CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

79

1.27x
Quality

72%

Does it follow best practices?

Impact

87%

1.27x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/anki-connect/skills/SKILL.md

The canonical home for this skill is anki-connect in intellectronica/agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

57%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body delivers concrete, executable curl+jq guidance and a sensible workflow with a strong safety/confirmation policy. Its weaknesses are an oversized inline action catalog that bloats the file and the absence of an explicit verify-after-modify feedback loop for destructive operations.

Suggestions

Move the Action Catalog into a separate references file (e.g. actions.md) and link to it from the body to reduce token load and improve progressive disclosure.

Add an explicit post-modification verification step to the workflow (e.g., re-query with notesInfo/cardsInfo after add/update/delete to confirm the change applied), which would raise workflow clarity above the destructive/batch cap of 3.

Tighten the Common Task Recipes section by consolidating the repeated 'Confirmation required' notes into a single referenced policy statement instead of restating it per recipe.

DimensionReasoningScore

Conciseness

Mostly efficient technical content with executable templates, but the large inline Action Catalog (~150 action names) and some recipe listings could be tightened or moved to a reference file, adding bulk that doesn't all earn its place.

3 / 5

Actionability

Provides copy-paste-ready curl+jq request templates, explicit request/response formats, and per-task action mappings; minor gaps like the empty-array placeholder in the multi example keep it just short of fully executable.

4 / 5

Workflow Clarity

A clear 4-step core workflow with error-checking and a confirmation policy exists, but destructive/batch operations lack an explicit post-modification verification feedback loop, capping this dimension at 3 per the rubric.

3 / 5

Progressive Disclosure

Well-organized with clear section headers, but the substantial inline Action Catalog is content that would be better split into a separate reference file; no external references are signaled despite the bulk.

3 / 5

Total

13

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly defines both purpose and trigger conditions with concrete, natural terminology. The main weakness is reliance on generic "read or modify" verbs rather than enumerating distinct actions.

DimensionReasoningScore

Specificity

Names the AnkiConnect domain and several concrete objects ("decks, notes, cards, models, media, or sync operations"), but the verbs are limited to generic "read or modify" rather than distinct concrete actions, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly states what the skill does ("interacting with Anki through AnkiConnect") and when to use it ("should be used whenever a user asks to interact with Anki, including to read or modify...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural terms users would say ("Anki", "decks", "notes", "cards", "sync") with good coverage, though a few common variations or synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (Anki via AnkiConnect) with distinct triggers, making conflict with other skills minimal.

5 / 5

Total

18

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
intellectronica/agent-skills
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.