audiocraft-audio-generation

AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.

Quality

61%

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/audiocraft-audio-generation/SKILL.md

Quality

Content

68%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 highly actionable with comprehensive executable examples and good reference structure pointing to real bundle files. Its main weaknesses are duplicated quick-start code, a batch workflow without validation checkpoints, and inlined content that could be offloaded to reference files.

Suggestions

Add a validation/verification step to the batch sound-generation workflow, e.g. assert each output file exists and is non-empty before recording success, to lift workflow clarity above 3.

Remove the duplicated basic MusicGen text-to-music example by keeping it in one place (Quick start or MusicGen usage) and cross-referencing from the other.

Move secondary material (MusicGen-Style, EnCodec usage, performance optimization, common issues) into dedicated reference files and link to them from the body to improve progressive disclosure and conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and code-dense, but the basic MusicGen text-to-music example is duplicated (Quick start and MusicGen usage sections) and the 'When to use'/'Use alternatives instead' bullet lists add length without unique instruction; it is above 2 because the bulk is actionable rather than padded prose.	3 / 5
Actionability	Provides fully executable, copy-paste-ready code across MusicGen (text, melody, stereo, continuation), MusicGen-Style, AudioGen, EnCodec, and reusable workflow classes with concrete model names and sample rates; matches the anchor for comprehensive coverage of common cases.	5 / 5
Workflow Clarity	Workflows are presented as runnable code with a clear sequence, but the batch sound-generation workflow (Workflow 2) performs repeated generation and file writes with no validation or verification that outputs succeeded; per the guidelines a batch operation lacking validation caps this at 3.	3 / 5
Progressive Disclosure	Clear section headers plus well-signaled, one-level-deep markdown links to real files (references/advanced-usage.md and references/troubleshooting.md, both present); not a 5 because a large amount of usage content (MusicGen-Style, EnCodec, performance, common issues) is inlined rather than split into reference files.	4 / 5
	Total	15 / 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 is concise and names distinctive, concrete capabilities, but it lacks any explicit 'when to use' trigger guidance and leans on technical model names rather than natural user phrases. Adding a Use-when clause with everyday trigger terms would lift completeness and trigger-term quality.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when generating music, sound effects, or audio from text descriptions, or when the user mentions MusicGen, AudioGen, or AudioCraft.'

Add natural trigger phrases users actually say, such as 'generate music', 'create sound effects', and 'audio generation', alongside the model names.

Optionally mention EnCodec or melody/stereo conditioning to broaden the concrete-action coverage toward a higher specificity score.

Dimension	Reasoning	Score
Specificity	Names the AudioCraft domain plus two concrete actions ('MusicGen text-to-music', 'AudioGen text-to-sound'), matching the anchor for 1-2 concrete actions without comprehensive coverage; it is not a 4 because no additional actions (e.g., EnCodec, melody conditioning) are listed.	3 / 5
Completeness	The description gives a clear 'what' (text-to-music, text-to-sound) but has no 'Use when...' clause or equivalent trigger guidance, which per the guidelines caps completeness at 3; it is above 2 only because the 'what' is explicit.	3 / 5
Trigger Term Quality	Includes relevant model-name keywords a user might say ('MusicGen', 'AudioGen', 'text-to-music', 'text-to-sound') but omits common natural variations like 'generate music', 'sound effects', or 'audio generation'; falls short of 4 due to those missing everyday phrases.	3 / 5
Distinctiveness Conflict Risk	The specific model names (MusicGen, AudioGen, AudioCraft) carve a clear niche with minor overlap risk against related music skills; not a 5 because the metadata lists related music/songwriting skills that share surface overlap.	4 / 5
	Total	13 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (570 lines); consider splitting into references/ and linking	Warning
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	12 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/creative/audiocraft-audio-generation/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.