生活与工具
#agent
create-skill
Helps you create new agent skills for Zed. Use this to create a skill, ask about SKILLs.md, or package reusable agent instructions.
DeepseekModel
官方收录技能
质量 优秀 · 90
v1.0.0
获取
https://deepseekmodel.com/api/download.php?id=zed-industries-zed-crates-agent-skills-builtin-create-skill-skill-md&format=skill
下载 .skill
标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name create-skill description Helps you create new agent skills for Zed. Use this to create a skill, ask about SKILLs.md, or package reusable agent instructions. Creating a Zed Agent Skill Use this skill when the user wants to create, edit, or understand agent skills in Zed. What is a Skill? A skill is a reusable set of instructions that an agent can load on demand. Each skill lives in its own directory and is defined by a SKILL.md file with YAML frontmatter. Where Skills Live Skills can be placed in two locations: Scope Path When to use Global ~/.agents/skills/<skill-name>/SKILL.md Personal skills, available in all projects Project-local <project>/.agents/skills/<skill-name>/SKILL.md Project-specific skills, shared with collaborators through version control Prefer project-local when the skill is specific to a repository. Prefer global when the skill is a personal workflow the user wants everywhere. SKILL.md Format Every SKILL.md must start with YAML frontmatter between --- delimiters: --- name: my-skill-name description: A clear, specific description of what this skill does and when to use it. --- # Skill Title Instructions for the agent go here. Write them as if you're telling the agent what to do when this skill is activated. Required Frontmatter Fields name (required): Must be 1–64 characters, lowercase alphanumeric with single-hyphen separators. Must match the containing directory name exactly. Regex: ^[a-z0-9]+(-[a-z0-9]+)*$ description (required): Must be 1–1024 characters. This is what the agent sees when deciding whether to use the skill — make it specific and actionable. Optional Frontmatter Fields disable-model-invocation : When set to true , the skill is hidden from the agent's automatic catalog. The user can still invoke it manually via the / slash command menu. Useful for skills that should only run when explicitly requested. Naming Rules The skill name must: Be lowercase letters and numbers only, with single hyphens as separators Not start or end with - Not contain consecutive -- Match the directory name that contains the SKILL.md Good: git-release , pr-review , rust-patterns Bad: Git-Release , pr--review , -my-skill , my_skill Writing Good Skill Instructions The body of the SKILL.md (after the frontmatter) contains the instructions the agent will follow. Guidelines: Be direct : Write instructions as if talking to the agent. "Do X", "Check Y", "Ask the user about Z". Be specific : Include concrete file paths, commands, formats, and patterns. Include when-to-use guidance : Help the agent understand the right context for this skill. Reference supporting files : Skills can include additional files in their directory. Reference them with relative paths (e.g., templates/component.tsx ). The agent can read these files when the skill is activated. Keep descriptions actionable : The description field is the agent's primary signal for whether to load this skill. "Helps with code" is too vague. "Generate React components following the project's design system patterns" is specific. Keep instructions focused : Limit instructions to those relevant to the skill itself. Avoid duplicating instructions from AGENTS.md and other skills in the current conversation if they are not relevant to the skill being created Supporting Files A skill directory can contain additional files beyond SKILL.md : ~/.agents/skills/react-component/ ├── SKILL.md ├── templates/ │ ├── component.tsx │ └── test.tsx └── examples/ └── button.tsx Reference these in the skill body. The agent can read them using the file path shown in the <directory> tag of the skill envelope. Step-by-Step: Creating a Skill Decide on scope (global vs project-local) based on the user's needs. Choose a descriptive, hyphenated name. Create the directory structure. The create_directory tool normally only creates directories inside the current project, but it has a special allow case for global skills under ~/.agents/skills . Write the SKILL.md with frontmatter and instructions. The write_file and edit_file tools also have a special allow case for creating or modifying files under ~/.agents/skills . Optionally add supporting files (templates, examples, references). After creating the skill, it will be automatically discovered by Zed's agent on the next conversation (no restart needed for global skills if the ~/.agents/skills/ directory already exists).
Agent 识别该技能的关键词,点击任意一个即可复制。
该技能未提供触发词。
下载的 .skill 包内含以下字段。
| 字段 | 说明 |
|---|---|
| format | 格式标识(skill/v1) |
| skill_id | 技能唯一 ID |
| name | 技能名称 |
| version | 版本号 |
| description | 技能描述 |
| category | 所属分类(数组) |
| trigger_words | 触发词列表 |
| tags | 标签列表 |
| source | 来源标识 |
| source_url | 来源链接(本页地址) |
| exported_at | 导出时间(每次下载生成) |
| system_prompt | 系统提示词正文 |
| model_config | 模型参数:provider / model / temperature / max_tokens / top_p |
| examples | 示例 |
| install_guide | 各平台导入说明(Coze / Dify / Claude / 自定义框架) |