Back to Details

skill-generalizer

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Skill Generalizer

Skill Generalizer

Overview

概述

Convert a working local skill into a clean public artifact. The goal is to preserve the reusable technique while removing private context, personal assumptions, and machine-specific setup.
将可运行的本地技能转换为干净的公开制品。目标是保留可复用技术的同时，移除私有上下文、个人假设和机器特定配置。

When To Use

使用场景

  • A user wants to publish, share, promote, open-source, or package a local skill.
  • A skill was born from personal workflows, private repos, local paths, transcripts, remote hosts, or team conventions.
  • The output needs to be useful to strangers without leaking the author's environment.
Do not use for tuning a skill only for the user's own machine; use 
skill-personalizer
for that.
  • 用户希望发布、分享、推广、开源或打包本地技能。
  • 技能源自个人工作流、私有仓库、本地路径、对话记录、远程主机或团队约定。
  • 输出内容需对陌生用户有用，且不会泄露作者的环境信息。
请勿用于仅针对用户自身机器调优技能；此类场景请使用
skill-personalizer
。

Workflow

工作流程

  1. Inspect the actual source skill and nearby repo files before judging.
  2. If the source skill quality is unclear, run the audit checks from 
    skill-personalizer
    first.
  3. Separate the reusable capability from personal implementation details.
  4. Redact or replace private names, paths, hosts, credentials, account IDs, transcripts, and one-off project facts.
  5. Rewrite the skill around general triggering conditions, portable workflows, and bounded assumptions.
  6. Keep 
    SKILL.md
    concise; move long rubrics, examples, or scripts into bundled resources.
  7. Check target-agent compatibility before writing install instructions or support claims.
  8. Produce publication-ready packaging and honest promotion copy only when requested.
  9. Verify frontmatter, file layout, install path, and at least one realistic usage prompt.
  1. 在评估前先检查实际的源技能及附近的仓库文件。
  2. 如果源技能质量不明确，先运行
    skill-personalizer
    中的审计检查。
  3. 将可复用能力与个人实现细节分离。
  4. 编辑或替换私有名称、路径、主机、凭证、账户ID、对话记录和一次性项目信息。
  5. 围绕通用触发条件、可移植工作流和有限假设重写技能。
  6. 保持
    SKILL.md
    简洁；将冗长的规则、示例或脚本移至捆绑资源中。
  7. 在编写安装说明或支持声明前，检查目标Agent的兼容性。
  8. 仅在被请求时生成可直接发布的打包内容和真实的推广文案。
  9. 验证前置元数据、文件布局、安装路径以及至少一个真实的使用提示。

Public Release Rules

公开发布规则

  • Frontmatter 
    description
    should describe when to use the skill, not summarize its workflow.
  • Public examples must be generic or explicitly sanitized.
  • Claims in README or marketplace copy must match files that actually exist.
  • Prefer portable commands and path placeholders over the author's home directory or private aliases.
  • If a personal detail is essential, turn it into a configurable variable with setup guidance.
  • 前置元数据
    description
    应描述技能的适用场景，而非总结其工作流程。
  • 公开示例必须是通用的或经过明确清理的。
  • README或市场文案中的声明必须与实际存在的文件相符。
  • 优先使用可移植命令和路径占位符，而非作者的主目录或私有别名。
  • 如果某个个人细节是必需的，将其转换为可配置变量并提供设置指南。

References

参考资料

Read publication-rubric.md when doing a full release pass, redaction review, README rewrite, or promotional packaging.
Read platform-compatibility.md before claiming support for Codex, Claude Code, Cursor, OpenCode, Gemini CLI, or other coding agents.
进行完整发布流程、脱敏审查、README重写或推广打包时，请阅读publication-rubric.md。
在声明支持Codex、Claude Code、Cursor、OpenCode、Gemini CLI或其他编码Agent之前，请阅读platform-compatibility.md。