一键导入
skill-creator
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
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
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
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
Execute a single agent step with custom system prompt and wait for completion.
Control the CARNELIAN browser control server (status/start/stop/tabs/snapshot/screenshot/navigate/act). Routes to the local browser control HTTP server.
Render canvas graphics and visualizations via Carnelian gateway node.invoke API
Communicate with Windsurf Cascade via JSONL channel files (message/delegate/request_help/share_context/status).
Manage Gateway cron jobs (status/list/add/update/remove/run/runs) and send wake events.
Send a message to a Discord channel via the Discord REST API
| name | skill-creator |
| description | Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets. |
| metadata | {"carnelian":{"runtime":"node","version":"0.1.0","sandbox":{"network":"none","resourceLimits":{"maxMemoryMB":256,"maxCpuPercent":25,"timeoutSecs":120}},"capabilities":["fs.read","fs.write"]}} |
This skill provides guidance for creating effective skills.
Skills are modular, self-contained packages that extend capabilities by providing specialized knowledge, workflows, and tools. They transform a general-purpose agent into a specialized agent equipped with procedural knowledge.
The context window is a public good. Only add context the agent doesn't already have. Challenge each piece of information: "Does the agent really need this explanation?"
skill-name/
├── SKILL.md (required)
│ ├── YAML frontmatter metadata (required)
│ │ ├── name: (required)
│ │ └── description: (required)
│ └── Markdown instructions (required)
└── Bundled Resources (optional)
├── scripts/ - Executable code
├── references/ - Documentation for context
└── assets/ - Files used in output
Skills use a three-level loading system:
Keep SKILL.md body under 500 lines. Split content into separate reference files when approaching this limit.