CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-video-calls-tavus

AI video conversations - create real-time video calls with AI personas

49

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/research-tools/capabilities/ai-video-calls-tavus/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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 is well-structured with executable curl scaffolding and a dynamic discovery path, but is held back by a malformed Create Conversation JSON example that drops the required parameter, duplicated capability prose, and an only-implied workflow sequence.

Suggestions

Fix the Create Conversation curl so persona_id and conversation_name are inside a single valid -d JSON object, e.g. -d '{"api":"tavus","path":"/v2/conversations","persona_id":"<id>","conversation_name":"Customer Support Call"}'.

Remove the verbatim duplication between the Capabilities and Usage sections; keep a one-line summary in Capabilities and the detail in Usage.

Present the list-personas-then-create flow as an explicit numbered sequence showing how the persona_id from the list response is passed into the create request.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete curl examples, but the capability descriptions ('This endpoint returns a list of all Personas' and the 'see, hear, and respond like a human' persona sentence) are repeated verbatim across the Capabilities and Usage sections, which is unnecessary padding that could be tightened.

3 / 5

Actionability

Provides concrete curl commands, but the Create Conversation example has malformed JSON: the -d payload closes after the path object, leaving the required persona_id and conversation_name as stray lines outside the request body, so the headline example is not copy-paste executable and omits the required parameter.

3 / 5

Workflow Clarity

A rough sequence is described in prose ('first list the Personas... then... create a conversation with that persona providing the persona ID'), but there is no numbered sequence or validation checkpoint, and the broken create example obscures how the persona_id actually flows into the request.

3 / 5

Progressive Disclosure

Content is well-organized into clear sections (Setup, Capabilities, Usage, Use Cases, Discover More) with a dynamic discovery mechanism via the search/details endpoints and no need for external bundle files; the only minor gap is the Capabilities/Usage description redundancy.

4 / 5

Total

13

/

20

Passed

Description

53%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.

The description conveys a clear, distinct niche and a concrete core action, but lacks an explicit 'Use when...' trigger clause and has only partial keyword coverage, capping completeness and trigger quality at the midpoint.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to start a real-time video call with an AI persona or digital avatar.'

Broaden trigger terms with natural synonyms such as 'AI avatar', 'video chat', and 'digital twin' so the description matches more user phrasings.

List 1-2 additional concrete actions (e.g. 'list available personas', 'manage conversations') to lift specificity beyond a single action.

DimensionReasoningScore

Specificity

Names the domain ('AI video conversations') and one concrete action ('create real-time video calls with AI personas') but offers no broader coverage of capabilities, matching the anchor for 1-2 concrete actions without being comprehensive.

3 / 5

Completeness

The 'what' is clear (create real-time video calls with AI personas) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Includes relevant natural terms ('video calls', 'AI personas', 'video conversations') a user might say, but misses common variations/synonyms like 'AI avatar', 'video chat', or 'digital twin', so coverage is partial rather than comprehensive.

3 / 5

Distinctiveness Conflict Risk

The niche (AI video calls with AI personas) is clearly distinct from most skills with only minor overlap risk against closely related conversational-AI skills, fitting 'mostly distinct' better than the fully-triggered anchor 5.

4 / 5

Total

13

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
gooseworks-ai/goose-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.