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.
Install with Tessl CLI
npx tessl i github:intellectronica/agent-skills --skill anki-connect81
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillAgent success when using this skill
Validation for skill structure
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description adequately identifies when to use the skill and targets a distinct domain (Anki/AnkiConnect), but lacks specificity in concrete actions and misses common user vocabulary like 'flashcards' or 'spaced repetition'. The structure is functional but could be more actionable.
Suggestions
Add specific concrete actions like 'create flashcards', 'import/export decks', 'schedule reviews', 'add media to cards' instead of generic 'read or modify'.
Include natural trigger terms users would say: 'flashcards', 'spaced repetition', 'SRS', 'study', 'memorize', 'learning cards'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Anki/AnkiConnect) and lists categories of actions (read/modify decks, notes, cards, models, media, sync), but doesn't describe concrete specific actions like 'create flashcards', 'export decks', or 'schedule reviews'. | 2 / 3 |
Completeness | Explicitly answers both what ('interacting with Anki through AnkiConnect' with listed operations) and when ('should be used whenever a user asks to interact with Anki'), providing clear trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes 'Anki', 'AnkiConnect', 'decks', 'notes', 'cards' which are relevant terms, but misses common user phrases like 'flashcards', 'spaced repetition', 'study', 'memorize', or 'SRS'. | 2 / 3 |
Distinctiveness Conflict Risk | Anki and AnkiConnect are highly specific tools with a clear niche; unlikely to conflict with other skills since the domain is well-defined and distinct. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with excellent workflow clarity and safety considerations. The curl+jq patterns are immediately executable and the confirmation policy is appropriately strict. However, the skill could be more concise by removing the exhaustive action catalog (discoverable via API) and splitting reference material into separate files.
Suggestions
Move the Action Catalog to a separate ACTIONS_REFERENCE.md file and reference it from the main skill, since actions are discoverable via apiReflect
Move Search Syntax Quick Notes to a separate SEARCH_SYNTAX.md file to reduce main skill length
Remove explanatory text that Claude already knows (e.g., 'Every request is JSON with...' - Claude understands JSON APIs)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally efficient but includes some redundancy, such as listing all actions in a catalog that Claude could discover via apiReflect, and the search syntax section explains concepts Claude likely knows. The safety policy section, while important, is somewhat verbose. | 2 / 3 |
Actionability | Provides fully executable curl+jq patterns that are copy-paste ready, with concrete examples for request building, response handling, and batching. The recipes section gives specific action names and clear guidance for common tasks. | 3 / 3 |
Workflow Clarity | Clear 4-step workflow (verify connectivity → discover actions → resolve request → execute and validate) with explicit validation checkpoints. The safety policy establishes clear confirmation gates before destructive operations, and error checking is explicitly required for each response. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but the skill is monolithic at ~300 lines. The action catalog and search syntax sections could be split into reference files. The 'Resources' section explicitly states no external files exist, missing an opportunity for better organization. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.