voice-refine
Transform verbose voice input into structured, token-efficient Claude prompts. Use when cleaning up voice memos, dictation output, or speech-to-text transcriptions that contain filler words, repetitions, and unstructured thoughts.
63
75%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./examples/skills/voice-refine/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, well-crafted description that clearly communicates a specific capability (transforming voice input into structured prompts), includes rich natural trigger terms spanning voice memos, dictation, and speech-to-text, and provides an explicit 'Use when' clause. It occupies a distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Transform verbose voice input into structured, token-efficient Claude prompts' and describes the types of content it handles (filler words, repetitions, unstructured thoughts). Multiple specific capabilities are conveyed. | 3 / 3 |
Completeness | Clearly answers both 'what' (transform verbose voice input into structured, token-efficient prompts) and 'when' (explicit 'Use when' clause covering voice memos, dictation output, speech-to-text transcriptions with filler words, repetitions, and unstructured thoughts). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'voice input', 'voice memos', 'dictation output', 'speech-to-text', 'transcriptions', 'filler words', 'repetitions'. Good coverage of variations a user might naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche at the intersection of voice/speech-to-text processing and prompt optimization. The combination of voice input cleanup and Claude prompt structuring is highly distinctive and unlikely to conflict with general text editing or generic prompt-writing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has a clear purpose and good structural organization with useful sections like filtering rules and output format. However, it lacks concrete implementation details—the transformation pipeline is described abstractly without executable steps, and the referenced supporting files don't exist. The skill would benefit from either providing actual transformation logic or being reframed as a prompt template with a worked before/after example showing each pipeline stage.
Suggestions
Add a complete worked example showing the input voice text being transformed step-by-step through each pipeline stage (DEDUPE → EXTRACT → STRUCTURE → COMPRESS) with the actual intermediate and final output.
Either create the referenced bundle files (guide/ai-ecosystem.md, examples/before-after.md) or remove the 'See Also' references to avoid dead links.
Replace the abstract pipeline description with concrete, actionable instructions for each step—e.g., specific regex patterns for filler removal, heuristics for identifying core requirements vs. tangents.
Add a validation/feedback step: what should Claude do if the voice input is ambiguous or contradictory? Include guidance for handling edge cases like incomplete thoughts or conflicting requirements.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary elements: the 'When to Use' section lists things Claude can infer, the compression metrics table adds little actionable value, and the flags table describes features that don't clearly map to an implementation. However, the filtering rules and output format are lean. | 2 / 3 |
Actionability | The skill provides a clear output format template and filtering rules, but lacks executable implementation. The transformation pipeline is described at a high level (DEDUPE, EXTRACT, STRUCTURE, COMPRESS) without concrete code or step-by-step instructions for how to actually perform each step. The flags reference a '/voice-refine' command but no implementation is provided. | 2 / 3 |
Workflow Clarity | The 4-step pipeline (DEDUPE → EXTRACT → STRUCTURE → COMPRESS) provides a clear sequence, and the --confirm flag implies a validation checkpoint. However, there are no explicit validation steps, no error handling guidance (e.g., what if intent is ambiguous), and no feedback loop for when the compression loses important information. | 2 / 3 |
Progressive Disclosure | References to 'guide/ai-ecosystem.md' and 'examples/before-after.md' suggest good progressive disclosure intent, but no bundle files exist to support these references. The main content is reasonably organized with clear sections, but the output format template, filtering rules, and examples could arguably be split out for a cleaner overview. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%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 | |
- Commit
60a4372
- 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.