uxc-skill-creator
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseUXC Skill Creator
UXC Skill 生成器
Use this skill to design and standardize provider wrapper skills built on top of .
uxc使用本Skill来设计和标准化基于构建的服务商包装器Skill。
uxcPrerequisites
前提条件
- skill is available as the base execution contract.
uxc - Target wrapper skill scope is clear (provider endpoint, core operations, auth model, write risk).
- Skill已作为基础执行契约可用。
uxc - 目标包装器Skill的范围明确(服务商端点、核心操作、认证模型、写入风险)。
Output Contract
输出约定
A wrapper skill created with this skill should include:
SKILL.mdagents/openai.yamlreferences/usage-patterns.mdscripts/validate.sh
Optional files are allowed only when they add real reusable value.
使用本Skill创建的包装器Skill应包含:
SKILL.mdagents/openai.yamlreferences/usage-patterns.mdscripts/validate.sh
仅当文件能带来真正的可复用价值时,才允许添加可选文件。
Core Workflow
核心工作流程
- Start from user-provided host input:
- record the raw host the user gives
- normalize endpoint candidates (scheme/no-scheme, path variants)
- Discover protocol and valid path before drafting skill text:
- search official docs/repo to confirm endpoint shape and auth model
- probe candidates with
uxc <endpoint> -h - confirm one working endpoint + protocol as the wrapper target
- Detect authentication requirement explicitly:
- run host help or a minimal read call and inspect envelope/error code
- if auth-protected, record required model (api key or oauth) and scopes
- verify local mapping path with when OAuth/binding is used
uxc auth binding match <endpoint>
- Fix the wrapper interface:
- provider endpoint ()
<host> - fixed link command name ()
<provider>-<protocol>-cli - auth mode (none, api key, oauth)
- provider endpoint (
- Write as a thin execution policy:
SKILL.md- link-first command flow
- help-first discovery flow
- JSON envelope parsing and safe-write guardrails
- Add provider-specific :
references/usage-patterns.md- minimal read and write examples
- key=value and bare JSON positional input examples
- Add with strict checks:
scripts/validate.sh- required files
- frontmatter fields
- command style constraints
- banned legacy patterns
- Add for skill UI metadata.
agents/openai.yaml - Run validation and iterate until clean.
- 从用户提供的主机输入开始:
- 记录用户提供的原始主机信息
- 标准化端点候选值(带/不带协议、路径变体)
- 在撰写Skill文本前,发现协议和有效路径:
- 搜索官方文档/仓库以确认端点形态和认证模型
- 使用探测候选端点
uxc <endpoint> -h - 确认一个可用的端点+协议作为包装器目标
- 明确检测认证要求:
- 运行主机帮助命令或最小化读取调用,检查信封/错误代码
- 如果受认证保护,记录所需的模型(API密钥或OAuth)和权限范围
- 当使用OAuth/绑定功能时,通过验证本地映射路径
uxc auth binding match <endpoint>
- 确定包装器接口:
- 服务商端点()
<host> - 固定的链接命令名称()
<provider>-<protocol>-cli - 认证模式(无、API密钥、OAuth)
- 服务商端点(
- 撰写作为精简的执行策略:
SKILL.md- 链接优先的命令流程
- 帮助优先的发现流程
- JSON信封解析和安全写入防护
- 添加服务商专属的:
references/usage-patterns.md- 最小化读取和写入示例
- key=value和纯JSON位置输入示例
- 添加带有严格检查的:
scripts/validate.sh- 必填文件检查
- 前置元字段检查
- 命令风格约束
- 禁用的旧版模式
- 添加用于Skill UI元数据的。
agents/openai.yaml - 运行验证并迭代直至无问题。
Hard Rules
硬性规则
- Default to link-first (then
command -v <link_name>).uxc link <link_name> <host> - Default to help-first (,
<link_name> -h).<link_name> <operation> -h - Use protocol-aware link naming:
- format:
<provider>-<protocol>-cli - examples: ,
notion-mcp-cligithub-openapi-cli
- format:
- Prefer ; allow bare JSON positional payload.
key=value - Keep JSON output as automation path; do not rely on .
--text - Do not use legacy default examples (/
list/describe/removed flags).call - Do not use dynamic link renaming at runtime.
- Do not assume protocol/path/auth from host string alone; verify by search + probe.
- 默认采用链接优先(然后
command -v <link_name>)。uxc link <link_name> <host> - 默认采用帮助优先(,
<link_name> -h)。<link_name> <operation> -h - 使用感知协议的链接命名:
- 格式:
<provider>-<protocol>-cli - 示例:,
notion-mcp-cligithub-openapi-cli
- 格式:
- 优先使用格式;允许纯JSON位置负载。
key=value - 将JSON输出作为自动化路径;不要依赖参数。
--text - 不要使用旧版默认示例(/
list/describe/已移除的标志)。call - 不要在运行时动态重命名链接。
- 不要仅从主机字符串推断协议/路径/认证方式;需通过搜索+探测进行验证。
References
参考资料
- Step-by-step implementation flow:
references/workflow.md
- Copy-ready templates:
references/templates.md
- Validation checklist and banned patterns:
references/validation-rules.md
- Observed pitfalls and better defaults:
references/anti-patterns.md
- 分步实现流程:
references/workflow.md
- 可直接复制的模板:
references/templates.md
- 验证清单和禁用模式:
references/validation-rules.md
- 已发现的陷阱和更优默认值:
references/anti-patterns.md
See Also
另请参阅
- Base execution and protocol/auth guidance:
skills/uxc/SKILL.md
- 基础执行与协议/认证指南:
skills/uxc/SKILL.md