CtrlK
BlogDocsLog inGet started
Tessl Logo

seedance-troubleshoot

This skill should be used when a Seedance 2.0 output is blurry, jittery, off-prompt, morphing, blocked, visually generic, unstable, desynced, inconsistent, or otherwise fails and needs root-cause diagnosis.

63

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

71%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, lean, and actionable, with a dense diagnostic table, a copy-paste retry template, and a clear repair workflow with an escalation feedback loop. Its main weakness is progressive disclosure: it references 11 supporting files that are absent from the bundle, leaving all of those links broken.

Suggestions

Add the missing references/ bundle files (directors-read.md, model-mechanics.md, retake-protocol.md, failure-atlas.md, continuation-handoff.md, continuity-qc.md, etc.) so the 11 in-body reference links resolve instead of 404ing.

Add one fully-worked end-to-end example applying the Conservative Retry Pattern to a real failing prompt (failing prompt → diagnosed root cause → repaired prompt) to lift actionability.

Trim the motivational '## Intent' paragraph to a single operational line, or fold its 'name the mechanism, never the user' guidance into the Repair Process to improve conciseness.

DimensionReasoningScore

Conciseness

Mostly lean operational prose with a dense diagnostic table and a copy-paste retry template, but the '## Intent' section ('A failed generation feels personal...') is motivational padding that could be trimmed.

4 / 5

Actionability

Provides a concrete Symptom→Cause→Repair table, a fill-in Conservative Retry Pattern template, and a sequenced Repair Process; however, no fully-worked end-to-end example is shown and deeper-diagnosis content is delegated to reference files.

4 / 5

Workflow Clarity

The Repair Process gives a clear sequenced workflow and Escalation Rules provide an error-recovery feedback loop ('If the same error repeats...'), but explicit validation checkpoints before producing output are implicit rather than stated.

4 / 5

Progressive Disclosure

Well-structured with condition-based one-level-deep references (e.g., 'When the diagnostic tree has no row... load model-mechanics.md'), but none of the 11 referenced files exist in the bundle — every reference link is broken, so navigation is not actually possible.

3 / 5

Total

15

/

20

Passed

Description

82%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.

A strong, specific description that pairs a clear 'what' (root-cause diagnosis) with an explicit 'when' clause and rich natural trigger terms tied to a distinct product niche. It is slightly thin on enumerating the skill's concrete actions and could add a few more common synonyms.

DimensionReasoningScore

Specificity

Names the domain ('Seedance 2.0 output') and one concrete action ('needs root-cause diagnosis'), but the long list enumerates failure symptoms rather than multiple distinct skill actions, so capability coverage is not comprehensive.

3 / 5

Completeness

Explicitly answers both what ('needs root-cause diagnosis') and when ('This skill should be used when a Seedance 2.0 output is blurry, jittery, ...') with concrete trigger phrases, satisfying the 'Use when...' expectation.

5 / 5

Trigger Term Quality

Lists many natural user terms ('blurry, jittery, off-prompt, morphing, blocked, visually generic, unstable, desynced, inconsistent') plus the product name, but omits common synonyms a user might say such as 'glitchy', 'flickering', or 'artifacts'.

4 / 5

Distinctiveness Conflict Risk

Tied to a specific product ('Seedance 2.0') and video-generation-specific failure modes (morphing, desynced, lip-sync), giving a clear niche with minimal overlap risk against other skills.

5 / 5

Total

17

/

20

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

relative_links

Relative link issues: 11 suspicious

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.