heartmula

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

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/media/heartmula/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable, copy-paste-ready install and usage guidance, but it is monolithic with no progressive disclosure of detail into bundle files and lacks explicit validation checkpoints in the install/patch workflow. Tightening repeated prose and isolating time-sensitive notes would improve conciseness.

Suggestions

Add explicit verification checkpoints after risky steps (e.g. "Run `python -c 'import heartlib'` to confirm the install" and "Re-run generation on a short sample to confirm the patch applied").

Move the patch details and/or the API parameter table into separate reference files (e.g. PATCHES.md, PARAMETERS.md) and link to them from the body to enable progressive disclosure.

Move the "As of Feb 2026" dependency-fix and version notes into a dedicated "Known issues / deprecations" section and remove the Overview's restated summary to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with executable commands and tables, but includes some repetition (Overview restates "Generates full songs... Comparable to Suno") and embeds time-sensitive info ("As of Feb 2026", version numbers) in the main flow rather than a deprecation section, which the guidelines penalize.	2 / 3
Actionability	It provides fully executable install commands, exact patch code with specific file paths and method names, copy-paste-ready usage examples, and a concrete parameter table, matching anchor 3.	3 / 3
Workflow Clarity	The numbered install sequence is clear but lacks explicit validation/verification checkpoints (e.g. confirm deps installed, verify the patch applied) as structured feedback loops, matching anchor 2.	2 / 3
Progressive Disclosure	It is a single ~170-line monolithic file with no bundle references, keeping patches, parameter tables, and pitfalls inline that could be split out, though sections are well organized, matching anchor 2.	2 / 3
	Total	9 / 12 Passed

Description

57%

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 specific and occupies a distinct niche, but it omits explicit trigger guidance and relies on a product comparison ("Suno-like") as its main hook. Adding a "Use when..." clause with natural keywords would raise completeness and trigger-term quality.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when the user wants to generate songs, music, or audio from lyrics and tags, or asks for an open-source Suno alternative."

Replace or supplement "Suno-like" with natural trigger terms users would actually say (e.g. "generate songs", "make music from lyrics", "AI music generation").

Mention concrete output or capabilities (e.g. "generates full songs as MP3") to strengthen specificity beyond a single action.

Dimension	Reasoning	Score
Specificity	"Suno-like song generation from lyrics + tags" names the domain and a concrete action but lists a single capability rather than multiple distinct actions, matching anchor 2.	2 / 3
Completeness	It states what the skill does but lacks any "Use when..." trigger clause, so per the guidelines completeness is capped at 2 (has what, when is missing).	2 / 3
Trigger Term Quality	"song generation", "lyrics", and "tags" are natural user terms, but common variations are missing and the primary hook "Suno-like" is a product comparison rather than a keyword users would say, matching anchor 2.	2 / 3
Distinctiveness Conflict Risk	Music/song generation from lyrics and tags is a clear niche with distinct triggers unlikely to conflict with other skills, matching anchor 3.	3 / 3
	Total	9 / 12 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/heartmula/SKILL.md
Commit: b7a05b6

Reviewed: about 14 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.