CtrlK
BlogDocsLog inGet started
Tessl Logo

seedance-antislop

This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.

64

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/seedance-antislop/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is concise and highly actionable with concrete replacement patterns and a clear slop taxonomy, scoring well on efficiency and actionability. It loses points on workflow clarity for lacking an explicit verification checkpoint and on progressive disclosure because the referenced bundle files are not present to verify.

Suggestions

Add an explicit verification step to the Rewrite Pass (e.g., confirm the tightened prompt preserves all reference tags and stays within the character budget) to introduce a feedback loop.

Either bundle the referenced files (references/vocab/*.md, anti-slop-lexicon) under ./references/ so paths resolve, or mark which references are external so progressive disclosure can be scored against real structure.

DimensionReasoningScore

Conciseness

The body is lean, assumes Claude's competence (no explanation of what prompting or video models are), and every section earns its place. It matches the lean-and-efficient anchor rather than the padded level-2 example.

3 / 3

Actionability

It gives concrete, copy-paste-ready replacement patterns ('locked close-up, warm practical key, cool rim light'), a six-class taxonomy each with a specific repair, and a concrete rewrite procedure. As an instruction-only skill this fully actionable guidance matches the highest anchor.

3 / 3

Workflow Clarity

The Rewrite Pass gives a sequenced First/Second/Third/Fourth procedure, but there is no explicit validation or verification checkpoint confirming the rewrite preserves meaning, reference tags, or character budget. Per the rubric, missing feedback loops caps workflow clarity at 2; it is above the unclear level because the sequence is explicit.

2 / 3

Progressive Disclosure

References are clearly signaled and one-level-deep ('[ref:anti-slop-lexicon]', 'references/vocab/*.md'), and sections are well organized, but no bundle directories or files exist under ./references/, ./scripts/, or ./assets/ to verify the referenced paths resolve. It is not a 3 because the referenced materials cannot be confirmed present; not a 1 because structure and signaling are present.

2 / 3

Total

10

/

12

Passed

Description

75%

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 clearly scopes the skill to Seedance 2.0 prompt tightening with an explicit use-when trigger and good distinctiveness. It is held back by only moderate trigger-term coverage and by not enumerating concrete skill actions.

Suggestions

Add a short list of concrete actions the skill performs (e.g., 'classify, rewrite, and return a tightened prompt') to lift specificity.

Broaden trigger terms with common user phrasings like 'make this prompt better', 'fix vague wording', or 'sharpen my Seedance prompt' for more natural recall.

DimensionReasoningScore

Specificity

Names the domain (Seedance 2.0 prompts) and the kinds of filler it targets, but does not list multiple distinct concrete actions the skill performs, matching the anchor that names domain and some actions but is not comprehensive. It is not a 3 because no enumerated set of specific actions is given.

2 / 3

Completeness

It states what the skill does (remove filler, sharpen production-specific wording) and explicitly when to use it via 'This skill should be used when a Seedance 2.0 prompt contains...', satisfying both what and when with explicit triggers. This matches the highest anchor.

3 / 3

Trigger Term Quality

Phrases like 'generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs' give some natural trigger words a user might say, but coverage of common variations is incomplete and several terms are prompt-engineering jargon rather than user-spoken keywords. Not a 3 because it lacks broad natural-term coverage; not a 1 because it does include recognizable natural phrases.

2 / 3

Distinctiveness Conflict Risk

The narrow framing to 'Seedance 2.0 prompt' production wording carves a clear niche unlikely to trigger for unrelated skills. This matches the distinct-trigger anchor; it is well above the generic/somewhat-specific levels.

3 / 3

Total

10

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

referenced_paths_exist

Referenced path issues: 3 missing, 2 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository
Emily2040/seedance-2.0
Reviewed

Table of Contents

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.