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.

1.73x

Quality

79%

Does it follow best practices?

Impact

92%

1.73x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agents/SKILL.md

Quality

Content

76%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.

A highly actionable, well-structured reference with copy-paste code across languages and clean navigation to real bundle files. Its main weakness is workflow safety: destructive and batch operations lack the validation checkpoints the rubric requires, capping workflow clarity.

Suggestions

Add an explicit validation/confirmation checkpoint before destructive and batch operations — e.g., wrap `agents.delete` with a 'list first, confirm the agent_id, then delete' step and recommend `agents push --dry-run` as a mandatory pre-check before every `agents push`.

Move the inline model catalog table and the exhaustive per-operation cURL blocks into references/agent-configuration.md (or a dedicated models reference), keeping SKILL.md as a tight overview with a pointer — this would lift progressive disclosure toward a 5 and reduce conciseness redundancy.

Collapse the triple-language (Python/JS/cURL) duplication for create/outbound operations: lead with one canonical SDK example and link to a language-variants section in a reference, trimming tokens without losing actionability.

Dimension	Reasoning	Score
Conciseness	Lean and code-focused with no over-explanation of concepts Claude already knows; minor trimmable redundancy in showing Python/JS/cURL for every operation and a few framing sentences — efficient but not spotless, so above the 3 anchor yet short of the 5 'every token earns its place' bar.	4 / 5
Actionability	Copy-paste-ready CLI commands and Python/JS/cURL snippets cover the common cases (create, start conversation, tools, widget, outbound calls, manage agents) with real voice IDs and concrete config; fits the fully-executable anchor and exceeds the 4 anchor's 'minor gaps' wording.	5 / 5
Workflow Clarity	Quick Start is well-sequenced and a `--dry-run` preview flag is mentioned, but destructive operations like `agents.delete` and batch `agents push` lack explicit validation/confirmation checkpoints; per the rubric cap, destructive/batch work without validation cannot exceed 3 even though sequences are present.	3 / 5
Progressive Disclosure	Clear sections with well-signaled, one-level-deep references to five verified-real files (installation, agent-configuration, client-tools, widget-embedding, outbound-calls); not a 5 because substantial bulk (the full model catalog table, exhaustive multi-language code blocks) is inlined in SKILL.md rather than split into the references.	4 / 5
	Total	16 / 20 Passed

Description

82%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, third-person description that clearly answers both what the skill does and when to invoke it, with platform-specific triggers that keep conflict risk low. The only real gap is capability breadth — a single 'Build' verb undersells the configure/embed/manage actions the body actually covers.

Dimension	Reasoning	Score
Specificity	Names the domain ("voice AI agents") and one concrete action ("Build") but offers only that single verb — no build/configure/embed/manage coverage — matching the anchor that lists 1-2 concrete actions without being comprehensive; not a 4 because it lacks several specific actions.	3 / 5
Completeness	Explicitly states both what ("Build voice AI agents with ElevenLabs") and when ("Use when creating voice assistants, customer service bots...") with concrete trigger phrases, matching the anchor that clearly answers both; not below 5 because the 'when' is specific and multi-triggered rather than vague.	5 / 5
Trigger Term Quality	Natural trigger phrases like "voice assistants", "customer service bots", "interactive voice characters", and "real-time voice conversation" give good keyword coverage; not a 5 because common synonyms (IVR, voice chatbot, AI receptionist, AI caller) are absent.	4 / 5
Distinctiveness Conflict Risk	Pinned to a specific platform ("with ElevenLabs") with a distinct voice-agent niche and dedicated triggers, giving minimal conflict risk with other skills; fits the clear-niche anchor rather than the 4 anchor that still allows overlap with closely related skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Path: .agents/skills/agents/SKILL.md
Commit: cd9f3c1

Reviewed: 13 days ago

Table of Contents

Discovery Implementation Validation

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.