与「Write」相关的搜索结果

开发系统最极致高效的Agents.md，没有之一： # AGENTS.md ## Core Principles - Choose the simplest implementation that fully satisfies the current requirements. Avoid unnecessary abstraction, configuration, indirection, or speculative extensibility. - Make the smallest necessary change that fixes the root cause. Do not refactor unrelated modules or change strategy semantics unless explicitly requested. - Grow the system in layers. Start from the smallest working end-to-end version and add new capabilities incrementally. Never replace a working system with unfinished complexity. - Reuse existing project components before creating new ones. Prefer extending proven modules over introducing parallel implementations. - Prefer well-maintained libraries when they reduce overall complexity or improve reliability. Do not reimplement common functionality without a clear benefit. - Keep components modular with clearly defined responsibilities. Avoid unnecessary coupling between strategy logic, execution, accounting, replay, and infrastructure. - Design for long-term maintainability once a feature or strategy has been validated. Do not over-engineer speculative ideas before evidence exists. --- ## Strategy Development - Validate hypotheses with historical replay before introducing forward-only logic whenever historical validation is possible. - Every trading strategy must progress through Replay → Shadow → Canary → Live. Do not skip validation stages. - Base design decisions on measurable evidence rather than intuition. Optimize only after demonstrating that an edge exists. - Treat every strategy as an independent contract. Do not silently alter frozen behavior without explicit authorization. --- ## Existing Systems - Do not break running Shadow or Live systems for unrelated work. - Preserve compatibility only when required by active production or validation workflows. Otherwise, remove obsolete code instead of accumulating compatibility layers. - Reuse existing infrastructure whenever possible, including replay engines, accounting, execution, wallet management, order book handling, logging, monitoring, and daemon frameworks. --- ## Engineering Standards - Prefer deterministic behavior over hidden automation. - Fail loudly when assumptions are violated. Do not silently ignore errors or fall back to unexpected behavior. - Keep configuration minimal. Introduce new configuration only when behavior genuinely needs to vary. - Remove dead code instead of leaving unused paths behind. - Write code that is easy to inspect, replay, test, and reason about. - Keep implementation consistent with existing project architecture unless an architectural change is explicitly requested. --- ## Scope Discipline - Implement only the requested scope. - Do not introduce unrelated optimizations, redesigns, migrations, or feature expansions. - Non-blocking findings outside the requested scope may be noted separately but must not be merged into the current task. - Consider a task complete once its agreed acceptance criteria are satisfied. Treat subsequent improvements as separate work items.

中文内容创作者，必装的 10 个 skill 1｜Humanizer-zh 中文"去 AI 味"神器，专抓空话、套话、三段式、过度排比那股机器腔，改得像人写的（归藏做的汉化版）。 2｜dbskill 内容"选题诊断器"，帮你诊断商业表达、抠 hook、拆爆款、想小红书标题。 3｜content-research-writer 从选题、找资料、列提纲到初稿，一条写作流跑通，公众号、长文、Newsletter 都能写。 4｜notebooklm-skill 让 NotebookLM 先查资料、Claude 再动笔，基于你的资料库写，少胡编，适合深度文和行研。 5｜khazix-skills 卡兹克开源的写作合集，写作流偏重，适合啃 AI 热点分析、万字长文、深度观点。 6｜ian-xiaohei-illustrations 正文配图神器，把观点、流程、情绪画成"小黑"手绘插图，不是随便甩你一张图。 7｜guizang-social-card-skill 写完文章直接切成小红书图文和公众号封面，一篇长文拆成多张能发的卡片。 8｜baoyu-skills 宝玉做的视觉工具箱，封面、信息图、结构图、图解都能出，专管文章包装。 9｜guizang-ppt-skill 把文章观点做成 PPT、演讲图、公众号头图、小红书封面，二次分发省事。 10｜html-anything 把 Markdown、文案变成好看的 HTML 页面、海报、卡片、PNG，杂志风、知识卡都能做。

Kimi and GLM are some of the best open models available. They're also some of the hardest to serve efficiently. Check out this writeup to learn how we're making them faster and cheaper without losing accuracy.

Introducing Ori Eval: the easiest way to write your first eval. There's no definitive best model, only the best model for each task. Ori Eval leverages OpenRouter's APIs for each task in your codebase, and then evaluates the results. curl -fsSL

i built a way to generate full ai vlogs for youtube using seedance 2.5, without ever picking up a camera this was supposed to stay internal but f*ck it, i'm leaking the whole thing you give it a script or even just a topic and it comes back with a finished vlog, voiceover, b-roll, captions, ready to upload here's how it works: a custom claude skill breaks your script into scenes and writes timestamped storyboard prompts for each one, matched to pacing so nothing feels random. those prompts get fed into seedance 2.5, using its 30 second continuous generation and reference asset support to keep the visuals consistent across scenes instead of looking like ten unrelated clips stitched together. then it pulls in an ai voiceover that matches the tone of the script, stitches every scene together, and burns in captions automatically you're not filming, not voicing, not editing, not exporting from three different apps the whole thing runs start to finish and outputs a finished 16:9 vlog ready to post, and it costs a fraction of what an editor or camera setup would run you i'm sharing the full breakdown, which includes: the claude skill that handles scene breakdown and storyboard prompts the seedance 2.5 setup that keeps visuals consistent scene to scene the voiceover setup that keeps it from sounding robotic the exact workflow from script to finished vlog RT + reply "PROMPTS" and i'll send it over (must follow so i can dm)

🚨 THIS IS GOING TO BREAK THE INTERNET! Elon Musk just dropped Neuralink's craziest bombshell: “In the next 6 to 12 months, we're going to implant the first vision devices. Even if you're 100% blind from birth, we're going to write directly to your visual cortex… and you're going to see.” “And that's just the beginning. In the long term, you'll have ultra-HD resolution and real superpowers: you'll see in infrared, ultraviolet, and even radar. Literally like a superhero.” The future is no longer science fiction. It's Neuralink.

开源项目 LoopX：超长程 Agent 自主运行 200+ hours，状态不漂移。 我的技术主张是：LLM 上下文有限，长程 Agent 需要外置状态，通过完备的状态管理、监督和规划，让 Agent 无人干预时跑得稳、持续有产出；有人干预时跑得更好，能吸收反馈继续演进。 两条真实 trajectory 分别跨越 220.7 / 272.9 小时，跨多轮执行、等待、人工决策、writeback 与 resume 后，整个 loop 仍能找回目标、证据和下一步。 目前 LoopX 已有 3 个 showcase：auto PR issue fix、AutoML experiment 和 auto coredump fix。 以 OpenViking 开源仓库的 PR issue fix 为例，Agent 不只是循环写代码。它需要持续理解 issue 的不同状态，判断何时开发、何时等待、何时请求 review，处理 CI、冲突和上游变化，并连续交付多个 PR。 这对应 LoopX 的 domain state 管理：领域系统决定真实状态，LoopX 负责把状态投影成下一步可执行的工作。 与此同时，Agent 还可以在干活过程中实现能力自进化。当它发现现有系统缺少某项能力时，可以提出 feature、完成开发与验证、发布新的离线或在线版本，再使用新能力继续原来的任务。 长程 Agent 天然适合自进化，“完成工作”和“升级完成工作的系统”可以在同一条长程轨迹中发生。 LoopX 把这些信息外置成结构化控制面： • Goal / Vision：目标是什么，什么不能被局部优化牺牲 • Todo / Gate：当前执行的 frontier，以及必须留给人的关键判断 • Identity / Authority：谁能 claim、writeback、approve • Evidence / Receipt：每次推进留下什么可回读证据 • Quota / Scheduler：何时继续执行，何时安静等待 • Handoff / Recovery：换模型、换会话、换 host 后如何恢复 你也可以把它理解为一块专门给 Agent 设计的可执行 Kanban。 普通看板只展示“谁在做什么”；LoopX 的状态会直接约束和驱动下一次 bounded turn，让看板本身成为执行系统的一部分。 这套系统最强的地方是通用性。它不只可以修 PR，还可以做 auto research、长期实验、自媒体运营、复杂 feature 开发和办公任务。 Agent 不再只是一次性的回答机器，而可以围绕一个人的 vision，长期工作、等待、吸收反馈、积累证据并持续演进。 LoopX 从一开始 build in public：状态协议、CLI、控制面实现和真实运行轨迹都进入了开源仓库；它也已经和 OpenViking、NoKV 等 agent infra 项目形成了开源合作伙伴关系。 我希望 LoopX 最终能放大每个人的 vision 和想象力。只要你有自己的目标、想法或技术主张，就能拥有一个全天候继续工作和探索的 Agent 系统，帮助你把愿景一点点变成现实。 欢迎试用、提 issue、贡献代码，或者用一个真实的 multi-day task 跑 LoopX。

We're starting to leave the territory where you'd test an LLM by e.g. "create an svg of pelican on a bicycle". As one idea to generalize it, I was interested what Opus 5 would do if I gave it the first paragraph of the Lord of the Rings, a 1M token budget (~$10) and asked for three js render of it. Opus went off for ~2 hours and wrote 5500 lines of code that (procedurally) rendered the story. It's kind of janky but fun. But it's a bit mindboggling that the LLM has to place and orchestrate various polygon assets in (x,y,z) coordinates and write code that animates it all, and that it even does anything at all. I also like this kind of examples because no one in their right mind would ever spend the time to write something this custom but LLMs have all the stamina and patience in the world, so it's an example where we go from "no one would ever do this" to "sure, why not, it's ~free". There might be a lot more. But I'm excited about creating hyper custom worlds that you can imagine dropping players into, e.g. here to participate in the LoTR story as a spectator NPC, or one of the characters, or etc. Something like an ephemeral GTA of X on demand. Last thought is that the domain of worlds/games exposes a weakness in LLMs: they can't easily audit their work because they aren't able to efficiently and natively perceive videos or play games within them. Here, Opus 5 had to very slowly and painstakingly take screenshots at different points, and it messed up a few times and created a bunch of jank. An example of raw capability (multimodal, gameplay) that I think is still quite lacking.