songwriting-and-ai-music

Songwriting craft and Suno AI music prompts.

Quality

63%

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

77%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 unusually concrete craft skill: the Suno prompting and phonetics sections are exemplary, copy-paste-ready guidance with a well-sequenced workflow that includes real validation checkpoints. Its weaknesses are re-teaching songwriting fundamentals Claude already knows and inlining reference-grade catalogs instead of splitting them out.

Suggestions

Trim or compress sections 2-4 (rhyme taxonomy, meter basics, show-don't-tell) to the non-obvious judgment calls only — e.g. the vowel-matching-on-held-notes and monosyllabic-swap tactics — and cut the general craft definitions.

Move the metatag catalogs and phonetic respelling tables into a references/ file (e.g. references/suno-metatags.md), keeping a short 'top tags' summary in SKILL.md with a clearly signaled link.

Dimension	Reasoning	Score
Conciseness	The Suno-specific sections (6, 7, 10) are dense and earn their tokens, but sections 2-4 re-explain craft concepts Claude already knows (rhyme-type taxonomy 'Perfect: lean/mean', 'whisper before a scream hits harder than just screaming', show-don't-tell), and version-sensitive info ('V4.5+ supports up to 1,000 chars') sits inline without a versioned framing. Matches anchor 3 ('mostly efficient but includes some unnecessary explanation or could be tightened') rather than 2, since the treatment is compressed lists rather than padded prose.	3 / 5
Actionability	Guidance is concrete and directly usable: the style formula 'Genre + Mood + Era + Instruments + Vocal Style + Production + Dynamics', a full GOOD style-prompt example, exhaustive metatag lists, specific limits ('~3,000 chars', 'Keep to 5-8 tags per section max'), and copy-paste-ready phonetic fixes ('Nous' -> 'Noose', '24/7' -> 'twenty four seven'). Matches anchor 5 — specific examples cover the common cases; the absence of code is not penalized for an instruction-only skill.	5 / 5
Workflow Clarity	Section 8 gives a clear 10-step sequence with explicit validation checkpoints ('Read/sing aloud — catch stumbles, fix meter'; 'Test proper nouns... in a short 30-second clip first') and feedback loops ('Generate 3-5 variations... Pick the best, use Extend/Continue'; '~3-5 generations per 1 good result'). Matches anchor 5; not 4 because recovery guidance on failure is present, not just implied.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent), so all ~290 lines live in SKILL.md. Section headers are good, but reference material — the ~30-line metatag catalog and the phonetic tricks — is inlined where a separate reference file would serve better, and the skill is far over the 50-line simple-skill exception. Matches anchor 3 ('some structure but... content that should be separate is inline') rather than 4, since there are no external references at all to be clearly signaled.	3 / 5
	Total	16 / 20 Passed

Description

48%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 correctly identifies its niche but is topic-labeling rather than action-stating, with no 'use when' trigger guidance. The frontmatter's separate triggers list is not visible in the description itself, so the description reads as incomplete.

Suggestions

Add concrete actions in third person, e.g. 'Guides song structure, rhyme and meter, lyric writing, parody adaptation, and Suno AI prompt construction (style fields, metatags, phonetic respelling).'

Append an explicit trigger clause: 'Use when writing song lyrics, creating a parody or adaptation of an existing song, or crafting Suno / AI music generation prompts.'

Include the natural synonyms users would say ('lyrics', 'make a song', 'write a song', 'parody', 'AI music') directly in the description rather than only in the separate triggers list.

Dimension	Reasoning	Score
Specificity	The description ("Songwriting craft and Suno AI music prompts") names its two domains but contains no concrete actions or verbs — it labels topics rather than stating what the skill does. It falls at anchor 2 ('names the domain but actions are minimal or generic'), not 3, which requires at least 1-2 concrete stated actions.	2 / 5
Completeness	A terse 'what' is conveyed (songwriting craft, Suno prompts), but there is no 'Use when...' clause or equivalent explicit trigger guidance in the description, which caps completeness at 3 per the judging guidelines. Not 4 because 'when' is entirely absent rather than merely imprecise.	3 / 5
Trigger Term Quality	Relevant keywords ('songwriting', 'Suno', 'music prompts') are present, but common natural phrasings users would actually say ('write lyrics', 'make a song', 'parody') are absent from the description field. Matches anchor 3 ('some relevant keywords but missing common variations or synonyms') rather than 4, since natural-term coverage is thin despite a separate triggers list in the frontmatter.	3 / 5
Distinctiveness Conflict Risk	'Suno AI music prompts' carves out a clear niche with minimal conflict risk, while 'Songwriting craft' has some overlap with general creative-writing skills. Matches anchor 4 ('mostly distinct; minor overlap risk with closely related skills'), not 5, because half the description is the broader, less distinctive term.	4 / 5
	Total	12 / 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: 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.