AB seedream
Generate and edit AI images using ByteDance's Seedream — featuring text-to-image, image editing, and batch sequential generation with up to 4K resolution, PNG output, typography/poster design excellence, and built-in prompt optimization. Supports Seedream v5.0 Lite (latest), v4.5, and v4 across 3 generations and 12 model variants. Available via Atlas Cloud API at up to 10% off standard pricing. Use this skill whenever the user wants to generate images, edit photos, create posters, design typography, batch generate related images, create AI art, or mentions Seedream, ByteDance image, Jimeng, or Doubao image generation. Also trigger when users ask to create product photos, marketing visuals, brand assets, social media graphics, illustrations, concept art, batch image series, or any visual content using AI.
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
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 · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "env_vars"
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) 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. 39 steps, 2 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2863 tokens
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 815: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 28 headings
- +3Step-by-step instructions: 39 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.