MCPInstall

anki-connect

This skill is for interacting with Anki through AnkiConnect, and should be used whenever a user asks to interact with Anki, including to read or modify decks, notes, cards, models, media, or sync operations.

Installs
896
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/intellectronica/agent-skills --skill anki-connect
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads anki-connect automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

AnkiConnect

Overview

Enable reliable interaction with Anki through the AnkiConnect local HTTP API. Use this skill to translate user requests into AnkiConnect actions, craft JSON requests, run them via curl/jq (or equivalent tools), and interpret results safely.

Preconditions and Environment

  • If Anki is not running, launch Anki, then wait until the AnkiConnect server responds at http://127.0.0.1:8765 (default). Verify readiness using curl, e.g. curl -sS http://127.0.0.1:8765 should return Anki-Connect.

Safety and Confirmation Policy (Critical)

CRITICAL — NO EXCEPTIONS

Before any destructive or modifying operation on notes or cards (adding, updating, deleting, rescheduling, suspending, unsuspending, changing deck, or changing fields/tags), request confirmation from the user. Use the AskUserQuestion tool if available; otherwise ask via chat. Only request confirmation once per logical operation, even if it requires multiple API calls (e.g., search + update + verify). Group confirmation by intent and scope (e.g., “Update 125 notes matching query X”).

Treat the following as confirmation-required by default:

  • Notes: addNote, addNotes, updateNoteFields, updateNoteTags, updateNote, updateNoteModel, deleteNotes, removeEmptyNotes, replaceTags, replaceTagsInAllNotes, clearUnusedTags.
  • Cards: setEaseFactors, setSpecificValueOfCard, suspend, unsuspend, forgetCards, relearnCards, answerCards, setDueDate, changeDeck.
  • Deck or model modifications that materially change cards/notes (deck deletion, model edits). Ask even if the action is not explicitly listed above.

API Fundamentals

Request Format

Every request is JSON with:

  • action: string action name
  • version: API version (use 6 unless user specifies otherwise)
  • params: object of parameters (optional)

Response Format

Every response is JSON with:

  • result: return value
  • error: null on success or a string describing the error

Always check error before using result.

Permissions

  • Use requestPermission first when interacting from a non-trusted origin; it is the only action that accepts any origin.
  • Use version to ensure compatibility; older versions may omit the error field in responses when version ≤ 4.

curl + jq Patterns

Prefer jq to build JSON and parse responses. Keep requests explicit and structured.

Minimal request template

jq -n --arg action "deckNames" --argjson version 6 '{action:$action, version:$version}' \
| curl -sS http://127.0.0.1:8765 -X POST -H 'Content-Type: application/json' -d @-

With params

jq -n \
	--arg action "findNotes" \
	--argjson version 6 \
	--arg query "deck:French tag:verbs" \
	'{action:$action, version:$version, params:{query:$query}}' \
| curl -sS http://127.0.0.1:8765 -X POST -H 'Content-Type: application/json' -d @-

Handling result/error

curl -sS http://127.0.0.1:8765 -X POST -H 'Content-Type: application/json' -d @- \
| jq -e 'if .error then halt_error(1) else .result end'

Batching multiple actions

Use multi to reduce round-trips and to group actions under a single confirmation when modifying data.

jq -n --argjson version 6 --arg query "deck:French" \
	'{action:"multi", version:$version, params:{actions:[
		{action:"findNotes", params:{query:$query}},
		{action:"notesInfo", params:{notes:[]}} 
	]}}' \
| curl -sS http://127.0.0.1:8765 -X POST -H 'Content-Type: application/json' -d @-

Replace the empty array with the result of the previous action when chaining; in CLI usage, split into two calls unless using a scripting language.

Core Workflow Guidance

1) Verify connectivity and version

  • Call requestPermission (safe).
  • Call version to confirm the API level and use version: 6 in requests.

2) Discover supported actions

  • Use apiReflect with scopes: ["actions"] to list supported actions.
  • Use this list to map user intent to action names.

3) Resolve user request into action sequence

  • Identify read-only vs destructive operations.
  • For destructive/modifying operations on notes/cards, request confirmation once with the scope and count.
  • Prefer findNotes/findCards + notesInfo/cardsInfo for previews before modification.

4) Execute and validate

  • Execute the call(s) in order.
  • Check error for each response.
  • Report summarized results and any IDs returned.

Common Task Recipes (CLI-Oriented)

List decks

  • Action: deckNames

Create deck

  • Action: createDeck
  • Confirmation required if the deck is being created as part of a card/note modification workflow.

Search notes / cards

  • Actions: findNotes, findCards
  • Use Anki search syntax (see “Search Syntax Quick Notes” below).

Preview note data

  • Action: notesInfo (note IDs)

Add notes

  • Actions: addNote, addNotes
  • Confirmation required.
  • Use canAddNotes or canAddNotesWithErrorDetail for preflight checks.

Update note fields or tags

  • Actions: updateNoteFields, updateNoteTags, or combined updateNote
  • Confirmation required.
  • Warning: Do not have the note open in the browser; updates may fail to apply.

Delete notes

  • Action: deleteNotes
  • Confirmation required.

Suspend/unsuspend cards

  • Actions: suspend, unsuspend
  • Confirmation required.

Move cards to a deck

  • Action: changeDeck
  • Confirmation required.

Set due date or reschedule

  • Action: setDueDate
  • Confirmation required.

Media upload/download

  • Actions: storeMediaFile, retrieveMediaFile, getMediaFilesNames, getMediaDirPath, deleteMediaFile
  • Use base64 (data), file path (path), or URL (url) for upload.

Sync

  • Action: sync

Search Syntax Quick Notes (for findNotes/findCards)

  • Separate terms by spaces; terms are ANDed by default.
  • Use or, parentheses, and - for NOT logic.
  • Use deck:Name, tag:tagname, note:ModelName, card:CardName.
  • Use front:... or other field names to limit by field.
  • Use re: for regex, w: for word-boundary searches, nc: to ignore accents.
  • Use is:due, is:new, is:learn, is:review, is:suspended, is:buried to filter card states.
  • Use prop: searches for properties like interval or due date.
  • Escape special characters with quotes or backslashes as needed.

Action Catalog (Use as a mapping reference)

Card Actions

  • getEaseFactors
  • setEaseFactors
  • setSpecificValueOfCard
  • suspend
  • unsuspend
  • suspended
  • areSuspended
  • areDue
  • getIntervals
  • findCards
  • cardsToNotes
  • cardsModTime
  • cardsInfo
  • forgetCards
  • relearnCards
  • answerCards
  • setDueDate

Deck Actions

  • deckNames
  • deckNamesAndIds
  • getDecks
  • createDeck
  • changeDeck
  • deleteDecks
  • getDeckConfig
  • saveDeckConfig
  • setDeckConfigId
  • cloneDeckConfigId
  • removeDeckConfigId
  • getDeckStats

Graphical Actions

  • guiBrowse
  • guiSelectCard
  • guiSelectedNotes
  • guiAddCards
  • guiEditNote
  • guiAddNoteSetData
  • guiCurrentCard
  • guiStartCardTimer
  • guiShowQuestion
  • guiShowAnswer
  • guiAnswerCard
  • guiUndo
  • guiDeckOverview
  • guiDeckBrowser
  • guiDeckReview
  • guiImportFile
  • guiExitAnki
  • guiCheckDatabase
  • guiPlayAudio

Media Actions

  • storeMediaFile
  • retrieveMediaFile
  • getMediaFilesNames
  • getMediaDirPath
  • deleteMediaFile

Miscellaneous Actions

  • requestPermission
  • version
  • apiReflect
  • sync
  • getProfiles
  • getActiveProfile
  • loadProfile
  • multi
  • exportPackage
  • importPackage
  • reloadCollection

Model Actions

  • modelNames
  • modelNamesAndIds
  • findModelsById
  • findModelsByName
  • modelFieldNames
  • modelFieldDescriptions
  • modelFieldFonts
  • modelFieldsOnTemplates
  • createModel
  • modelTemplates
  • modelStyling
  • updateModelTemplates
  • updateModelStyling
  • findAndReplaceInModels
  • modelTemplateRename
  • modelTemplateReposition
  • modelTemplateAdd
  • modelTemplateRemove
  • modelFieldRename
  • modelFieldReposition
  • modelFieldAdd
  • modelFieldRemove
  • modelFieldSetFont
  • modelFieldSetFontSize
  • modelFieldSetDescription

Note Actions

  • addNote
  • addNotes
  • canAddNotes
  • canAddNotesWithErrorDetail
  • updateNoteFields
  • updateNote
  • updateNoteModel
  • updateNoteTags
  • getNoteTags
  • addTags
  • removeTags
  • getTags
  • clearUnusedTags
  • replaceTags
  • replaceTagsInAllNotes
  • findNotes
  • notesInfo
  • notesModTime
  • deleteNotes
  • removeEmptyNotes

Statistic Actions

  • getNumCardsReviewedToday
  • getNumCardsReviewedByDay
  • getCollectionStatsHTML
  • cardReviews
  • getReviewsOfCards
  • getLatestReviewID
  • insertReviews

Notes and Pitfalls

  • Keep Anki in the foreground on macOS or disable App Nap to prevent AnkiConnect from pausing.
  • When updating a note, ensure it is not being viewed in the browser editor; updates may not apply.
  • importPackage paths are relative to the Anki collection.media folder, not the client.
  • deleteDecks requires cardsToo: true to delete cards along with decks.

Resources

No bundled scripts or assets are required for this skill.

FAQ

What does the anki-connect skill do?

This skill is for interacting with Anki through AnkiConnect, and should be used whenever a user asks to interact with Anki, including to read or modify decks, notes, cards, models, media, or sync operations.

How do I install anki-connect?

Run npx skills add https://github.com/intellectronica/agent-skills --skill anki-connect in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/anki-connect/ (personal) or .claude/skills/anki-connect/ (project).

Which AI agents can use anki-connect?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is anki-connect safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains anki-connect?

It is published by intellectronica in intellectronica/agent-skills. It has 896 recorded installs.

More from intellectronica/agent-skills

View all →

notion-api

intellectronica/agent-skills

This skill provides comprehensive instructions for interacting with the Notion API via REST calls. This skill should be used whenever the user asks to interact with Notion, including reading, creating, updating, or deleting pages, databases, blocks, comments, or any other Notion content. The skill covers authentication, all available endpoints, pagination, error handling, and best practices.

context7

intellectronica/agent-skills

Retrieve up-to-date documentation for software libraries, frameworks, and components via the Context7 API. This skill should be used when looking up documentation for any programming library or framework, finding code examples for specific APIs or features, verifying correct usage of library functions, or obtaining current information about library APIs that may have changed since training.

Docs & Writing11.2K installs

youtube-transcript

intellectronica/agent-skills

Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com/watch?v=, youtu.be/, or similar). Supports output with or without timestamps.

AI & Agents3.4K installs

nano-banana-pro

intellectronica/agent-skills

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

Media & Creative3.2K installs

ultrathink

intellectronica/agent-skills

Display colorful ANSI art of the word "ultrathink". Use when the user says "ultrathink" or invokes /ultrathink.

AI & Agents1.9K installs

beautiful-mermaid

intellectronica/agent-skills

Render Mermaid diagrams as SVG and PNG using the Beautiful Mermaid library. Use when the user asks to render a Mermaid diagram.

Docs & Writing1.8K installs

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs