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.
86
83%
Does it follow best practices?
Impact
87%
1.27xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description that clearly identifies its niche (Anki/AnkiConnect) and provides explicit 'when to use' guidance. Its main weakness is that the capabilities are listed at a category level (decks, notes, cards) rather than as specific concrete actions (create flashcards, browse notes, export decks). The description also uses 'This skill is for' phrasing which, while acceptable, could be more action-oriented.
Suggestions
Replace category-level terms with specific concrete actions, e.g., 'Creates and modifies flashcards, manages decks, searches notes, adds media, and triggers sync operations through AnkiConnect'
Add a few more natural user phrasings like 'flashcards', 'spaced repetition', or 'study' which users might say when they want Anki help but don't mention Anki by name
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Anki via AnkiConnect) and lists categories of actions (read or modify decks, notes, cards, models, media, sync operations), but doesn't describe specific concrete actions like 'create flashcards', 'export decks', or 'search notes'. The actions are more like entity categories than concrete operations. | 2 / 3 |
Completeness | Clearly answers both 'what' (interacting with Anki through AnkiConnect to read/modify decks, notes, cards, models, media, or sync) and 'when' ('should be used whenever a user asks to interact with Anki'). Has an explicit trigger clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'Anki', 'AnkiConnect', 'decks', 'notes', 'cards', 'models', 'media', 'sync'. These are terms users would naturally use when asking about Anki-related tasks. Good coverage of the domain vocabulary. | 3 / 3 |
Distinctiveness Conflict Risk | Anki and AnkiConnect are very specific tools with a clear niche. The description is unlikely to conflict with other skills since it targets a distinct application and API. The trigger terms are highly specific to this domain. | 3 / 3 |
Total | 11 / 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 safety policies and clear workflow guidance. Its main weakness is length — the inline action catalog and some reference material inflate the token cost significantly and would benefit from being split into separate reference files. The executable curl+jq patterns and thorough confirmation policy are standout strengths.
Suggestions
Move the Action Catalog section to a separate ACTIONS_REFERENCE.md file and link to it from the main skill, reducing token usage significantly.
Move the Search Syntax Quick Notes to a separate SEARCH_SYNTAX.md reference file, keeping only a brief mention and link in the main skill.
Remove or condense the API Fundamentals section — Claude already understands JSON request/response patterns; a single example suffices.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes a large action catalog that serves as a reference dump. The search syntax section and action catalog could be moved to separate reference files. Some sections like 'API Fundamentals' explain things Claude likely already knows (JSON request/response format). | 2 / 3 |
Actionability | Provides fully executable curl+jq patterns that are copy-paste ready, concrete action names for every task, and specific parameter examples. The CLI-oriented recipes map directly to user intents with clear action names and notes about required confirmations. | 3 / 3 |
Workflow Clarity | The core workflow is clearly sequenced (verify connectivity → discover actions → resolve intent → execute and validate) with explicit validation steps (check error before result, use canAddNotes for preflight, preview before modification). The safety/confirmation policy is thorough with explicit feedback loops. | 3 / 3 |
Progressive Disclosure | The skill is a monolithic document with the full action catalog inline (~80+ action names) that would be better as a separate reference file. The search syntax and action catalog sections bloat the main file when they could be linked references. However, the top-level organization with clear headers is reasonable. | 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.
- Repository
- intellectronica/agent-skills
- Commit
9b0e00a
- 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.