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.

36

Quality

32%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/voice-agents/SKILL.md

The canonical home for this skill is voice-agents in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

30%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 a skeletal, partly-broken outline: it surfaces the right architectural concepts but delivers almost no executable guidance, no sequenced workflow, and a placeholder sharp-edges table. It reads as an unfinished draft rather than a usable skill.

Suggestions

Replace the placeholder Sharp Edges table with real solutions — concrete latency budgets (e.g., target ms per component), jitter thresholds, and named semantic-VAD / barge-in implementation steps.

Finish the truncated intro ('Mos...') and remove the duplicated persona paragraph so the body does not merely restate the description.

Add an actionable workflow for the core task (e.g., choosing S2S vs. pipeline → budgeting latency per component → measuring/validating end-to-end), with explicit validate-and-fix checkpoints.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (it does not explain what STT/TTS is), but it wastes tokens on a duplicated persona intro and an 8-row placeholder 'Sharp Edges' table whose solution cells are bare header fragments, so it could be tightened — anchor 3.

3 / 5

Actionability

Guidance is almost entirely abstract — Patterns are one-line descriptions and the Sharp Edges 'solutions' are empty header fragments with no code, commands, latency numbers, or thresholds; named techniques (semantic VAD, barge-in, jitter) provide only minimal concrete hints, matching anchor 2.

2 / 5

Workflow Clarity

There is no sequenced workflow and no validation checkpoints anywhere in the body, and it is not a single-action skill with an unambiguous action, matching anchor 1 ('steps missing... no sequence').

1 / 5

Progressive Disclosure

Section headers exist (Capabilities, Patterns, Anti-Patterns, Sharp Edges) but no bundle files or external references are present and the inline content is thin and partly broken (mid-sentence truncation 'Mos' and a placeholder table), so structure is present but poorly organized — anchor 3.

3 / 5

Total

9

/

20

Passed

Description

35%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 is a second-person persona statement that names the voice-agent/latency niche clearly but never states what the skill does or when to invoke it. It is reasonably distinctive yet light on actions and trigger guidance.

Suggestions

Rewrite in third person and lead with concrete actions the skill performs (e.g., 'Designs and tunes production voice-agent architectures; budgets end-to-end latency across STT, LLM, and TTS components').

Add an explicit 'Use when...' trigger clause listing natural phrases users would say (voice agent, voicebot, conversational AI, call agent, realtime voice, latency budget).

Include the key architectural choice (S2S vs. pipeline) and a couple of natural trigger synonyms so the description answers both 'what' and 'when'.

DimensionReasoningScore

Specificity

It names the domain ('voice AI architect', 'production voice agents', 'physics of latency') but lists no concrete skill actions — it is persona framing, not a function description; the second-person voice ('You are...', 'You understand...') triggers the rubric's -1 penalty, dropping the baseline 2 to 1.

1 / 5

Completeness

It offers only a vague 'what' (a persona and insight rather than a stated function) and provides no 'when' / 'Use when' clause at all, matching anchor 2 and satisfying the missing-trigger cap of 3.

2 / 5

Trigger Term Quality

It includes some relevant natural terms ('voice AI', 'voice agents', 'latency') but misses common variations and synonyms users might say (voicebot, IVR, conversational AI, phone/call agent, realtime voice), matching anchor 3.

3 / 5

Distinctiveness Conflict Risk

'Voice agents' is a clear, fairly distinct niche with only minor overlap risk against generic LLM-architect / conversational-AI skills, matching anchor 4.

4 / 5

Total

10

/

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
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.