voice-clone-lab

Create and register cloned voices for later TTS only when the speaker has explicit consent. Use when the user asks for voice clone, clone voice, 克隆音色, 复刻声音, or wants a reusable voice_id.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./src/opensquilla/skills/bundled/voice-clone-lab/SKILL.md

Quality

Content

75%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 content is a well-structured, consent-first instruction skill that tells Claude exactly which tools to call, which fields to gather, and how to handle each tool result. It balances clarity with brevity and embeds explicit consent validation and rights guardrails into the workflow.

Suggestions

De-duplicate the 'OpenRouter is not an audio provider and cannot replace explicit consent' statement that appears in both the intro and Request triage sections.

Make the retry loop explicit in the workflow (after asking for missing consent_metadata, re-attempt voice_clone once consent is complete) so the feedback path is unambiguous.

Consider moving the per-language locale/accent guidance into a short reference table to tighten the Locale and accent quality notes section.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence without explaining basic concepts, though the OpenRouter/consent disclaimer is restated near-verbatim in two sections and could be consolidated.	4 / 5
Actionability	Concrete, specific guidance for an instruction-only skill: exact triage fields, required consent_metadata fields, named tool calls (audio_provider_capabilities, voice_clone), and a defined output contract; minor gaps in exact parameter schemas.	4 / 5
Workflow Clarity	A clear 7-step numbered consent-first workflow with an explicit validation checkpoint (reject/stop when consent is missing or vague) and a feedback loop (consent_required → ask one concise question), though the retry-after-clarification loop is implied rather than crisply numbered.	4 / 5
Progressive Disclosure	Single self-contained SKILL.md with well-organized section headers (Request triage, Consent-first workflow, Tool-result handling, Rights and copyright guard, Locale notes, Output contract) and no nested references; no bundle files are present so all content is appropriately inline.	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.

The description is well-constructed: it clearly states its purpose and consent-gating, provides a concrete 'Use when' clause, and lists natural bilingual trigger terms. It is specific enough to fire reliably for the right intent while avoiding generic language.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ('Create and register cloned voices for later TTS') plus a consent condition, but does not enumerate a comprehensive set of capabilities.	3 / 5
Completeness	Explicitly states what it does ('Create and register cloned voices for later TTS only when the speaker has explicit consent') and when to use it via a concrete 'Use when the user asks for...' clause with trigger phrases.	5 / 5
Trigger Term Quality	Strong coverage of natural synonyms including bilingual terms ('voice clone', 'clone voice', '克隆音色', '复刻声音', 'reusable voice_id'), though 'voice cloning' and '声音克隆' are absent.	4 / 5
Distinctiveness Conflict Risk	Voice cloning for TTS is a clear niche with distinct, specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: TokenRhythm/opensquilla
Path: src/opensquilla/skills/bundled/voice-clone-lab/SKILL.md
Commit: 94ac35e

Reviewed: 4 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.