The domain model for what makes a skill great. A skill exists to wrangle determinism out of a stochastic system; the root virtue is Predictability, and every term below is a lever on it. This is the disclosed reference for writing-great-skills.
使技能优秀的领域模型。技能的存在是为了从随机系统中驯服出确定性；根本美德是可预测性，以下每个术语都是作用于它的一个杠杆。这是 writing-great-skills 的已披露参考。
The terms are grouped by axis: Invocation (how a skill is reached), Information Hierarchy (how its content is arranged), Steering (how the agent's runtime behaviour is shaped), and Pruning (how it is kept lean). Each failure mode lives beside the lever that cures it, tagged failure mode.
术语按轴分组：调用方式（技能如何被触达）、信息层级（内容如何排列）、引导（代理运行时行为如何塑造）和修剪（如何保持精简）。每个失败模式都放在治愈它的杠杆旁边，标记为失败模式。
Bold terms in any definition are themselves defined in this glossary; find them by their heading.
任何定义中的粗体术语本身都在本术语表中定义；按标题查找它们。
The degree to which a skill makes the agent behave the same way on every run — the same process, not the same output (a brainstorming skill should predictably diverge; its tokens vary, its behaviour doesn't). The root virtue every other term serves — cost and maintainability are symptoms of it, not rivals.
技能使代理每次运行以相同方式行为的程度——相同的过程，而非相同的输出（头脑风暴技能应该可预测地发散；它的 token 在变，行为不变）。每个其他术语都服务于这一根本美德——成本和可维护性是它的症状，而非对立面。
Avoid: consistency, reliability, robustness, output-determinism
避免：consistency、reliability、robustness、output-determinism
How a skill is reached — and the two loads you pay for the choice.
技能如何被触达——以及你为该选择付出的两种负载。
A skill that keeps its description field, so the agent can see it and fire it autonomously — and the human can still type its name, so model-invocation always includes user reach. There is no model-only state: a description only ever adds agent discovery, never removes the human's. Pays a permanent context load on every turn in exchange for that discoverability. Reachable by other skills, because the description that makes it agent-discoverable makes it invocable. A model-invoked skill whose content is all reference is also one home for shared reference: another skill can invoke it, so reference needed by several skills lives in one place. Pick model-invocation only when the agent must reach the skill on its own; if it never fires except by hand, drop the description and pay no context load.
保留 description 字段的技能，使代理可以看到并自主触发它——而人类仍然可以输入它的名字，因此模型调用始终包含用户触达。不存在"纯模型"状态：description 只会增加代理发现，永远不会移除人类的触达方式。它以每回合永久的上下文负载换取这种可发现性。可被其他技能触达，因为那使其可被代理发现的 description 也使其可被调用。内容全是参考的模型调用技能也是共享参考的一个居所：其他技能可以调用它，于是多个技能需要的参考集中在一处。只有当代理必须自主触达该技能时才选择模型调用；如果它永远只靠手动触发，就去掉 description，不付上下文负载。
Avoid: ability, tool, capability
避免：ability、tool、capability
A skill with its description stripped — invisible to the agent and reachable only by the human typing its name (user-only, where model-invoked is user-and-agent). Trades agent-discoverability for zero context load. Because it has no description, nothing but the human can reach it: no other skill can fire it.
剥离了 description 的技能——对代理不可见，只能通过人类输入其名字来触达（用户仅限，而模型调用是用户与代理均可）。以放弃代理可发现性换取零上下文负载。因为它没有 description，除了人类外没有任何东西能触达它：没有其他技能可以触发它。
Avoid: procedure, workflow, command
避免：procedure、workflow、command
The skill's machine-readable trigger, and the one context pointer a model-invoked skill is forced to keep loaded at all times. Its mere presence is the invocation axis: keep it and the skill is model-invoked (and reachable by other skills); delete it and the skill is user-invoked, reachable only by the human. The source of a model-invoked skill's context load.
技能的机器可读触发器，也是模型调用技能被迫始终保持加载的那个上下文指针。它的存在本身就是调用轴：保留它，技能就是模型调用（并且可被其他技能触达）；删除它，技能就变成用户调用，只能被人类触达。这是模型调用技能上下文负载的来源。
Avoid: frontmatter, summary
避免：frontmatter、summary
A reference held in the agent's context that names some out-of-context material and encodes the condition for reaching it. The description is the top-level context pointer (context window → skill); pointers to disclosed files are the same object one level down. Its wording, not the target, decides when the agent reaches — and how reliably. A must-have target behind a weakly worded pointer is a variance bug: fix the wording first, and inline the material only if sharpening fails.
代理上下文中持有的一个引用，命名某些上下文之外的材料并编码触达它的条件。Description 是顶层的上下文指针（上下文窗口 → 技能）；指向已披露文件的指针是同一概念下一层。它的措辞，而非目标，决定了代理何时触达——以及多可靠。一个必达目标放在措辞薄弱的指针后面是方差 bug：先修复措辞，只有锐化失败时才把材料内联。
Avoid: link, reference, import
避免：link、reference、import
The cost a model-invoked skill imposes on the agent's context window — its description, always loaded, spending both tokens and attention. What user-invoked skills escape by having no description, and the brake on splitting into more model-invoked skills.
模型调用技能对代理上下文窗口施加的成本——其 description 始终加载，既消耗 token 也消耗注意力。用户调用技能通过不设 description 来避免这个成本，这也是拆分为更多模型调用技能的制动器。
Avoid: token cost, context bloat
避免：token cost、context bloat
The cost a user-invoked skill imposes on the human — what they must hold in their head: which skills exist and when to reach for each (the human is the index). What model-invocation removes by being agent-discoverable, and the brake on splitting into more user-invoked skills. Not a cost to minimise: it is the price of human agency, the reason some skills stay user-invoked. Spend it where human judgement matters; remove it where it does not.
用户调用技能对人类的成本——他们必须记住的内容：哪些技能存在以及何时使用每一个（人类充当索引）。模型调用通过代理可发现性消除了这个成本，这也是拆分为更多用户调用技能的制动器。这不是要最小化的成本：它是人类主动权的代价，是某些技能保持用户调用的原因。在人类判断重要的地方花费它；在无关的地方消除它。
Avoid: human index, burden, overhead
避免：human index、burden、overhead
A user-invoked skill whose job is to point at your other user-invoked skills — naming each and when to reach for it — so the human has one skill to remember instead of many. It can only hint, never fire them: user-invoked skills have no description, so nothing but the human can reach them. The cure for cognitive load when user-invoked skills multiply.
一个用户调用技能，其工作是指向你的其他用户调用技能——命名每个技能以及何时使用它——这样人类只需记住一个技能而非多个。它只能提示，永远不能触发它们：用户调用技能没有 description，所以除了人类外没有任何东西能触达它们。当用户调用技能增多时，它是认知负载的解药。
Avoid: dispatcher, menu, registry, index, router procedure
避免：dispatcher、menu、registry、index、router procedure
How finely you divide skills. Finer division spends one of the two loads: more model-invoked skills spend context load (more descriptions crowding the window and competing for attention); more user-invoked skills spend cognitive load (more for the human to remember and reach for). Two cuts guide the division. By invocation, split off a model-invoked skill where you have a distinct leading word to trigger it — a trigger word you actually use in your prompts. By sequence, split a run of steps where a step's post-completion steps need hiding, since isolating it in its own context clears what follows. Beware the reverse: merging sequences exposes each step's post-completion steps to what follows, inviting premature completion.
划分技能的精细程度。更细的划分消耗两种负载之一：更多模型调用技能消耗上下文负载（更多 description 挤占窗口并竞争注意力）；更多用户调用技能消耗认知负载（人类需要记住和触达的更多）。两种切分方式指导划分。按调用方式，在有独特前导词触发它时拆分出模型调用技能——你在提示中实际使用的触发词。按序列，在步骤的完成后步骤需要隐藏时拆分一系列步骤，因为将其隔离在自己的上下文中会清除后面的内容。警惕相反的做法：合并序列会将每个步骤的完成后步骤暴露给后续步骤，招致过早完成。
Avoid: chunking, modularity
避免：chunking、modularity
How a skill's content is arranged, and how far down the ladder each piece sits.
技能的内容如何排列，以及每部分在阶梯上放在多深的位置。
A skill's content ranked by how immediately the agent needs it — a single ladder, produced by two cuts: in-file or behind a pointer, and step or reference. The rungs:
技能的内容按代理对其需求的紧迫程度排列——一个单一的阶梯，由两种切分方式产生：文件内或在指针后面，以及步骤或参考。阶梯层级：
A skill with no steps uses just the bottom two rungs — often a legitimately flat peer-set (e.g. every rule of a review on one rung), which is a fine arrangement, not a smell. The hierarchy is independent of invocation: a skill can be model- or user-invoked whether it is all steps, all reference, or both. When a skill has steps, in-file reference that should be disclosed buries them and turns attending to them into a coin-flip — a variance lever, not just a legibility one. Keep the top of the ladder legible; push down it whatever you can.
没有步骤的技能只使用下面两层——通常是合理的扁平对等集合（例如审查的每条规则在同一层级上），这是很好的安排，不是坏味道。层级独立于调用方式：技能可以是模型调用或用户调用，无论它全是步骤、全是参考，还是两者兼有。当技能有步骤时，本应披露的文件内参考会淹没它们，把对步骤的关注变成抛硬币——这是方差杠杆，而不仅仅是可读性杠杆。保持阶梯顶部可读；尽可能多地向下方推。
Avoid: structure, organization, layout
避免：structure、organization、layout
The ordered actions the agent performs — when a skill has them, the primary tier of its content, and the part that earns its place in SKILL.md. Not every skill has steps: a skill can be all steps (tdd), all reference (a review), or both, independent of invocation. Every step ends on a completion criterion, clear or vague.
代理执行的有序动作——当技能有步骤时，它是内容的主要层级，也是它在 SKILL.md 中占据位置的原因。不是每个技能都有步骤：技能可以全是步骤（tdd）、全是参考（如审查），或两者兼有，这独立于调用方式。每个步骤都以一个完成标准结束，无论清晰还是模糊。
Avoid: workflow, instructions, choreography
避免：workflow、instructions、choreography
Material the agent refers to on demand — definitions, facts, parameters, examples, conditional instructions. When a skill has steps it is secondary to them; when a skill has none it is the entire content; or it lives outside any skill entirely — see External Reference. Reached via context pointers, and the prime candidate for progressive disclosure.
代理按需查阅的材料——定义、事实、参数、示例、条件指令。当技能有步骤时，它次于步骤；当技能没有步骤时，它就是全部内容；或者它完全存在于任何技能之外——见外部参考。通过上下文指针触达，是渐进式披露的首要候选。
Avoid: supporting material, docs, background
避免：supporting material、docs、background
Reference that lives outside the skill system — a plain file, no description, no steps, not invocable — that any skill can point at. The home for shared reference that needn't fire on its own, and the only shared home two user-invoked skills can use, since neither has a description and so neither can fire the other.
存在于技能系统之外的参考——一个普通文件，没有 description、没有步骤、不可调用——任何技能都可以指向它。不需要自行触发的共享参考的居所，也是两个用户调用技能可以使用的唯一共享居所，因为它们都没有 description，所以都不能触发对方。
Avoid: doc, resource, knowledge base
避免：doc、resource、knowledge base
Moving reference down the ladder — out of SKILL.md and behind a context pointer — so the top stays legible. Not primarily a token optimisation; it is how the information hierarchy is protected. Licensed by branching: disclose what only some branches need, inline what every path needs, and if a pointer fires unreliably on must-have material, sharpen its wording, and pull it back inline only if that fails.
将参考沿阶梯向下移动——从 SKILL.md 移出，放到上下文指针后面——以保持顶部可读。这主要不是 token 优化；它是保护信息层级的方式。由分支授权：只披露某些分支需要的内容，内联每条路径都需要的内容；如果指针在必达材料上触发不可靠，就锐化其措辞，只有锐化失败时才把它拉回内联。
Avoid: lazy loading, chunking
避免：lazy loading、chunking
Keeping the material an agent needs at once in one place — a concept's definition, rules, and caveats under a single heading, not scattered across the file — so reading one part brings its neighbours with it. The within-file companion to the Information Hierarchy: the hierarchy ranks how far down a piece sits; co-location decides what sits beside it once there. There is no formula for the right format of a body of reference; the test is that a skill should read like documentation written for the agent, and grouped material reads that way where scattered material does not. Distinct from Duplication: that repeats one meaning in two places, where scattering fragments a single meaning across many.
将代理一次需要的材料放在一个地方——概念的定义、规则和注意事项放在单个标题下，而非分散在文件中——这样阅读一部分就能连带看到邻近内容。它是信息层级的文件内伴侣：层级决定一段内容放在多深；共置决定它到了那里之后与什么相邻。对于参考体的正确格式没有公式；检验标准是：技能应该读起来像为代理编写的文档，分组的材料读起来如此，而分散的材料则不然。与重复不同：重复是在两个地方重复一个含义，而分散是把一个含义打散到多处。
Avoid: grouping, clustering, cohesion
避免：grouping、clustering、cohesion
Failure mode. A skill that is simply too long — too many lines in SKILL.md — independent of whether they are stale or repeated. Even an all-live, all-unique skill can sprawl. It costs readability (the agent wades through more before it can act, and attention thins across the excess), maintainability (every extra line is one more to keep relevant), and tokens. The cure is the information hierarchy: push reference down behind context pointers, and split by branch or sequence so each path carries only what it needs. Distinct from sediment (length from stale accumulation) and duplication (length from repeated meaning) — sprawl is length itself, whatever its cause.
失败模式。技能单纯太长——SKILL.md 中的行数过多——无论这些行是陈旧还是重复。即使是全活跃、全唯一的技能也可能蔓延。它损害可读性（代理在能行动之前要跋涉更多内容，注意力在过量内容中变薄）、可维护性（每多一行都需要保持相关）以及 token。治愈方法是信息层级：将参考推到上下文指针后面，按分支或序列拆分，使每条路径只携带所需内容。与沉淀（来自陈旧累积的长度）和重复（来自重复含义的长度）不同——蔓延是长度本身，无论其原因。
Avoid: bloat, length, size, verbosity
避免：bloat、length、size、verbosity
The levers that shape the agent's runtime behaviour toward Predictability.
将代理运行时行为塑造向可预测性的杠杆。
A distinct way a skill can be invoked — a case the skill handles — so different runs take different paths through it. A skill with many steps may carry many branches; a linear one has none.
技能可被调用的不同方式——技能处理的一个场景——使得不同的运行在技能中走不同的路径。有很多步骤的技能可能有很多分支；线性技能则没有。
Avoid: path, case, fork
避免：path、case、fork
A compact concept — also called a Leitwort — already living in the model's pretraining, that the agent thinks with while running the skill. It encodes a behavioural principle in the fewest possible tokens by invoking priors the model already holds (e.g. lesson, proximal zone of development, fog of war, tracer bullets). Repeated as a token, never as a sentence, it accumulates a distributed definition across the skill and anchors a whole region of behaviour. Coining your own works if you define it clearly, but a made-up word recruits no priors — you pay in definition tokens what a pretrained word gives free. Reach for an existing word first.
一个紧凑的概念——也称 Leitwort——已经存在于模型的预训练中，代理在运行技能时用它来思考。它通过调用模型已有的先验，用最少的 token 编码行为原则（例如 lesson、proximal zone of development、fog of war、tracer bullets）。以 token 的形式重复，从不以句子的形式重复，它在整个技能中积累分布式定义并锚定整个行为区域。自创词汇如果定义清楚也可以工作，但自造词不会招募先验——你在定义上付出的 token 是预训练词免费提供的东西。优先选用已有的词。
A leading word serves predictability twice. In the body it anchors execution — the agent reaches for the same behaviour every time the concept appears, and inside flat reference it focuses attention on a class of thing to look for, recruiting the right checks each run. In the description it anchors invocation — and not only within the skill: when the same word lives in your prompts, your docs, and your codebase, the agent links that shared language to the skill and fires it more reliably. Word a description with the leading words you actually use when you want the skill.
前导词以两种方式服务于可预测性。在正文中它锚定执行——代理每次该概念出现时都采取相同的行为，在扁平参考内部则将注意力集中在要寻找的一类事物上，每次运行招募正确的检查。在 description 中它锚定调用——而且不仅在技能内部：当同一个词出现在你的提示词、文档和代码库中时，代理将这种共享语言与技能关联起来，更可靠地触发它。用你在想要该技能时实际使用的前导词来编写 description。
Avoid: keyword, term, motif
避免：keyword、term、motif
The condition that tells the agent a unit of work is done — the target it judges against. Two properties make it a lever, not just a quality. Its clarity (can the agent tell done from not-done?) resists premature completion — a vague bound ("understanding reached") lets the agent declare done and slip to the next step; this axis needs steps to bite, since premature completion is a between-steps failure. Its demand (how much it requires) sets legwork — "every modified model accounted for" forces thorough work where "produce a change list" does not — and this axis is not step-bound: it can bind a body of flat reference too, which is how a skill with no steps still carries an exhaustiveness bar ("every rule applied"). The strongest criteria are both checkable and exhaustive.
告诉代理一个工作单元已完成的条件——它用来判断的目标。两个属性使其成为杠杆，而不仅仅是质量。它的清晰度（代理能否区分完成与未完成？）抵抗过早完成——模糊的边界（"已达到理解"）让代理宣布完成并滑向下一步；这个轴需要步骤才能起作用，因为过早完成是步骤间的失败。它的要求度（它要求多少）设定基础工作——"每个修改过的模型都已计入"强制彻底的工作，而"生成变更列表"则不会——这个轴不受步骤约束：它也可以约束扁平参考体，这就是没有步骤的技能仍然承载穷尽标准（"每条规则都已应用"）的方式。最强的完成标准既可检查又穷尽。
Avoid: done condition, exit condition, stopping rule
避免：done condition、exit condition、stopping rule
The work an agent does behind the scenes within a single step — reading files, exploring the codebase, making changes, digging up what it needs rather than offloading to the user. It lives below the step structure: never written as its own step, latent in the wording, controlled by the agent rather than the skill. The within-step counterpart to post-completion steps' across-step pull. Raised by a leading word (comprehensive, thorough) or a completion criterion that demands the work be exhaustive — including the demand axis applied to flat reference, which is what drives a skill of flat reference to cover all its rungs. Goes thin either when that demand is missing or when premature completion cuts the step short.
代理在单个步骤内部幕后所做的工作——读取文件、探索代码库、进行修改、挖掘所需内容而非推给用户完成。它存在于步骤结构之下：从不写成自己的步骤，潜藏在措辞中，由代理而非技能控制。它是完成后步骤跨步骤拉力的步骤内对等物。由前导词（comprehensive、thorough）或要求工作穷尽的完成标准提升——包括应用于扁平参考的要求轴，这就是驱动扁平参考技能覆盖其所有层级的原因。当该要求缺失或过早完成缩短步骤时，基础工作会变薄。
Avoid: scope, effort, diligence, coverage
避免：scope、effort、diligence、coverage
The steps that follow the current step. Visible, they pull the agent forward into premature completion — the more it sees, the stronger the tug; the defence is to hide them by splitting the sequence of steps into two.
当前步骤之后的步骤。它们可见时，会将代理拉向过早完成——看到得越多，拉力越强；防御方法是通过将步骤序列拆分为二来隐藏它们。
Avoid: horizon, fog of war, lookahead
避免：horizon、fog of war、lookahead
Failure mode. Ending the current step before it is genuinely done, because the agent's attention slips to being done rather than to the work. A between-steps failure: it needs steps to occur — a skill with no steps that quits early isn't premature completion but thin legwork under an unmet demand. A tug-of-war between two forces: visible post-completion steps (the pull forward) and the completion criterion's clarity (the resistance — a sharp, checkable bar holds; a vague one gives way). Fuzziness is the necessary condition: a sharp bound resists the pull no matter how many later steps are visible, so a step that never rushes needs no defending. Two levers hold a step that does, but reach for them in order: sharpen the bound first — it is cheap and local. Split only if the criterion is irreducibly fuzzy and you observe the rush, and hide the later steps — and hiding only works across a real context boundary (a user-invoked handoff or sub-agent dispatch; an inline model-invoked call leaves the later steps in context and clears nothing). One cause of thin legwork, but distinct: legwork can be thin even when a step runs to full completion.
失败模式。在当前步骤真正完成之前就结束，因为代理的注意力滑向了"完成"而非工作本身。它是一种步骤间的失败：需要步骤才能发生——没有步骤的技能提前退出不是过早完成，而是未满足要求下的薄基础工作。两种力之间的拔河：可见的完成后步骤（向前的拉力）和完成标准的清晰度（抵抗力——尖锐、可检查的边界能守住；模糊的边界则会让步）。模糊性是必要条件：尖锐的边界无论后面有多少步骤可见都能抵抗拉力，所以从不匆忙的步骤不需要防御。两个杠杆可以守住确实匆忙的步骤，但应按顺序使用：先锐化边界——它便宜且局部。只有当标准不可约地模糊且你确实观察到匆忙时，再隐藏后面的步骤——而隐藏只在真正的上下文边界上有效（用户调用的交接或子代理派遣；内联的模型调用调用会把后面的步骤留在上下文中，什么也没清除）。这也是薄基础工作的一个原因，但与之不同：即使步骤运行到完全完成，基础工作也可能很薄。
Avoid: premature closure, the rush, rushing, shortcutting
避免：premature closure、the rush、rushing、shortcutting
Failure mode. Steering by prohibition — telling the agent what not to do — which drags the forbidden behaviour into context and makes it more available, not less. Don't think of an elephant, and the elephant is all there is; never write verbose comments, and verbosity is the pattern the agent has just read. The negation is a weak modifier the strongly-activated concept overruns, so the ban half-reads as an instruction to do the thing. Its leading word is the elephant: whatever a prohibition names into the frame. Cure: prompt the positive — describe the target behaviour ("write one-line comments") so the banned one is never spoken. A prohibition earns its place only as a hard guardrail on a behaviour you cannot phrase positively; even then, pair it with what to do instead.
失败模式。通过禁止来引导——告诉代理不要做什么——这会把被禁止的行为拖进上下文，使其更易被联想到，而非更难。不要想大象，结果大象成了唯一能想到的东西；永远不要写冗长的注释，冗长就成了代理刚读完的模式。否定是一个弱修饰符，被强烈激活的概念会覆盖它，所以禁止半读半会变成做这件事的指令。它的前导词就是大象：即禁止行为在框架中命名的任何东西。治愈方法：提示正向行为——描述目标行为（"写一行注释"），这样被禁止的行为根本不会被提及。禁止只有在作为无法正面表述的行为的硬边界时才有一席之地；即使如此，也要同时说明应该做什么。
Avoid: ironic rebound, don't-prompting, the pink elephant
避免：ironic rebound、don't-prompting、the pink elephant
Keeping a skill lean — each remedy paired with the failure it cures.
保持技能精简——每种疗法与它所治愈的失败模式配对。
The desired state where each meaning lives in exactly one authoritative place, so a change to the skill's behaviour is a change in one place. Duplication is its violation.
每个含义恰好存在于一个权威位置的期望状态，这样对技能行为的改变只需改一处。重复是对它的违反。
Avoid: home, canonical location
避免：home、canonical location
Failure mode. The same meaning given more than one single source of truth. It costs maintenance (change one place, you must change the others), costs tokens, and inflates prominence — repeating a meaning weights it on the ladder past its real rank. The accidental inverse of a leading word, which raises attention on purpose by repeating a token, never the meaning.
失败模式。同一个含义有多个单一真相源。它消耗维护精力（改一处，必须改其他处）、消耗 token，并夸大突出度——重复含义在层级上将其权重提升到超过真实排名。它是前导词的意外反面，前导词通过故意重复 token 来提高注意力，从不重复含义。
Avoid: repetition, redundancy
避免：repetition、redundancy
Whether a line still bears on what the skill does — the lens for what to keep. A line loses relevance either by never bearing on the task (mere exposition, or a branch that should be disclosed) or by going stale: drifting out of date as the behaviour or world it describes changes. Shorter skills are easier to keep relevant, because each line is cheaper to check. Distinct from no-op: relevance asks whether a line bears on the task, not whether it changes behaviour.
一行是否仍然与技能的功能有关——决定保留什么的透镜。一行失去相关性，要么是因为从未与任务有关（纯粹的解释，或应该披露的分支），要么是因为变得陈旧：随着它所描述的行为或世界变化而过时。较短的技能更容易保持相关，因为每一行的检查成本更低。与无操作不同：相关性问的是一行是否与任务有关，而非它是否改变行为。
Avoid: load-bearing, staleness, freshness
避免：load-bearing、staleness、freshness
Failure mode. Layers of old content that settle in a skill and are never cleared, because adding feels safe and removing feels risky — so stale and irrelevant lines accumulate and you must core down through them to find what is still live. The default fate of any skill without a pruning discipline; the slow erosion of relevance, as opposed to duplication's repeated meaning.
失败模式。在技能中沉积且从不清理的旧内容层，因为添加感觉安全而删除感觉冒险——所以陈旧和不相关的行不断累积，你必须深挖才能找到仍然活跃的内容。任何缺乏修剪纪律的技能都难逃此命运；它是相关性的缓慢侵蚀，与重复的重复含义相反。
Avoid: accretion, bloat, cruft, rot
避免：accretion、bloat、cruft、rot
Failure mode. An instruction that changes nothing because the model already does it by default — you pay load to tell the agent what it would do anyway. The test: does a line change behaviour versus the default? A line can be perfectly relevant and still be a no-op. The same priors that make a leading word free make a no-op worthless.
失败模式。一个指令不改变任何东西，因为模型默认已经这样做了——你付出负载来告诉代理它无论如何都会做的事。测试方法：一行是否改变了与默认行为相比的行为？一行可以完全相关但仍然是无操作。使前导词免费的相同先验使无操作毫无价值。
A leading word is a technique; No-Op is a verdict on a line — and they cross. A leading word too weak to beat the default is a no-op (be thorough when the agent is already thorough-ish), and the fix is a stronger word that passes the verdict (relentless), not a different technique. So the No-Op test — does it change behaviour versus the default? — is also how you grade whether a leading word is earning its repetitions. This is model-relative, not reader-relative: two people disagreeing over whether a line is a no-op disagree about the default, and settle it by running the skill, not by debate.
前导词是一种技术；无操作是对一行的裁决——它们有交叉。太弱而无法击败默认行为的前导词就是无操作（代理已经够彻底时还说 be thorough），修复方法是通过裁决的更强词汇（relentless），而非不同的技术。因此，无操作测试——它是否改变了与默认行为相比的行为？——也是你评判前导词是否值得其重复的方式。这是模型相对的，而非读者相对的：两个人对一行是否为无操作有分歧，实际上是对默认行为有分歧，通过运行技能来解决，而非通过辩论。
Avoid: redundant instruction, restating the obvious, belaboring
避免：redundant instruction、restating the obvious、belaboring