seedance-prompt-short

This skill should be used when the user asks for a compact Seedance 2.0 prompt, short Chinese prompt, prompt compression, 30-100 word output, or removal of unnecessary prompt language.

Quality

65%

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-prompt-short/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 highly actionable with concrete templates and a clear preservation priority, and it is lean and well-organized, but a dangling reference to a missing bundle file and the absence of an explicit post-compression verification checkpoint hold it back.

Suggestions

Either create references/multilingual-community-examples with the bilingual guidance or remove the '[ref:multilingual-community-examples]' call and inline the essential multilingual rule, so the signaled reference resolves.

Add an explicit verification step after compression, e.g. 'Before returning, confirm continuity locks, exact reference tags, and completed-beat exclusions are still present; if any are missing, restore them.'

Trim the 'Intent' section to a single operational line so every token in the body earns its place.

Dimension	Reasoning	Score
Conciseness	The body is lean, well-structured, and assumes Claude's competence (no explanations of Seedance or T2V/I2V), but the 'Intent' section is non-operational prose ('soul of their shot', 'If the user would mourn a deleted word, it was never filler') that could be tightened.	2 / 3
Actionability	For an instruction-only skill it provides copy-paste-ready fill-in templates (T2V/I2V/V2V/Chinese with bracketed slots), an explicit 1-8 preservation priority, concrete deletion rules, and a 30-100 word output budget — fully actionable guidance.	3 / 3
Workflow Clarity	A clear priority sequence and checklist exist, but there is no explicit validation/verification checkpoint to confirm that continuity locks, reference tags, and completed-beat exclusions survived compression, and removal of those words is a destructive edit that warrants such a check.	2 / 3
Progressive Disclosure	The body is well-organized into clear sections and is under 50 lines, but it signals a reference ('load [ref:multilingual-community-examples]') to a bundle file that does not exist in references/, leaving bilingual guidance partially delivered and breaking navigation.	2 / 3
	Total	9 / 12 Passed

Description

65%

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 leads with a clear, explicit trigger clause and uses natural, domain-specific terms, but it conflates the skill's action with its triggers, leaving the 'what' implied and introducing some overlap risk through generic compression triggers.

Suggestions

Add a concrete action statement separate from the triggers, e.g. 'Compresses Seedance 2.0 video prompts to 30-100 words while preserving production signal.', so the 'what' is stated explicitly.

Qualify the generic triggers with the Seedance scope (e.g. 'Seedance prompt compression' rather than bare 'prompt compression') to reduce overlap with non-Seedance compression skills.

Lead with the action before the trigger list so the description answers what the skill does before when to use it.

Dimension	Reasoning	Score
Specificity	Names the domain ('compact Seedance 2.0 prompt', 'prompt compression', 'removal of unnecessary prompt language') but frames these as things the user asks for rather than listing multiple concrete actions the skill performs, so it is not comprehensive enough for a 3.	2 / 3
Completeness	It has an explicit when clause ('This skill should be used when the user asks for...') but the what — the skill compressing the prompt — is only implied through the triggers rather than stated as a distinct action, so it does not clearly answer both.	2 / 3
Trigger Term Quality	Phrases like 'prompt compression', 'short Chinese prompt', 'compact Seedance 2.0 prompt', and '30-100 word output' are natural terms a user would actually say, giving good coverage of likely triggers.	3 / 3
Distinctiveness Conflict Risk	The 'Seedance 2.0' framing is a clear niche, but generic triggers like 'prompt compression', '30-100 word output', and 'removal of unnecessary prompt language' could cause it to fire for non-Seedance compression, overlapping with similar prompt-compression skills.	2 / 3
	Total	9 / 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-prompt-short/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.