Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kldrgon/language-output-design-skill --skill language-output-designgit clone --depth 1 https://github.com/kldrgon/language-output-design-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kldrgon/language-output-design-skill/language-output-design)<a href="https://agentmods.dev/skills/kldrgon/language-output-design-skill/language-output-design"><img src="https://agentmods.dev/badge/skills/kldrgon/language-output-design-skill/language-output-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kldrgon/language-output-design-skill/language-output-design"><img src="https://agentmods.dev/badge/skills/kldrgon/language-output-design-skill/language-output-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00081 | $0.01182 |
| Opus 5 | $0.00041 | $0.00591 |
| Sonnet 5 | $0.00016 | $0.00236 |
| Haiku 4.5 | $0.00008 | $0.00118 |
Grade A, and why
language-output-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Language Output Design
本 Skill 将通用语言逻辑转化为可执行的写作流程。它细化始终生效的 Rule，不覆盖 Rule，也不把一种表达方式变成固定模板。
渐进式读取
先执行本文件的核心流程。仅在对应判断确实需要时继续读取。
- 受众、知识类型或认知负荷不明确时，读取 references/foundations/INDEX.md
- 需要设计信息入口、主线、语体、列表、表格、示例或例外时，读取 references/composition/INDEX.md
- 需要生成解释、步骤、参考资料、诊断、建议或改写时，读取 references/scenarios/INDEX.md
- 需要校准质量、查看正反例或处理边界情况时，读取 references/examples/INDEX.md
不要预读全部资料。先确定任务分支，再沿索引读取最少的必要文件。
核心流程
1. 确定交流结果
明确受众最终需要获得什么。
- 行动类结果应使受众能够完成具体操作
- 判断类结果应使受众能够选择、接受或拒绝某个方案
- 机制解释应使受众理解对象之间的关系和状态变化
- 记忆框架应保留能够迁移到新情境的结构
- 参考内容应使受众快速定位参数、规格或定义
同时判断受众的先验知识、内容复杂度、交流是否实时、信息能否回看、错误代价和预期篇幅。
2. 选择认知支点
选择最能组织后文的信息入口。它可以是结论、原理、目标、现象、必要背景、关键定义或具体例子。
执行、决策、排查和快速查阅通常从结果或下一步进入。陌生概念通常从机制、关系或必要前置知识进入。抽象结构难以理解时，可以从一个能显露结构的例子进入。
不要机械执行“第一句必须是结论”或“必须先讲原理”。入口必须帮助当前受众处理后续信息。
3. 建立主线
先写出当前任务的最短完整逻辑链。每一段只承担一个主要作用，并让下一段与上一段形成明确关系。
主线未闭合时，不沿术语、例外、例子或联想持续深入。不会改变当前结论的支线放到主线之后。会改变答案或带来危险的限制与结论同时出现。
4. 选择表达形式
连续的因果、机制、取舍和论证使用段落。彼此独立、需要核对、排序或依次执行的信息使用列表。多个对象按相同维度横向比较时使用表格。格式必须表达真实的信息关系，不能只用于制造整齐感。
根据交流方式、正式程度、受众关系和可回看性选择语体。对话需要自然承接；文档需要稳定、准确和可检索；教学需要显露关系与中间状态。
5. 配置解释强度
新手需要必要前置概念、关键中间状态、完整示例和明确因果。熟手只需要差异、边界和新增信息。
示例必须展示机制、边界、步骤或迁移方式。类比必须说明对应关系；可能产生错误映射时说明失效边界。
6. 完成校验
交付前检查以下内容。
- 入口是否为后文提供了有效支点
- 主线是否完整，支线是否在合适位置展开并返回
- 决定性限制是否被埋到末尾
- 示例是否与对应规则相邻并说明映射
- 段落、列表和表格是否适合当前信息关系
- 指代是否唯一，术语是否适合受众
- 重复内容是否增加了原因、条件、证据、结果或新表示
- 输出是否真正支持当前行动、判断、理解、记忆或查阅
硬性边界
不要用同义改写制造解释深度。不要把“不是 X，而是 Y”当作默认句式。不要用对称的正反陈述回避有证据支持的判断。不要用无关但有趣的细节争夺注意力。不要为了口语感制造碎片，也不要为了正式感堆积抽象名词。
用户已经持有明确误解、对比本身就是问题或错误做法会造成危险时，可以立即纠正。纠正应指出具体差异和后果，不能只替换标签。
最终选择以交流结果为准。任何模板、检查项或示例都不能机械覆盖当前情境。
What ships with it
38 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/composition/corrections-and-contrast.md 1.3 KB
- references/composition/discourse-flow.md 1.4 KB
- references/composition/entry-and-order.md 1.5 KB
- references/composition/examples-and-analogies.md 1.4 KB
- references/composition/INDEX.md 1017 B
- references/composition/limits-and-exceptions.md 1.3 KB
- references/composition/lists-and-format.md 1.4 KB
- references/composition/register-and-tone.md 1.5 KB
- references/composition/tables-and-comparisons.md 2.0 KB
- references/examples/decisions/conditions-and-tradeoffs.md 2.2 KB
- references/examples/diagnostics/evidence-and-uncertainty.md 2.3 KB
- references/examples/discourse/long-answer-structure.md 2.5 KB
- references/examples/examples-and-analogies/migration-and-boundaries.md 2.1 KB
- references/examples/explanations/concepts.md 2.8 KB
- references/examples/explanations/novice-and-expert.md 2.4 KB
- references/examples/INDEX.md 2.1 KB
- references/examples/limits/technical-constraints.md 1.8 KB
- references/examples/procedures/ordinary-operations.md 2.2 KB
- references/examples/procedures/safety-critical.md 2.6 KB
- references/examples/reference-content/parameter-entries.md 2.1 KB
- references/examples/register/formal-and-teaching.md 2.9 KB
- references/examples/rewriting/ai-patterns.md 4.4 KB
- references/examples/rewriting/discourse-flow.md 2.4 KB
- references/examples/rewriting/register.md 2.5 KB
- references/examples/tables/experiment-comparison.md 1.8 KB
- references/examples/tables/when-to-use.md 2.1 KB
- references/foundations/audience-and-context.md 1.8 KB
- references/foundations/cognitive-load.md 2.0 KB
- references/foundations/INDEX.md 658 B
- references/foundations/knowledge-types.md 1.8 KB
- references/foundations/research-basis.md 2.5 KB
- references/scenarios/decisions.md 1.1 KB
- references/scenarios/diagnostics.md 1.2 KB
- references/scenarios/explanations.md 1.3 KB
- references/scenarios/INDEX.md 778 B
- references/scenarios/procedures.md 1.3 KB
- references/scenarios/reference-content.md 1.0 KB
- references/scenarios/rewriting.md 1.4 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 81 lines · 81 tokens per session scan A e5c8d1ea9715
language-output-design is a skill published in the GitHub repository kldrgon/language-output-design-skill (3 stars, last pushed 13d ago), licensed MIT. It adds 81 tokens to every session and 1,182 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…