Skills Plugins MCP Prompt Model 博客 我的中心

anki

Use when the user wants to create Anki flashcards, manage Anki decks, search notes, or interact with Anki via AnkiConnect. Triggers on phrases like "create flashcards", "add to Anki", "make Anki cards", "batch create notes", or "manage my Anki deck".

DeepseekModel 官方收录技能 质量 优秀 · 78 v1.0.0

获取

https://deepseekmodel.com/api/download.php?id=nailuogg-anki-mcp-server-skills-anki-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 anki description Use when the user wants to create Anki flashcards, manage Anki decks, search notes, or interact with Anki via AnkiConnect. Triggers on phrases like "create flashcards", "add to Anki", "make Anki cards", "batch create notes", or "manage my Anki deck". metadata {"author":"nailuoGG","version":"1.0.0"} Anki MCP Server Skill Create and manage Anki flashcards through the anki-mcp-server MCP integration. Prerequisites Anki desktop app is running AnkiConnect addon installed (default port 8765) MCP server configured in Claude: { "mcpServers" : { "anki" : { "command" : "npx" , "args" : [ "-y" , "anki-mcp-server" ] } } } Note: Do not use the .mcpb packaged version — it outputs Electron metadata to stdout which breaks the MCP stdio protocol. Quick Reference Goal Tool Key Args Check connection anki_check_connection — List all decks anki_list_decks — Create deck anki_create_deck name List all tags anki_list_tags — Add note tags anki_add_note_tags noteId or noteIds , tags Remove note tags anki_remove_note_tags noteId or noteIds , tags Create one note anki_create_note type , deck , fields Batch create notes anki_batch_create_notes notes[] (10–20 per batch) Search notes anki_search_notes query (Anki syntax), limit , offset Get note details anki_get_note_info noteId Update note anki_update_note id , fields , tags Delete note anki_delete_note noteId or noteIds List note types anki_list_note_types — Get field names anki_get_note_type_info modelName Legacy unprefixed tool names still work, but prefer the anki_* tools for new workflows. Core Workflows From text/notes → Flashcards Call anki_list_decks to confirm target deck (create if needed) Call anki_get_note_type_info to confirm field names for the chosen type Extract knowledge points — one concept per card Call anki_batch_create_notes (10–20 notes per call, max 50) Minimum information principle: Each card tests exactly one thing. Note Types Type Fields Use For Basic Front , Back Definitions, facts, Q&A Cloze Text with {{c1::deletion}} Fill-in-the-blank, sequences Always call anki_get_note_type_info first when using custom note types — field names vary. Batch Create Example { "notes" : [ { "type" : "Basic" , "deck" : "Programming::Python" , "fields" : { "Front" : "What does list comprehension look like in Python?" , "Back" : "[expr for item in iterable if condition]" } , "tags" : [ "python" , "syntax" ] } , { "type" : "Cloze" , "deck" : "Programming::Python" , "fields" : { "Text" : "In Python, {{c1::def}} defines a function and {{c2::return}} sends back a value." } , "tags" : [ "python" , "basics" ] } ] , "allowDuplicate" : false , "stopOnError" : false } Search Syntax deck:Python # Cards in Python deck tag:重要 is:due # Due cards tagged "重要" is:new # Unseen cards note:Basic # Cards using Basic note type "exact phrase" # Exact text match Tags Use anki_list_tags to inspect existing tags. For metadata-only changes, prefer anki_add_note_tags and anki_remove_note_tags ; use anki_update_note only when replacing the full tag list. Deck Naming Use :: for hierarchy: Language::English::Vocabulary , CS::Algorithms::Sorting Common Mistakes Mistake Fix Not calling anki_get_note_type_info first Always check field names before creating notes with custom types Batches > 50 notes Split into multiple calls of 10–20 Using .mcpb file Use npx -y anki-mcp-server instead Anki not running Start Anki, verify AnkiConnect is active Wrong field names Field names are case-sensitive — use anki_get_note_type_info to verify
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)
同一份技能可按不同平台格式导出。
.skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用 下载
.skillpro 增强格式,额外含脚本 / 工具 / 依赖 / 钩子占位 下载
.json 纯 JSON 导出,只含 system_prompt 与模型参数 下载
Coze 带 frontmatter 的 Markdown,Coze 平台导入用 下载
Dify Dify DSL,创建应用后直接导入 下载

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。