songwriting-and-ai-music

Songwriting craft and Suno AI music prompts.

Quality

60%

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/creative/songwriting-and-ai-music/SKILL.md

Quality

Content

63%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 a dense, well-organized, largely actionable craft reference with a clear sequenced workflow, strong on Suno-specific knowledge that Claude would not already have. Its main weaknesses are mild over-explanation of basic songwriting theory, a monolithic single-file structure with a large inline reference catalog, and the absence of an end-to-end worked example.

Suggestions

Trim or condense the basic-theory sections (rhyme types, meter, show-don't-tell) to only what is non-obvious, since Claude already knows these concepts, to improve conciseness.

Move the metatag catalog (structure/vocal/dynamics/gender/atmosphere/SFX tags) into a references file (e.g. references/suno-metatags.md) and link to it, keeping only the most-used tags inline, to improve progressive disclosure.

Add one fully worked example — a short original or parody song with its complete Style field, lyrics, and metatag placement — to push actionability toward a 5.

Dimension	Reasoning	Score
Conciseness	The Suno-specific material (style formula, metatags, phonetic tricks) is genuinely additive and dense, but sections on basic rhyme types, meter, and show-don't-tell re-explain craft concepts Claude already knows and could be trimmed.	3 / 5
Actionability	Concrete, usable guidance abounds — the Style field FORMULA with BAD/GOOD examples, the metatag catalog, and phonetic-respelling rules are directly applicable; it falls short of 5 only because there is no single end-to-end worked example tying the pieces together.	4 / 5
Workflow Clarity	Section 8 gives a clear 10-step sequence with validation checkpoints (step 5: read/sing aloud and fix meter) and a revision feedback loop ("EXPECT: ~3-5 generations per 1 good result"), missing only explicit if/then error-recovery branching for a 5.	4 / 5
Progressive Disclosure	The body is well-sectioned with numbered headers, but it is a ~290-line monolithic SKILL.md with no external references, and the large inline metatag catalog is content that could plausibly live in a separate reference file; the under-50-line simple-skill exception does not apply.	3 / 5
	Total	14 / 20 Passed

Description

56%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 short and names a clear, distinctive niche, but it is topic-based rather than action-based and omits explicit "when to use" guidance from the description prose itself (relying on a separate triggers field). Strengthening it with concrete verbs and an inline Use-when clause would raise specificity and completeness.

Suggestions

Lead with concrete verbs, e.g. "Writes and adapts song lyrics and engineers Suno AI music prompts" to lift specificity from domain-naming to action-describing.

Add an explicit trigger clause to the description itself, e.g. "Use when writing songs or lyrics, crafting Suno/AI music prompts, or adapting or parodying existing songs," rather than relying only on the separate triggers field.

Include natural synonyms users say ("lyrics", "parody", "adapting a song") directly in the description to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The phrase "Songwriting craft and Suno AI music prompts" names the domain clearly but uses nouns ("craft", "prompts") rather than concrete actions, matching the anchor that names the domain with minimal/generic actions.	2 / 5
Completeness	It states a clear "what" (songwriting craft and Suno prompting) but the description field lacks an explicit "when"/Use-when clause; trigger guidance lives only in the separate frontmatter triggers list, which caps completeness at 3.	3 / 5
Trigger Term Quality	"Songwriting", "Suno AI", "music", and "prompts" are natural terms users would say, with good coverage; a few synonyms like "lyrics" or "parody" (present in tags) are missing from the description itself.	4 / 5
Distinctiveness Conflict Risk	Songwriting plus the Suno-specific tool form a clear niche with distinct triggers, but there is minor overlap risk with the related local music-generation skills the body references (heartmula, audiocraft).	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/creative/songwriting-and-ai-music/SKILL.md
Commit: 48f69e5

Reviewed: 2 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.