← 返回 Skills 市场

以文言文压缩输出、节省 token。当用户要求文言回复、节省 token、省输出时触发。支持三档：极致(/e/Extreme)、适度(/m/Medium)、轻微(/l/Light)。

Name: 以文言文压缩输出、节省 token。当用户要求文言回复、节省 token、省输出时触发。支持三档：极致(/e/Extreme)、适度(/m/Medium)、轻微(/l/Light)。
Author: u5bf

作者 u5bf · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

136

总下载

当前安装

版本数

在 OpenClaw 中安装

/install classical-chinese-v1

功能描述

以文言文压缩输出、节省 token。当用户要求文言回复、节省 token、省输出时触发。支持三档：极致(/e/Extreme)、适度(/m/Medium)、轻微(/l/Light)。

使用说明 (SKILL.md)

\r \r

文言压缩（省 Token）\r

核心原则\r

\r 以文言代白话，最大化信息密度。省 token 为首要目标，可读性按需妥协。\r \r

压缩等级\r

\r | 等级 | 命令 | 目标节省 | 规则 |\r |------|------|----------|------|\r | 极致 | /e | 50%+ | 能一字不两字，省主语/虚词/关联词 |\r | 适度 | /m | 30-40% | 简练文言，保基本可读（默认） |\r | 轻微 | /l | ~20% | 浅白文言，优先可读 |\r \r 默认 /m。用户可在首句指定，如"【极致】解释递归"。\r \r

使用流程\r

识别等级（/e /m /l 或默认 /m）\r
转写为文言（调用 references/compression_rules.md）\r
技术内容原文保留（代码、路径、专有名词、错误信息）\r
估算压缩率（见下）\r \r

量化验证\r

\r 回复后简记：[原~N字→文~M字，省X%]\r

若节省 \x3C 预期下限，等级不变，下次更精简\r
若节省 > 预期上限，可适当放宽\r \r

边界处理\r

用户输入为文言\r

直接以同档或更高压缩等级回复，无需转换。\r \r

专有名词\r

已知：框架/库/品牌名 → 保留原文（React, Python, Git）\r
未知：新产品/概念 → 音译或原文，必要时加注\r \r

歧义处理\r

文言多义时，优先取最简义\r
关键术语首次用原文括注：功能→功能（function）\r \r

连续对话\r

切换等级须显式标注\r
上下文已建立的文言术语保持一致\r
追问若需详细解释，可临时降一档\r \r

低压缩例外\r

\r 以下情况可临时降档：\r

复杂逻辑首次解释\r
错误诊断需清晰步骤\r
用户明确要求详细\r \r 降档时注明：[降档说明]\r \r

技术内容保护\r

\r 以下原文不译：\r

代码、变量名、函数名、类名\r
路径、URL、端口号\r
错误代码、日志内容\r
公式、数字、版本号\r
JSON/XML/HTML 等标记语言\r

安全使用建议

This skill is internally consistent and low-risk: it only contains rules for compressing text into classical Chinese and does not access credentials or external systems. Before enabling broadly, try several representative prompts (including technical instructions, error messages, and code) to confirm the chosen compression level preserves the details you need—especially for the /e extreme mode which purposely sacrifices readability for token savings. Avoid using it on sensitive legal/medical/security instructions without manual review. If you rely on fully faithful technical output, prefer /m or /l and verify the '[原~N字→文~M字，省X%]' summary the skill appends.

功能分析

Type: OpenClaw Skill Name: classical-chinese-v1 Version: 1.0.0 The skill is a utility designed to compress AI responses using Classical Chinese (Wenyanwen) to save tokens. It contains translation rules and instructions for the agent to maintain technical accuracy (preserving code, paths, and variables) while increasing information density, with no evidence of malicious intent, data exfiltration, or unauthorized execution across SKILL.md and references/compression_rules.md.

能力评估

✓ Purpose & Capability

Name, description, and required artifacts match: the skill is an instruction-only compressor to produce classical-Chinese outputs and only references an included rules file. It declares no binaries, env vars, or other resources that would be unexpected for this purpose.

ℹ Instruction Scope

SKILL.md gives concrete conversion rules, preserves code/paths/versions, and asks the agent to report compression stats. The only caution: the skill explicitly makes 'token saving' the primary goal and permits aggressive, lossy compression (especially at /e). That is coherent with the stated purpose but may remove nuance or clarity for sensitive/technical explanations despite the stated preservation rules—test on representative content to ensure important details are not lost.

✓ Install Mechanism

No install spec and no code files that run on the host; the skill is instruction-only, so nothing is written to disk or downloaded at install time.

✓ Credentials

The skill requests no environment variables, credentials, or config paths—proportional and minimal for an output-formatting instruction set.

✓ Persistence & Privilege

always is false and the skill is user-invocable. It does not request persistent presence or modify other skills or system settings.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install classical-chinese-v1
安装完成后，直接呼叫该 Skill 的名称或使用 /classical-chinese-v1 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Classical Chinese Compression skill v1.0.0 - Introduces a skill that rewrites output in concise Classical Chinese to save tokens. - Supports three compression levels: Extreme (/e), Medium (/m, default), and Light (/l), each with specific rules for brevity and readability. - Automatically preserves original text for technical content like code, proper nouns, paths, and error messages. - Includes an efficiency tracking system that compares original and compressed lengths to ensure token savings meet targets. - Provides clear guidelines for handling ambiguous wording, technical terms, and edge cases such as user input in Classical Chinese or requests for clarity.

元数据

Slug classical-chinese-v1

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题