CtrlK
BlogDocsLog inGet started
Tessl Logo

agents

Build voice AI agents with ElevenLabs. Use when creating voice assistants, customer service bots, interactive voice characters, or any real-time voice conversation experience.

89

1.73x
Quality

88%

Does it follow best practices?

Impact

92%

1.73x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

A highly actionable, concise, and well-structured reference skill with strong progressive disclosure and copy-paste code. The main gap is workflow clarity — content is capability-organized without explicit sequencing or validation checkpoints for the more fragile operations.

Suggestions

Add an explicit ordered 'deploy your first agent' walkthrough (create -> configure -> push -> verify with `agents status`) with a verification checkpoint after push.

Include a brief validation step for destructive/batch operations (e.g., recommend `agents push --dry-run` before `push`, and confirming before `agents delete`).

Tighten the Tools intro paragraph, which contains a long explanatory sentence that could be trimmed for token efficiency.

DimensionReasoningScore

Conciseness

Lean and code-driven throughout — no concept padding, no explanation of what voice agents or libraries are; every section is commands or executable code plus minimal framing prose that earns its place.

3 / 3

Actionability

Abundant copy-paste-ready executable examples across Python, JavaScript, cURL, CLI, and HTML, with concrete voice IDs, model names, and error codes.

3 / 3

Workflow Clarity

Sections are organized by capability rather than as a sequenced end-to-end workflow, and validation/checkpoint steps are absent; the sequence present (e.g., init -> add -> push) is light without explicit verification.

2 / 3

Progressive Disclosure

Clear overview in SKILL.md with five real one-level-deep reference files, each signaled inline and summarized in a References section; detail is appropriately pushed out of the overview.

3 / 3

Total

11

/

12

Passed

Description

90%

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 states both capability and trigger conditions with natural, distinctive keywords. The only weakness is specificity — it leads with one generic verb and enumerates agent types rather than listing multiple distinct concrete actions.

Suggestions

Lead with more concrete verbs (e.g., 'Create, configure, and deploy voice AI agents...') to broaden the action specificity beyond 'Build'.

Consider naming a concrete deliverable (e.g., 'with web embedding and outbound calling') to make the capability range more tangible.

DimensionReasoningScore

Specificity

Names the domain ('voice AI agents') and several agent types ('voice assistants, customer service bots, interactive voice characters'), but centers on a single generic verb ('Build') rather than multiple distinct concrete actions.

2 / 3

Completeness

Explicitly answers both what ('Build voice AI agents with ElevenLabs') and when ('Use when creating voice assistants...'), with an explicit trigger clause.

3 / 3

Trigger Term Quality

Good natural coverage with terms users would actually say — 'voice assistants', 'customer service bots', 'interactive voice characters', and 'real-time voice conversation'.

3 / 3

Distinctiveness Conflict Risk

Clear niche (ElevenLabs real-time voice agents) with distinct voice-specific triggers unlikely to fire for non-voice skills.

3 / 3

Total

11

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
calesthio/OpenMontage
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.