seedance-audio

This skill should be used when the user asks for Seedance 2.0 audio, dialogue, lip-sync, music, sound effects, ambience, beat-sync, audio-reference mapping, desync troubleshooting, or sound-driven visual timing.

Quality

68%

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/seedance-audio/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 body is well-structured and actionable with concrete patterns and example fragments, but it carries some unnecessary framing prose, lacks verification checkpoints in its fix flows, and references bundle files that are not present to verify.

Suggestions

Trim or condense the Intent paragraph to remove motivational framing that does not change Claude's behavior.

Add a verification step to the Failure Fixes flow (e.g. "re-render a short test clip to confirm lip-sync is in sync before committing the full take") so the remediation has an explicit checkpoint.

Ensure the referenced `[ref:audio-guide]` and `[ref:audio-post-delivery]` files actually exist under ./references/, or inline the minimal needed guidance if no bundle is shipped.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and actionable, but the Intent paragraph ("Half of every emotion enters through the ears ... The soul here is giving every scene its sound before being asked") is motivational framing that could be trimmed, matching "mostly efficient but includes some unnecessary explanation".	2 / 3
Actionability	Provides a concrete copy-paste sound-layer format ("Dialogue: ... Sound: ... SFX: ... Music: ... Silence: ...") and a table of specific ready-to-use audio directions per need; for an instruction-only skill this is specific, example-backed guidance.	3 / 3
Workflow Clarity	The Failure Fixes section lists remediation steps ("shorten the line, lock the camera, remove head turns ...") but includes no validation checkpoint to confirm the desync is resolved, matching "sequence present but checkpoints missing or implicit".	2 / 3
Progressive Disclosure	References are clearly signaled one level deep ("Load `[ref:audio-guide]` for ...", "Load `[ref:audio-post-delivery]` when ..."), but the referenced bundle files are not present under ./references/, so the navigation cannot be verified against an actual bundle structure.	2 / 3
	Total	9 / 12 Passed

Description

72%

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 has strong, natural trigger coverage and a clear niche, but leans entirely on "when" phrasing without stating concrete actions, leaving the "what" implied. Tightening by adding one clause of explicit actions would lift completeness and specificity.

Suggestions

Add an explicit action clause, e.g. "Generates and syncs Seedance 2.0 audio: dialogue, lip-sync, music, ambience, and sound effects" before the "Use when" triggers so the "what" is stated, not implied.

Consider dropping the most technical trigger ("audio-reference mapping") or pairing it with a plainer term to keep all triggers user-natural.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete audio sub-domains ("dialogue, lip-sync, music, sound effects, ambience, beat-sync, audio-reference mapping, desync troubleshooting") but states no concrete action verbs describing what the skill does, matching the "names domain and some actions, but not comprehensive" anchor.	2 / 3
Completeness	The "when" is explicit ("should be used when the user asks for ...") but the "what" is only implied from the domain name rather than stated as actions, so it does not clearly answer both what AND when.	2 / 3
Trigger Term Quality	Natural terms a user would say are well covered ("dialogue, lip-sync, music, sound effects, ambience, beat-sync ... desync troubleshooting"), beyond the "some relevant keywords" bar; only a couple of terms like "audio-reference mapping" are slightly technical.	3 / 3
Distinctiveness Conflict Risk	"Seedance 2.0 audio" with triggers like lip-sync, beat-sync, and desync troubleshooting is a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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	14 / 16 Passed

Repository: Emily2040/seedance-2.0
Path: skills/seedance-audio/SKILL.md
Commit: 6c51262

Reviewed: 1 day 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.