Loading...
Loading...
Compare original and translation side by side
.skills/internal/{skill-name}/.skills/internal/{skill-name}/my-skill-namemy-skill-name.skills/internal/{skill-name}/
└── SKILL.md # Main entry point (required).skills/internal/{skill-name}/
├── SKILL.md # Overview + quick start
└── references/
├── topic-1.md # Deep dive on topic 1
├── topic-2.md # Deep dive on topic 2
└── topic-3.md # Examples/guides.skills/internal/{skill-name}/
└── SKILL.md # 主入口文件(必填).skills/internal/{skill-name}/
├── SKILL.md # 概述+快速入门
└── references/
├── topic-1.md # 主题1深度讲解
├── topic-2.md # 主题2深度讲解
└── topic-3.md # 示例/指南---
name: skill-name-kebab-case
description: One sentence describing what this skill does and who should use it.
---namename# Headingundefined---
name: skill-name-kebab-case
description: One sentence describing what this skill does and who should use it.
---namename# 标题undefined
**Reference files** (optional, for complex skills):
```yaml
---
name: reference-title
description: What this reference covers
---
**参考文件**(复杂Skill可选):
```yaml
---
name: reference-title
description: What this reference covers
---
**Writing guidelines**:
- Target 300-500 words for SKILL.md
- Use concrete examples over abstract explanations
- Include code blocks or snippets when relevant
- Link between skills using relative paths: `[skill-name](...)`
- Write for LLM consumption (clear, structured, no marketing)
- **Never duplicate data that lives in source files.** If information can be derived from a config file, script, or definition that already exists in the repo, don't copy it into the skill. Instead, tell the agent where to find it (`"Run scripts/deploy-info telecine for current service list"`) or which file to read (`"See telecine/deploy/worker-resources.config.ts for current allocations"`). Skills should be a guide to reasoning, not a cache of facts.
- **Test for drift:** before finalizing any section, ask: "If someone changes a config file tomorrow, will this prose become wrong?" If yes, rewrite the section to reference the source rather than restating it.
**编写指南**:
- SKILL.md目标字数300-500字
- 优先使用具体示例而非抽象解释
- 相关时包含代码块或片段
- 使用相对路径关联其他Skill:`[skill-name](...)`
- 为LLM编写(清晰、结构化、无营销内容)
- **切勿复制源文件中的数据**。若信息可从仓库中已有的配置文件、脚本或定义中获取,请勿复制到Skill中。应告知Agent数据位置(`"运行scripts/deploy-info telecine获取当前服务列表"`)或要读取的文件(`"查看telecine/deploy/worker-resources.config.ts获取当前资源分配"`)。Skill应是推理指南,而非事实缓存。
- **检查内容漂移**:完成任何章节前,问自己:“如果明天有人修改配置文件,这段内容会失效吗?”如果是,重写章节以引用源文件而非重复内容。scripts/scripts/{name}npx tsx scripts/{name}.tsscripts/skills-syncpackage.json"See telecine/deploy/worker-resources.config.ts for current allocations."deploymentsscripts/deploy-info telecinescripts/deploy-info elementsscripts/scripts/{name}npx tsx scripts/{name}.tsscripts/skills-syncpackage.json"查看telecine/deploy/worker-resources.config.ts获取当前资源分配。"deploymentsscripts/deploy-info telecinescripts/deploy-info elements# Verify files exist
ls -la .skills/internal/{skill-name}/
# Should see: SKILL.md (required)
# May see: references/ directory with additional .md filesnamedescriptionnamedescription[text](path)[text](references/file.md)# Manually verify the content structure
cat .skills/internal/{skill-name}/SKILL.md# 验证文件存在
ls -la .skills/internal/{skill-name}/
# 应看到:SKILL.md(必填)
# 可能看到:包含额外.md文件的references/目录namedescriptionnamedescription[文本](路径)[文本](references/file.md)# 手动验证内容结构
cat .skills/internal/{skill-name}/SKILL.mdnpm run skills:sync# Check that files now exist in all 3 directories
ls -la .skills/internal/{skill-name}/SKILL.md
ls -la .cursor/skills/{skill-name}/SKILL.md
ls -la .claude/skills/{skill-name}/SKILL.md✅ Skill synced successfully!
Synced to:
- .skills/internal/ (canonical source)
- .cursor/skills/ (Cursor agent)
- .claude/skills/ (Claude Code agent)npm run skills:sync# 检查文件是否存在于所有3个目录中
ls -la .skills/internal/{skill-name}/SKILL.md
ls -la .cursor/skills/{skill-name}/SKILL.md
ls -la .claude/skills/{skill-name}/SKILL.md✅ Skill同步成功!
已同步至:
- .skills/internal/(标准源)
- .cursor/skills/(Cursor Agent)
- .claude/skills/(Claude Code Agent)git add .skills/internal/{skill-name}/git commit -m "Create {skill-name} skill"git log -1 --name-statusgit add .skills/internal/{skill-name}/git commit -m "Create {skill-name} skill"git log -1 --name-statusI'll help you create a debugging skill for video rendering. Let me gather some details:
- Should this cover common rendering errors (artifacts, playback issues, encoding)?
- Who are the primary users (developers, content creators)?
- What systems does it cover (Elements, React, API)?
Perfect! I'll create a reference skill calledwith:elements-rendering-debug
- SKILL.md: Overview of debugging workflow
- references/common-issues.md: Artifacts, playback, memory issues
- references/diagnostics.md: How to inspect and troubleshoot
- references/solutions.md: Common fixes and workarounds
Creating the skill structure...[writes files]
Validating the skill: ✅ Directory structure correct ✅ SKILL.md frontmatter valid ✅ All references included ✅ Links formatted correctly
Ready to sync this skill across all agent directories?Running: npm run skills:sync✅ Synced successfully!
- .skills/internal/elements-rendering-debug/ (canonical)
- .cursor/skills/elements-rendering-debug/
- .claude/skills/elements-rendering-debug/
Committing to git:git add .skills/internal/elements-rendering-debug/ git commit -m "Add elements-rendering-debug skill"✅ Complete! The skill is now available in all agent directories.
我将帮你创建一个视频渲染调试Skill。请提供一些细节:
- 是否需要涵盖常见渲染错误( artifacts、播放问题、编码)?
- 主要用户是谁(开发者、内容创作者)?
- 涵盖哪些系统(Elements、React、API)?
完美!我将创建名为的参考型Skill,包含:elements-rendering-debug
- SKILL.md:调试工作流概述
- references/common-issues.md: artifacts、播放、内存问题
- references/diagnostics.md:检查与故障排除方法
- references/solutions.md:常见修复与解决方法
创建Skill结构中...[写入文件]
验证Skill: ✅ 目录结构正确 ✅ SKILL.md前置元数据有效 ✅ 包含所有参考文件 ✅ 链接格式正确
准备好将此Skill同步到所有Agent目录了吗?运行:npm run skills:sync✅ 同步成功!
- .skills/internal/elements-rendering-debug/(标准源)
- .cursor/skills/elements-rendering-debug/
- .claude/skills/elements-rendering-debug/
提交到Git:git add .skills/internal/elements-rendering-debug/ git commit -m "Add elements-rendering-debug skill"✅ 完成!该Skill现已在所有Agent目录中可用。
Service CPU Memory Max Instances web 1000m 1Gi 10 render-fragment 2000m 4Gi 200
worker-resources.config.tscloudrun.tsscripts/deploy-infoRunto see current services and resource allocations.scripts/deploy-info telecine
Service CPU Memory Max Instances web 1000m 1Gi 10 render-fragment 2000m 4Gi 200
worker-resources.config.tscloudrun.tsscripts/deploy-info运行查看当前服务和资源分配。scripts/deploy-info telecine
ls .skills/internal/{skill-name}/npm run skills:syncgit add .skills/internal/{skill-name}/
git commit -m "Update {skill-name} skill"ls .skills/internal/{skill-name}/npm run skills:syncgit add .skills/internal/{skill-name}/
git commit -m "Update {skill-name} skill"ls .skills/internal/SKILL.mdls .skills/internal/SKILL.mdnpm run skills:syncnpm run skills:sync:drynpm run skills:sync:verbosenpm run skills:generatenpm run skills:syncnpm run skills:sync:drynpm run skills:sync:verbosenpm run skills:generate.skills/internal/.cursor/skills/.claude/skills/.skills/external/.skills/internal/.cursor/skills/.claude/skills/.skills/external/skills/SYNC.md.skills/internal/skills-docs/SKILL.mdskills/SYNC.md.skills/internal/skills-docs/SKILL.md.skills/internal/npm run skills:sync.skills/internal/npm run skills:syncnpm run skills:sync:dry.skills/internal/.skills/internal/.skills/internal/.skills/internal/npm run skills:syncgit checkout HEAD -- .skills/internal/{skill-name}/npm run skills:syncnpm run skills:sync:dry.skills/internal/.skills/internal/.skills/internal/.skills/internal/npm run skills:syncgit checkout HEAD -- .skills/internal/{skill-name}/npm run skills:sync