CD seedance-fight-scenes
Generate intense fight scene and action sequence video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants fight scenes, combat, martial arts, battles, action choreography, sword fights, hand-to-hand combat, chase scenes, superhero action, or any high-energy action video. Triggers on: fight, combat, battle, martial arts, action scene, choreography, duel, sword fight, kung fu, chase, brawl, punch, kick, weapon combat, superhero fight, or any action/fight request. Use even for "make an intense action video" or "epic battle.
Generate intense fight scene and action sequence video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants fight scenes, combat, martial arts…
As a process D 43/100 · 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securitySKILL.md:159Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Footwork: Bouncing, lateral movement, close-range engagement
-
low Risky intent
intent-offensive-securitySKILL.md:292Offensive-security / dual-use content (legitimate for authorised testing; review intended use)3. **Lateral Tracking**: Pan side-to-side following lateral movement—maintain subject center
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 intense fight scene and action sequence video prompts for… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
body-longSKILL.md body ≈ 11026 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 43/100
- 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
- 30Running it twice. 14 mutating operations with no state check
- 40Consistency. Frontmatter name (seedance-fight-scenes) differs from the folder (05-fight-scenes)
- 40Execution cost. Instruction body is 11026 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Steps. 258 steps, 7 vague phrases
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- low 16 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 543: enough signal without eating the budget
- +4Structure: 74 headings
- +3Step-by-step instructions: 258 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.