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。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/diegosouzapw/awesome-omni-skill --skill ccncreate-topic命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | ccn:create-topic |
| description | Create a new topic file in .notes/ with frontmatter template |
| disable-model-invocation | true |
| argument-hint | ["topic-name"] |
This skill creates a new topic file in the .notes/ directory with structured frontmatter and section headers.
When this command is invoked with /ccn:create-topic $ARGUMENTS:
If $ARGUMENTS is empty or not provided:
Take the provided topic name and transform it:
.md extensionExamples:
Store the result as the filename.
Use the Read tool to check if .notes/{filename} already exists.
If the file EXISTS:
If the file DOES NOT exist:
Use the Bash tool to ensure the directory exists:
mkdir -p .notes
Create YAML frontmatter with these fields:
description: "Knowledge and patterns for {original topic name}"
keywords: Generate array from normalized filename
["api", "design", "api_design"]last_updated: Today's date in YYYY-MM-DD format
Use the Write tool to create .notes/{filename} with this structure:
---
description: "Knowledge and patterns for {topic}"
keywords: [{keyword array}]
last_updated: "YYYY-MM-DD"
---
# {Topic Name}
## Overview
(Add overview content here)
## Key Concepts
(Document key concepts here)
## Patterns
(Capture recurring patterns here)
## Notes
(Add detailed notes here)
---
*Topic created: YYYY-MM-DD*
Important formatting notes:
Tell the user: "Created: .notes/{filename}"
If any tool fails (mkdir, Read, Write):
Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating phases.
AshAi extension guidelines for integrating AI capabilities with Ash Framework. Use when implementing vectorization/embeddings, exposing Ash actions as LLM tools, creating prompt-backed actions, or setting up MCP servers. Covers semantic search, LangChain integration, and structured outputs.
This skill should be used when solving hard questions, complex architectural problems, or debugging issues that benefit from GPT-5 Pro or GPT-5.1 thinking models with large file context. Use when standard Claude analysis needs deeper reasoning or extended context windows.
基于 SOC 职业分类