CD seedance-anime-action
Generate anime-style video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants anime, Japanese animation style, shonen action, seinen drama, magical girl, mecha, isekai, slice-of-life anime, or any Japanese animation aesthetic. Triggers on: anime, Japanese animation, shonen, seinen, manga style video, anime fight, anime opening, anime ending, sakura, chibi, kawaii, mecha, isekai, or any anime-style request. Use even for "make it look like an anime" or "Japanese cartoon style.
Generate anime-style video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants anime, Japanese animation style, shonen action, seinen drama…
As a process D 45/100 · Unfinished process — weak spots: inputs and preconditions, failures and branches, consistency
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Generate anime-style video prompts for Seedance 2.0 on Higgsfield.… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
body-longSKILL.md body ≈ 17431 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 45/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 10Execution cost. Instruction body is 17431 tokens: crowds the task out of the window
- 30Running it twice. 24 mutating operations with no state check
- 40Consistency. Frontmatter name (seedance-anime-action) differs from the folder (08-anime-action)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 249 steps, 3 vague phrases
- low 20 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 496: enough signal without eating the budget
- +4Structure: 103 headings
- +3Step-by-step instructions: 249 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.