songsee

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

Quality

73%

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

Fix and improve this skill with Tessl

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

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

Quality

Content

92%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 quick-start: fully executable commands covering the main usage patterns, a compact flag reference, and just enough notes about decoding and grid rendering. The only improvement area is supplying example values or defaults for the numeric flags so the reference is fully self-sufficient.

Suggestions

Add example values or defaults for numeric flags (e.g. "--window 2048 --hop 512", "--width 1200 --height 600") so the flag reference is actionable without consulting external docs.

Briefly state what each --viz panel type produces (one word each) so users can choose panels without guessing.

Dimension	Reasoning	Score
Conciseness	The body is a lean command listing ("songsee track.mp3", "cat track.mp3 \| songsee - --format png") with zero explanations of concepts Claude already knows and no padding; every token earns its place.	5 / 5
Actionability	Quick-start commands are copy-paste executable and cover the common cases (single spectrogram, multi-panel, time slice, stdin), but a few flags ("--window / --hop FFT settings", "--width / --height") lack example values or defaults, leaving minor gaps.	4 / 5
Workflow Clarity	This is a simple single-purpose skill and the single action (invoke songsee with the shown flag patterns) is unambiguous; the simple-skill exception applies and there are no destructive or batch operations requiring validation.	5 / 5
Progressive Disclosure	At roughly 25 lines with no need for external references (none exist in the bundle) and well-organized sections (Quick start, Common flags, Notes), this meets the rubric's criterion for a top progressive-disclosure score on small skills.	5 / 5
	Total	19 / 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 is clear and appropriately concrete about what the tool does, with a distinct niche (audio spectrogram generation via a named CLI). Its main weakness is the complete absence of any trigger guidance and limited natural-keyword coverage, which leaves users and Claude without explicit cues for when to reach for this skill.

Suggestions

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

Include natural synonyms users would actually say, such as "waveform", "audio analysis", "visualize audio", and common audio file extensions, to improve trigger-term coverage.

Consider naming one or two more concrete capabilities (e.g. time-sliced rendering, styled multi-panel grids, PNG/JPG output) to lift specificity beyond two actions.

Dimension	Reasoning	Score
Specificity	"Generate spectrograms and feature-panel visualizations from audio" names the domain and two concrete actions, but coverage is not comprehensive (no styles, time slices, or output formats mentioned), matching the '1-2 concrete actions' anchor rather than the 'several specific actions' anchor.	3 / 5
Completeness	The "what" is clear (generate spectrograms and feature panels from audio), but there is no "Use when..." clause or equivalent trigger guidance, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	"spectrograms", "feature-panel visualizations", and "audio" are relevant keywords, but common variations users would naturally say ("waveform", "visualize audio", "audio analysis", ".mp3") are missing, which fits the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	"from audio with the songsee CLI" carves a distinct niche with a named tool, leaving only minor overlap risk with general charting/visualization skills; it falls just short of the 'minimal conflict risk' anchor because "visualizations" is a broad term.	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: Bitterbot-AI/bitterbot-desktop
Path: skills/songsee/SKILL.md
Commit: 1c7dc1b

Reviewed: 20 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.