Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.
86
83%
Does it follow best practices?
Impact
96%
19.20xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
67%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 concise and specific about what the skill does, naming concrete outputs (spectrograms, feature-panel visualizations) and the specific tool (songsee CLI). Its main weaknesses are the absence of an explicit 'Use when...' clause and limited trigger term coverage for common user phrasings related to audio analysis.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user asks to visualize audio, generate spectrograms, or analyze audio features.'
Include additional natural trigger terms users might say, such as 'audio visualization', 'frequency plot', 'mel spectrogram', '.wav', '.mp3', or 'audio analysis'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Generate spectrograms and feature-panel visualizations from audio' and names the specific tool 'songsee CLI'. These are concrete, well-defined capabilities. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (generate spectrograms and feature-panel visualizations from audio using songsee CLI), but lacks an explicit 'Use when...' clause specifying when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Includes good terms like 'spectrograms', 'audio', and 'songsee CLI', but misses common variations users might say such as 'audio visualization', 'frequency analysis', 'waveform', 'mel spectrogram', or file extensions like '.wav', '.mp3'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: audio spectrograms and feature-panel visualizations using a specific CLI tool ('songsee'). Very unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent, lean skill that efficiently teaches CLI usage for the songsee tool. It provides concrete, executable examples covering all major use cases, organizes flags and notes cleanly, and wastes no tokens on explanations Claude doesn't need. A model example of a concise single-tool skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line earns its place. No unnecessary explanations of what spectrograms are or how audio processing works. Assumes Claude's competence and provides only the essential flags and usage patterns. | 3 / 3 |
Actionability | Provides fully executable, copy-paste-ready CLI commands covering the main use cases (basic spectrogram, multi-panel, time slicing, stdin piping). Flag reference is concrete and specific. | 3 / 3 |
Workflow Clarity | This is a simple, single-purpose CLI tool skill. The usage patterns are unambiguous single-step commands, and the notes section clarifies format dependencies. No multi-step destructive operations require validation checkpoints. | 3 / 3 |
Progressive Disclosure | For a simple CLI skill under 50 lines with no need for external references, the content is well-organized into logical sections (quick start, flags, notes) that are easy to scan and navigate. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 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 | 8 / 11 Passed | |
ec8d4f8
Table of Contents
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.