BD seedance-shot-design
Professional-grade virtual film director and prompt engineer for Seedance 2.0 (即梦). Transforms vague ideas into cinematic, production-ready video prompts with Hollywood-caliber shot design. Covers every workflow — text-to-video, image-to-video, multi-modal references, video extension, character swap, dialogue-driven short films, and music-synced edits. Ships with a cinematography dictionary (50+ safe camera-move phrases), a director style library (Villeneuve, Wes Anderson, Shinkai, Wuxia & more), a 3-layer lighting & quality-anchor system that kills the "plastic AI look," and a built-in structured validation checklist so every prompt passes before delivery. Supports bilingual output (Chinese/English) with smart >15 s auto-segmentation for long-form storytelling. Trigger words: Seedance, Shot Design, AI video, storyboard, video prompt, short film, cinematic prompt, 即梦, 视频提示词, 分镜, 视频脚本, AI视频, 短片脚本, 镜头设计, 运镜.
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Dangerous commands
cmd-pipe-to-shellreferences/seedance-specs.md:110Downloads and executes remote code from an unrecognised host (pipe to shell) (test fixture / example file)curl -fsSL https://jimeng.jianying.com/cli | bash
fixture
Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5752 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 49/100
- 0Result and completion. Does not say what the result is
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 70Execution cost. Instruction body is 5752 tokens
- 100Tools and files. No external tools needed
- 100Steps. 70 steps
- 100Consistency. Name and required fields are in place
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)
- +3Description length 919: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -223 emoji in the instructions: noise for the model
- -32 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 27 headings
- +3Step-by-step instructions: 70 items
- +4Has examples (32 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.