music-generation

Use this skill when the user requests to generate, create, compose, or produce music or songs — background music, theme songs, jingles, or instrumental tracks. Generates a song from a style/mood prompt and optional lyrics via the MiniMax music API.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

86%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.

A tight, highly actionable skill: the spec format and invocation are fully concrete and match the bundled script. The only gaps are minor duplication between the Fields and Behavior sections and the absence of any failure-handling guidance.

Suggestions

Merge the 'Fields' and 'Behavior' bullets into one list (e.g., 'lyrics (optional): sung as provided; use [Verse]/[Chorus] tags') to remove the duplicated explanation of the lyrics/is_instrumental interaction.

Add one line of error guidance after Step 3, e.g., 'If the script reports MINIMAX_API_KEY is not set or a MiniMax error, surface the message to the user before retrying.'

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept tutorials ('Do NOT read the python file, just call it' is a good token-saving directive), but the 'Behavior' bullets partially restate the 'Fields' documentation and the Overview repeats the frontmatter description, so a little trimming is possible.	4 / 5
Actionability	Fully executable: a copy-paste-ready bash command with absolute paths, a complete JSON spec example, parameter documentation, and env-var defaults that exactly match the bundled scripts/generate.py.	5 / 5
Workflow Clarity	The Understand -> Create spec -> Execute -> Output handling sequence is clear and unambiguous for this non-destructive single-generation task, but there is no guidance on what to do when generation fails (e.g., the script reporting 'MINIMAX_API_KEY is not set' or an API error).	4 / 5
Progressive Disclosure	Scored against the actual bundle: a single script (scripts/generate.py) is referenced by a real, correct path and explicitly kept out of context, and the ~73-line body is well-sectioned (Overview, Workflow, Environment, Output Handling, Notes) with no content that belongs in a separate file.	5 / 5
	Total	18 / 20 Passed

Description

87%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.

A well-formed description: explicit what-and-when with concrete trigger phrases in third person, and a distinct niche. Its only weakness is slightly limited synonym coverage (no 'soundtrack'/'melody' style variations) and a single-capability framing.

Dimension	Reasoning	Score
Specificity	'Generates a song from a style/mood prompt and optional lyrics via the MiniMax music API' names the concrete action, its inputs, and output variants (background music, theme songs, jingles, instrumental tracks), with only minor gaps (e.g., output format is not mentioned). It is below 5 because it describes essentially one capability rather than several distinct actions.	4 / 5
Completeness	Both parts are explicit: the 'what' ('Generates a song from a style/mood prompt and optional lyrics via the MiniMax music API') and a concrete 'when' ('Use this skill when the user requests to generate, create, compose, or produce music or songs...') with multiple trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Strong natural-phrase coverage — 'generate, create, compose, or produce music or songs' plus 'background music, theme songs, jingles, or instrumental tracks' — but common variations like 'soundtrack', 'melody', 'make a beat', or 'BGM' are missing, so it falls just short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	Music/song generation is a clear niche with distinct triggers (jingles, theme songs, instrumental tracks) that no generic document, code, or media skill would claim; conflict risk is minimal.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: bytedance/deer-flow
Path: skills/public/music-generation/SKILL.md
Commit: ee44d1e

Reviewed: 18 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.