#教程/实践

更新：根据反馈，我想出了一个更好的提示词版本 让 Codex 查看你的会话、Memories 和 Chronicle，识别模式，复用已有的内容，只创建最小可用的 skill、subagent 或自动化。 "回顾我最近 30 天的工作，如果可用历史更短则回顾全部可用历史，找出值得打包的重复性手动工作流。 按以下顺序使用可用证据： - 最近的 Codex 会话和任务摘要。 - Codex Memories 和 rollout 摘要，以发现跨会话重复出现的模式。 - Chronicle（如果已启用），以发现 Codex 之外的重复性工作。仅将 Chronicle 用于发现；尽可能在相关源系统中确认重要细节。 - 现有的 skills、自定义 agents 和自动化，以便复用或扩展已有的内容，而不是重复创建。 广泛寻找那些重复、耗时、易出错、上下文繁重或能从一致流程中受益的工作。包括编码、研究、写作、规划、沟通、运营、分析和个人事务方面的工作流。 仅当候选对象满足以下条件时才采取行动： - 至少出现过两次，或明显可能重复出现且重复成本高昂； - 具有稳定的输入、可重复的流程，以及明确的输出或停止条件； - 能实质性提升速度、质量、一致性或可靠性； - 尚未被充分覆盖。 选择最小的合适形式： - Skill：可复用的工作流或操作手册。 - 自定义 subagent：适合委派的有界专家角色或调查任务。 - 自动化：定时或周期性的检查、报告、提醒或监控。 - 跳过：过于一次性、模糊、敏感或证据不足而无法打包的工作。 首先产出一份简洁的候选清单，包含： - 重复的工作流 - 支持性证据和日期 - 频率/置信度 - 推荐形式：skill、subagent、自动化、扩展现有内容或跳过 - 为什么值得或不值得创建 然后只创建高置信度且缺失的项目。保持它们范围狭窄、实用、感知来源且易于验证。不要创建推测性、重叠或过于宽泛的资产。 最后总结： - 你创建或扩展了什么 - 你刻意跳过了什么 - 在打包之前还需要更多证据的内容

自动模式的两项更新： · 现已在 Pro 套餐中可用 · 除 Opus 4.7 外，现也已支持 Sonnet 4.6 按 Shift+tab，让 Claude 运行。

I built "zero2claude", a free course that takes people from zero terminal experience to shipping with Claude Code. The curriculum goes from absolute zero → software basics → Claude Code fundamentals → advanced usage. No shortcuts, no assumptions. 17,000+ students. 7 languages. ~500 active hourly. No marketing. No ads. Pure word of mouth. The entire platform? Built and operated by one person with Claude Code. Lighthouse audit: ✅ Performance : 96 ✅ Accessibility : 100 ✅ Best Practices : 100 ✅ SEO : 100 Production stats: ~6.4M requests/day. 74 req/sec sustained. <0.003% error rate. Claude Code doesn't just write code. It builds production-grade, scalable products. The best way to grow Claude Code adoption isn't to simplify the tool. It's to level up the people. Give fishing rods, not fish. Free. No paywall. My contribution to the community. Link in the comments 👇

If you are managing multiple machines across clusters and farms, you could ask Grok Build to spin off a sub-agent SSH tunnel into the machines while interacting with tmux sessions for you. Thanks to @skcd42 for the tips. Now I can fully live inside the main Grok Build instance without additional tabs to other clusters.

It was fun trying to get this... ideating with AI and and crafting the prompt. Ref images + the Prompt. 🙌😅 { "title":"Soccer Match Selfie Video", "style":"Ultra realistic smartphone selfie footage, documentary realism, authentic human interaction, natural imperfections, NOT polished commercial footage.", "character_consistency":"Use ALL FIVE attached character refs exactly throughout the video. Preserve accurate face, hairstyle, age, skin tone, freckles, glasses, sideburns, ethnicity, smile shape, and clothing style.", "characters":[ "South Asian male, curly dark hair, black round glasses, trimmed beard, oversized dark sweatshirt.", "East Asian female, long straight black hair, freckles, pastel casual outfit.", "White middle-aged businessman, short brown hair, receding hairline, navy casual jacket.", "White rugged male, thick dark hair, dramatic sideburns, black bomber jacket.", "White woman, shoulder-length brown hair, cheerful smile, black casual outfit." ], "environment":"Huge modern soccer stadium at night, bright floodlights, LED scoreboard glow, cheering crowd, green football pitch visible.", "camera":"Front-facing smartphone camera, handheld shaky motion, wide-angle selfie distortion, autofocus hunting, motion blur, exposure changes, cropped faces, imperfect framing.", "actions":[ "calm pre-game selfie", "laughing together", "singing chants", "near-goal anticipation", "dramatic reactions", "goal celebration", "jumping and screaming", "happy exhausted ending selfie" ], "behavior":{ "south_asian_male":"holds phone and reframes constantly", "east_asian_female":"warm natural smile and laughter", "businessman":"calm then emotional", "rugged_male":"intense dramatic reactions", "white_woman":"points excitedly toward field and camera" }, "wardrobe":"hoodies, soccer scarves, oversized sweaters, windbreakers, casual jackets, dark streetwear.", "prompt":"Ultra-realistic handheld selfie video of five friends attending a packed nighttime soccer match. The South Asian man films with a smartphone while all five crowd naturally into frame. They laugh, chant, joke, react to near goals, scream after scoring, wave scarves, bounce with the crowd, and celebrate wildly together. Realistic stadium lighting, social-media-style footage, immersive sports atmosphere, authentic candid energy." }