songsee

Audio spectrograms/features (mel, chroma, MFCC) via CLI.

Quality

82%

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

Quality

Content

100%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 body is exemplary: concise, fully executable, and well organized. The Quick Start examples plus the two reference tables give Claude everything needed to run the tool correctly on the first try, with no padding or background filler.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout: executable commands, compact tables for viz types and flags, and no concept explanations Claude already knows (e.g., no 'what a spectrogram is' preamble). Every line ('WAV and MP3 are decoded natively; other formats require ffmpeg', the vision_analyze note) adds non-obvious information.	5 / 5
Actionability	Everything is copy-paste ready: the install command ('go install github.com/steipete/songsee/cmd/songsee@latest') and Quick Start examples ('songsee track.mp3 -o spectrogram.png', '--viz spectrogram,mel,...', '--start 12.5 --duration 8', stdin pipe) cover the common cases, and the Common Flags table documents every option with concrete values ('classic', 'magma', 'inferno', 'viridis', 'gray').	5 / 5
Workflow Clarity	This is a simple, single-purpose CLI-wrapper skill and the single action is unambiguous: prerequisites (install, optional ffmpeg) then run songsee with documented flags. It is not a destructive or batch operation, so the validation cap does not apply, and the per-example flag usage leaves no sequence gaps.	5 / 5
Progressive Disclosure	The skill needs no external reference files (none exist in the bundle) and the body is short with well-organized sections (Prerequisites, Quick Start, Visualization Types, Common Flags, Notes); nothing that belongs in a separate file is inlined, and no referenced paths are broken.	5 / 5
	Total	20 / 20 Passed

Description

65%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 terse and technically precise, with good domain keywords and excellent distinctiveness, but it is incomplete: it names features rather than actions and entirely omits any 'when to use this' trigger guidance. Adding a Use-when clause would raise both completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when working with audio files, generating spectrograms, or analyzing audio features (mel, chroma, MFCC)' — its absence currently caps completeness at 3.

Lead with action verbs instead of nouns, e.g. 'Generate spectrograms and audio feature visualizations (mel, chroma, MFCC) from audio files via CLI' to make capabilities concrete.

Include natural synonyms users would say, such as 'waveform', 'audio analysis', or 'visualize audio', to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ('Audio spectrograms/features') and three concrete feature types ('mel, chroma, MFCC'), but states no actions at all — no verbs like generate, extract, or visualize. This matches anchor 3 (domain plus a few concrete items but not comprehensive) rather than anchor 4, which requires several specific actions.	3 / 5
Completeness	The 'what' is clear (generate audio spectrograms and features via CLI), but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description, which per the judging guidelines caps completeness at 3. It is above anchor 2 because the 'what' is concrete, not vague.	3 / 5
Trigger Term Quality	Good keyword coverage with natural technical terms ('audio', 'spectrograms', 'mel', 'chroma', 'MFCC') that audio-focused users would actually say, but a few natural terms are missing (e.g., 'waveform', 'audio analysis', 'visualize'). It fits anchor 4 rather than anchor 5, which expects synonyms and file extensions.	4 / 5
Distinctiveness Conflict Risk	'mel, chroma, MFCC' plus 'spectrograms' form a clear audio-analysis niche with distinct technical triggers and minimal overlap risk with other skill domains. It clearly matches anchor 5.	5 / 5
	Total	15 / 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: NousResearch/hermes-agent
Path: skills/media/songsee/SKILL.md
Commit: 68fa7e9

Reviewed: 3 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.