AC seedance-2-0-video
Generate AI videos using ByteDance Seedance 2.0. Use when the user wants to: (1) generate videos from text prompts, (2) generate videos from images (first frame, first+last frame), (3) generate long videos (>15s) by chaining multiple segments with last-frame continuity, or (4) query/manage video generation tasks. Supports Seedance 2.0 model with audio support and draft mode.
As a process C 56/100 · Has gaps — weak spots: result and completion, consistency, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Dangerous commands
cmd-eval-dynamicseedance.py:255Dynamic code execution from decoded/untrusted inputos.system(f'open "{filepath}"')
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 56/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (seedance-2-0-video) differs from the folder (seedance-2-0-video-generation)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4057 tokens
- 100Steps. 24 steps
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 377: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.