heartmula

HeartMuLa: Suno-like song generation from lyrics + tags.

Quality

68%

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 ./optional-skills/creative/heartmula/SKILL.md

Quality

Content

82%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 is a strong, highly actionable single-file guide with concrete commands, precise patches, and a clear install sequence. Its main weakness is a minor conciseness redundancy and the lack of an explicit post-install validation checkpoint.

Suggestions

Dedupe the overview ('Generates full songs from lyrics + tags. Comparable to Suno for open-source.') since the bulleted component list and frontmatter already convey this.

Add an explicit validation/smoke-test checkpoint after step 5 (e.g., a one-line command to confirm the patched model loads) to close the workflow validation gap.

Reconcile the license inconsistency (frontmatter says MIT, body says Apache-2.0) to avoid a factual conflict.

Dimension	Reasoning	Score
Conciseness	The body is dense and actionable (commands, patches, parameter table) with only minor over-explanation/redundancy (the overview restates 'Generates full songs from lyrics + tags. Comparable to Suno'), fitting the 'efficient; minor instances that could be trimmed' anchor rather than the fully lean 5.	4 / 5
Actionability	Copy-paste ready commands (git clone, uv venv, hf download), an exact runnable generation invocation, a parameter table, and precise source patches with file paths and insertion points cover the common cases fully.	5 / 5
Workflow Clarity	Installation is a clearly numbered 1-5 sequence with GPU verification guidance present, but there is no explicit post-install validation/smoke checkpoint, matching 'clear sequence with most checkpoints present; minor validation gaps'.	4 / 5
Progressive Disclosure	A single self-contained, well-sectioned file (Overview, When to Use, Hardware, Installation, GPU, Usage, Pitfalls, Links) with no bundle files and no content clearly needing separation; it does not match the 5 anchor's emphasis on one-level-deep references to separate files.	4 / 5
	Total	17 / 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 conveys a clear, distinctive capability (Suno-like song generation from lyrics and tags) but omits any explicit trigger guidance, which caps its completeness. Adding a 'Use when...' clause and more natural trigger terms (music, audio) would lift several dimensions.

Suggestions

Add an explicit 'Use when...' clause listing trigger scenarios (e.g., user wants to generate songs/music, asks for an open-source Suno alternative).

Broaden natural trigger terms to include 'music', 'audio', 'make a song', and 'AI music generation' beyond 'Suno-like'.

Optionally surface one or two additional concrete actions (e.g., transcribe lyrics, align audio-text) to raise specificity from a single composite action to a list.

Dimension	Reasoning	Score
Specificity	Quotes 'song generation from lyrics + tags' name the domain plus two concrete inputs but describe only one composite action, matching the '1-2 concrete actions, not comprehensive' anchor rather than the multiple-action list of 4.	3 / 5
Completeness	The 'what' is clear ('song generation from lyrics + tags') but there is no 'Use when...' or equivalent trigger guidance; per the rubric guideline, missing trigger guidance caps completeness at 3, matching the 'clear what, when missing' anchor.	3 / 5
Trigger Term Quality	'Suno-like', 'song generation', 'lyrics + tags' provide some natural terms but miss common variations users would say ('music', 'audio', 'make a song'), fitting the 'some relevant keywords but missing synonyms' anchor.	3 / 5
Distinctiveness Conflict Risk	The named 'HeartMuLa' and 'Suno-like song generation' niche is mostly distinct with only minor overlap risk against general music-generation skills, but trigger phrasing is thinner than the comprehensive 5 anchor.	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: NousResearch/hermes-agent
Path: optional-skills/creative/heartmula/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.