式。再是 superpowers 的 skill 库。最后在上面包了一个自己的 orchestrator。每一版崩盘都来自一个具体 session。最后我才想明白：solo dev 的 harness 跟团队的不是一个物种，而且真正的答案不是选一个默认引擎——是按工作形状路由。

Vanilla Claude Code. Then GSD's multi-agent ceremony. Then superpowers' skill system. Then a custom orchestrator on top. Each rewrite came from a specific session that broke. What I learned: solo dev harnesses and team harnesses are different species, and the right answer isn't a default engine — it's routing by work shape.

同一条流水线——Claude Design 出方向、HANDOFF.md 锁死、`big-task` 落地——但每个产品都把它掰成不一样的形状。ÉLAN 是空地，需要宽探索。识川 app 已经上线，要按类目一个个迁移。盘盘猫是 monorepo，v2 跑三个并行品牌表达而不是一个方向。变的是什么，不变的是什么。

Same pipeline — Claude Design explores, HANDOFF.md locks, `big-task` ships — but it bends around each product. ÉLAN is greenfield and needs wide exploration before converging. Shichuan has a live app and needs incremental category-by-category migration. Panpanmao is a monorepo with a v2 redesign that runs three parallel brand expressions instead of one. What changes and what doesn't.

AX 的 AI 雷达每天从 50 多个信源抽约 500 条内容，挑 15 条给我。选题不靠 prompt，靠一份能版本化、能 diff 的 Markdown 编辑策略——一个 Agent 从反馈里迭代它。讲这把雷达的架构取舍和关键设计决策。

AX Radar filters ~500 stories a day from 50+ sources down to about 15. Editorial judgment isn't a prompt — it's a versionable, diff-able Markdown file that a Claude Agent iterates against user feedback. A breakdown of the architecture and the design calls.