CtrlK
BlogDocsLog inGet started
Tessl Logo

voice-agents

You are a voice AI architect who has shipped production voice agents handling millions of calls. You understand the physics of latency - every component adds milliseconds, and the sum determines whether conversations feel natural or awkward.

25

Quality

16%

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/voice-agents/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

18%Scale 1-5

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

This skill is essentially a skeleton or template that was never filled in with actual content. It names relevant concepts (S2S vs pipeline architectures, VAD, barge-in detection) but provides zero actionable guidance, no code examples, no workflows, and no concrete implementation details. The sharp edges table contains placeholder text ('Issue' repeated for every row) and code comments without actual code, making it unusable.

Suggestions

Add concrete, executable code examples for both S2S (e.g., OpenAI Realtime API setup) and pipeline (STT→LLM→TTS) architectures with specific library calls and configuration.

Fill in the anti-patterns with actual descriptions explaining what goes wrong and how to avoid it, rather than leaving them as empty headers.

Replace the placeholder 'Issue' entries in the Sharp Edges table with actual issue descriptions (e.g., 'Cumulative latency exceeds 500ms', 'Background noise triggers false turn detection') and provide complete code solutions rather than comment fragments.

Add a step-by-step workflow for building a voice agent, including latency measurement, validation of each pipeline component, and testing checkpoints.

DimensionReasoningScore

Conciseness

The content is relatively short but wastes tokens on vague section headers, empty anti-pattern descriptions, and a capabilities list that reads like tags rather than actionable content. The sharp edges table has placeholder 'Issue' text repeated without actual issue descriptions, which is wasted space.

3 / 5

Actionability

There is no concrete, executable guidance anywhere in this skill. No code examples, no specific commands, no copy-paste ready snippets. The sharp edges table contains code comments as 'solutions' but they are just comment fragments (e.g., '# Measure and budget latency for each component:') with no actual implementation. Patterns are described in one sentence each with no concrete steps.

1 / 5

Workflow Clarity

There are no sequenced steps, no validation checkpoints, and no workflow of any kind. The patterns section names two architectures but provides zero guidance on how to implement either one. Anti-patterns are listed as headers with no content beneath them.

1 / 5

Progressive Disclosure

The content has some section structure (Patterns, Anti-Patterns, Sharp Edges) but no references to external files, no bundle files exist, and the content that is present is skeletal/placeholder rather than well-organized. The sharp edges table appears to be a broken template with repeated 'Issue' placeholders.

2 / 5

Total

7

/

20

Passed

Description

14%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.

This description is written as a persona/identity statement rather than a functional skill description. It tells Claude who to be rather than what the skill does or when to use it. It lacks concrete actions, explicit trigger guidance, and uses first/second person framing issues (though technically third-person-adjacent, it's persona-based).

Suggestions

Replace the persona statement with concrete actions: e.g., 'Designs voice AI agent architectures, optimizes end-to-end latency, selects STT/TTS/LLM components, and configures telephony integrations.'

Add an explicit 'Use when...' clause with natural trigger terms: e.g., 'Use when the user asks about building voice bots, reducing voice agent latency, choosing speech-to-text providers, or designing real-time conversational AI systems.'

Remove the first-person persona framing ('You are a voice AI architect who has shipped...') and replace with third-person capability statements describing what the skill does.

DimensionReasoningScore

Specificity

No concrete actions are described. The description uses abstract language about being a 'voice AI architect' and 'understanding the physics of latency' without specifying what the skill actually does (e.g., design voice pipelines, optimize latency, configure STT/TTS).

1 / 5

Completeness

Neither 'what does this do' nor 'when should Claude use it' is explicitly answered. There is no 'Use when...' clause and no description of concrete capabilities—only a persona statement.

1 / 5

Trigger Term Quality

Contains some relevant terms like 'voice AI', 'voice agents', 'latency', and 'calls', but these are embedded in persona-style prose rather than presented as natural trigger keywords. Missing common user phrases like 'build a voice bot', 'reduce latency', 'speech-to-text', 'telephony'.

2 / 5

Distinctiveness Conflict Risk

The domain of 'voice AI' and 'production voice agents' is somewhat specific and narrows the scope, but without concrete actions or triggers, it could overlap with general AI architecture or latency optimization skills.

3 / 5

Total

7

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.