songsee

Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.

19.20x

Quality

76%

Does it follow best practices?

Impact

96%

19.20x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./openclaw/skills/songsee/SKILL.md

The canonical home for this skill is songsee in openclaw/openclaw

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 body is an exemplary lean CLI skill: copy-paste-ready commands covering the main usage patterns, a tight flag reference, and useful dependency notes with zero padding. As a short single-purpose skill with no bundle files, it satisfies workflow clarity and progressive disclosure through its clean section organization alone.

Dimension	Reasoning	Score
Conciseness	The ~25-line body is lean and efficient: every line is an executable command, a flag, or a dependency note ("WAV/MP3 decode native; other formats use ffmpeg if available"), with no explanation of concepts Claude already knows. This matches anchor 5; nothing could be trimmed without losing information.	5 / 5
Actionability	Four copy-paste-ready commands in Quick start (basic spectrogram, full multi-panel --viz chain, time slice with --start/--duration and -o, stdin pipe) cover the common cases, and Common flags enumerates the key options. This matches anchor 5 (fully executable, specific examples covering common cases); it is not anchor 4 because there are no material gaps — the -o/--format flags used in examples are self-demonstrating even though -o is not re-listed under Common flags.	5 / 5
Workflow Clarity	This is a simple, single-action skill (run songsee on an audio input) and that single action is unambiguous with concrete invocations, so per the simple-skill guideline workflow clarity scores 5. No destructive or batch operations are involved, so the validation cap does not apply.	5 / 5
Progressive Disclosure	The body is under 50 lines, requires no external references (the skill bundle has no references/, scripts/, or assets/ files), and is cleanly organized into Quick start, Common flags, and Notes sections. Per the simple-skill guideline, this matches anchor 5 (well-organized sections, no monolithic wall of text, no nested references).	5 / 5
	Total	20 / 20 Passed

Description

53%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 states a clear, concrete capability but entirely lacks "when to use" trigger guidance, which caps completeness and weakens trigger-term quality. Adding a "Use when..." clause with natural user phrasings and file extensions would address the two lowest-scoring dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to visualize, analyze, or inspect audio files (e.g. .mp3, .wav), or asks for spectrograms, waveforms, or audio feature panels."

Include natural synonyms users would actually say — "audio analysis", "waveform", "plot audio", ".mp3", ".wav" — alongside the existing "spectrograms" and "feature-panel" terms.

Optionally enumerate one or two more concrete capabilities (multi-panel visualizations like mel/chroma/loudness, time-sliced output) to lift specificity from anchor 3 toward 4.

Dimension	Reasoning	Score
Specificity	"Generate spectrograms and feature-panel visualizations from audio" names the domain and 1-2 concrete actions, matching anchor 3. It does not list several specific actions (e.g. panel types, output formats, time slicing), so it falls short of anchor 4.	3 / 5
Completeness	The description clearly answers "what" (generate spectrograms and feature panels from audio via the songsee CLI) but has no "Use when..." clause or equivalent trigger guidance. Per the judging guideline, a missing explicit trigger clause caps completeness at 3; it is not anchor 2 because the "what" is clear, not vague.	3 / 5
Trigger Term Quality	"spectrograms", "feature-panel visualizations", and "audio" are relevant keywords, but common user phrasings like "audio analysis", "waveform", or file extensions (.mp3, .wav) are absent. This matches anchor 3 (some relevant keywords, missing common variations/synonyms) rather than anchor 4's fuller coverage.	3 / 5
Distinctiveness Conflict Risk	The spectrogram/feature-panel/audio niche plus the named "songsee CLI" makes it mostly distinct with only minor overlap risk against general audio or visualization skills, matching anchor 4. It is not anchor 5 because it lacks explicit distinct trigger phrases, and not anchor 3 because the domain is more specific than generic document/file handling.	4 / 5
	Total	13 / 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: trpc-group/trpc-agent-go
Path: openclaw/skills/songsee/SKILL.md
Commit: 9bb1c42

Reviewed: 5 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.