一键导入
skill-creator
Guide the agent to create a new project skill with correct placement, required metadata, and a practical SKILL.md template.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Guide the agent to create a new project skill with correct placement, required metadata, and a practical SKILL.md template.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | skill-creator |
| description | Guide the agent to create a new project skill with correct placement, required metadata, and a practical SKILL.md template. |
Use this skill when the user asks to create a new skill, write a skill, or add guidance for skill authoring.
Create a skill that can be auto-discovered by the current project. The required directory structure is:
.agent/skills/<skill-name>/
└── SKILL.md
The entry file must be named SKILL.md. Do not use any other filename.
.agent/skills/<skill-name>.<skill-name> should be short, stable, and readable. Prefer kebab-case such as skill-creator or api-review..agent/skills/<skill-name>/SKILL.md.SKILL.md must begin with YAML frontmatter.namedescriptionalways: true, only add this when the skill should always be active.requiredTools: [...], only add this when the skill should be visible only if specific agent tools are enabled.When creating a new skill, start the file with this template before writing the body:
---
name: your-skill-name
description: One-sentence description of when this skill should be used.
---
If the skill should always be active, use:
---
name: your-skill-name
description: One-sentence description of when this skill should be used.
always: true
---
If the skill depends on a tool that may be disabled for a session, add requiredTools:
---
name: your-skill-name
description: One-sentence description of when this skill should be used.
requiredTools:
- execute_command
---
When any listed tool is disabled, the skill is hidden from both active skill content and the skill summary.
name should match the skill's responsibility and stay concise and clear.description should explain when the skill should be used. Do not write vague filler text.Use this structure for the skill body:
# Skill Name
One sentence explaining what this skill is for.
## When to Use
- Trigger condition 1
- Trigger condition 2
## Steps
1. Describe the first step.
2. Describe the second step.
3. Describe the third step.
## Constraints
- Constraint 1 that must be followed
- Constraint 2 that must be followed
## Output
- Describe the expected files, changes, or result.
When you are actually creating a new skill for the user:
.agent/skills/<skill-name>..agent/skills/<skill-name>/SKILL.md.name and description both exist and are non-empty.---
name: api-review
description: Use this skill when the user asks for an API design or contract review.
---
# API Review
Use this skill when the user asks for an API design, contract, or request/response structure review.
## Steps
1. Read the relevant API definitions and call sites.
2. Check naming, consistency, error handling, and compatibility risks.
3. Output findings, risks, and suggested improvements.
SKILL.md entry file.name or description is missing, the current project will not recognize it as a valid skill.Use when building, running, testing, or debugging Dora engine games with the Dora CLI, including TypeScript, TSX/DoraX, Lua, YueScript, Teal, XML, Wa, Yarn, Rust WASM, Web IDE service recovery, and in-engine validation.
Use when developing the Dora-SSR engine itself, including C++ engine code, Lua/YueScript dev services, generated bindings, DoraX runtime, Web IDE integration, docs, tests, local validation, and release-facing engine changes.
Dora SSR coding rules for game/workspace projects; prevents browser DOM/Canvas/Node.js code in Dora engine scripts and forces Dora API lookup before using unfamiliar engine APIs.
Use this skill when designing, creating, or polishing UI/screens/HUDs/menus so the result is visually refined, coherent, responsive, and implemented with the correct Dora UI APIs.
Rules and examples for using execute_command with Lua and Git safely inside the Dora Agent runtime.
Agent memory files with grep-based scoped recall.