seedance-filter

This skill should be used when a Seedance 2.0 prompt is blocked, rejected, silently degraded, or likely to trigger a content filter; or when the user asks for a safer rewrite without losing the creative intent.

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/seedance-filter/SKILL.md

Quality

Content

65%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 well-organized with a concrete repair method and substitution table, but it is undermined by three referenced bundle files that do not exist and by the absence of a validation checkpoint for its safety-sensitive output.

Suggestions

Add or restore the referenced files (directors-read.md, filter-vocab.md, multilingual-community-examples.md) under references/, or remove the links and inline the essential content, so the prerequisite 'load' step is actually executable.

Add a validation checkpoint after the rewrite step that confirms the safer wording no longer contains the flagged risk element and still preserves composition, mood, and authorized references.

Merge the Boundary and Boundary Rule sections and tighten the Intent paragraph to remove redundancy and editorial padding.

Dimension	Reasoning	Score
Conciseness	Mostly dense and useful (5-step method, substitution table, output contract), but the Boundary and Boundary Rule sections repeat near-identical refusal guidance and the Intent paragraph adds editorial padding that could be trimmed.	4 / 5
Actionability	Concrete 5-step method with enumerated risk categories, an intent-to-safer-direction substitution table, and an explicit output contract; held back from 5 by a missing prerequisite file (Director's Read) and no worked before/after example.	4 / 5
Workflow Clarity	A clear sequence exists (load record -> classify -> 5-step repair -> output contract), but there are no validation checkpoints verifying the rewrite stays safe, and the required first step references a file that does not exist.	3 / 5
Progressive Disclosure	The body is well-sectioned with one-level-deep, conditionally-loaded references signposted in markdown, but all three referenced files (directors-read.md, filter-vocab.md, multilingual-community-examples.md) are absent from the bundle, so navigation is broken.	3 / 5
	Total	14 / 20 Passed

Description

73%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 has a clear, distinctive niche and strong natural trigger terms with an explicit 'use when' clause. Its main weakness is that the 'what it does' is conveyed implicitly through triggers rather than stated as concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the Seedance 2.0 domain and ~2 actions (handling blocked/rejected/degraded prompts, safer rewrites), but conveys capabilities through trigger clauses rather than enumerating concrete actions, leaving coverage less than comprehensive.	3 / 5
Completeness	The 'when' is explicit and strong ('This skill should be used when...'), and the 'what' (safer rewrite of blocked prompts) is present but largely implied via triggers rather than stated as a clear capability.	4 / 5
Trigger Term Quality	Strong cluster of natural user phrasings ('blocked, rejected, silently degraded, content filter, safer rewrite') but misses common synonyms like 'flagged,' 'moderation,' or 'censored' that would round out coverage.	4 / 5
Distinctiveness Conflict Risk	Scoped to a named product (Seedance 2.0) with a specific filter/rewrite niche, giving it distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 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
relative_links	Relative link issues: 3 suspicious	Warning

	Total	13 / 16 Passed

Repository: Emily2040/seedance-2.0
Path: skills/seedance-filter/SKILL.md
Commit: 44b5149

Reviewed: 23 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.