voice-refine

Transform verbose voice input into optimized Claude prompts

Install with Tessl CLI

npx tessl i github:FlorianBruniaux/claude-code-ultimate-guide --skill voice-refine

What are skills?

1.21x

Quality

58%

Does it follow best practices?

Impact

91%

1.21x

Average score across 3 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./examples/skills/voice-refine/SKILL.md

SKILL.md

Review

Evals

Quality

Discovery

32%

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 identifies a specific niche (voice-to-prompt transformation) but is too terse to be effective. It lacks explicit trigger guidance, concrete examples of what transformations occur, and natural keyword variations that users would actually say when needing this skill.

Suggestions

Add a 'Use when...' clause with trigger terms like 'voice input', 'dictation', 'spoken prompt', 'transcribed text', or 'speech-to-text'

Specify concrete actions: what does 'optimized' mean? (e.g., 'removes filler words, structures requests, adds context')

Include file type or input format triggers if applicable (e.g., 'audio transcripts', '.txt from voice memos')

Dimension	Reasoning	Score
Specificity	Names the domain (voice input to prompts) and one action (transform), but lacks comprehensive detail about what 'optimized' means or what specific transformations occur.	2 / 3
Completeness	Describes what it does (transform voice input) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Includes 'voice input' and 'prompts' which are relevant, but misses common variations users might say like 'speech-to-text', 'dictation', 'spoken', 'transcription', or 'voice commands'.	2 / 3
Distinctiveness Conflict Risk	The 'voice input' aspect provides some distinctiveness, but 'optimized Claude prompts' is vague enough to potentially overlap with general prompt engineering or writing assistance skills.	2 / 3
	Total	7 / 12 Passed

Implementation

85%

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

This is a well-structured skill with excellent organization and clear workflow. The main weakness is that it describes what the transformation does conceptually but doesn't provide the actual implementation logic Claude would use to perform the transformation - it's more of a specification than executable guidance.

Suggestions

Add concrete transformation rules or regex patterns for the DEDUPE step (e.g., specific filler word patterns to match and remove)

Include a complete before/after example showing the exact output format populated with the French input example provided

Dimension	Reasoning	Score
Conciseness	The skill is lean and efficient, using tables and bullet points effectively. No unnecessary explanations of concepts Claude would know - it jumps straight to actionable content.	3 / 3
Actionability	Provides clear structure and examples of input/output, but lacks executable code for the actual transformation logic. The pipeline is described conceptually rather than with concrete implementation.	2 / 3
Workflow Clarity	The 4-step transformation pipeline is clearly sequenced (DEDUPE → EXTRACT → STRUCTURE → COMPRESS). The flags provide clear behavioral options, and the output format is explicit.	3 / 3
Progressive Disclosure	Well-organized with clear sections, appropriate use of tables for flags and metrics, and references to external files (guide/ai-ecosystem.md, examples/before-after.md) for deeper content.	3 / 3
	Total	11 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Reviewed: about 7 hours 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.