SKILLEMALL.ai

AC seedream5.0

使用 Seedream5.0 接口进行文生图与参考图生成。当用户提到“生成图片”“出图”“海报图”“封面图”“根据参考图生成”或要求指定分辨率与水印时,优先使用本 skill。调用接口 fzGenerateImg5,参数含 prompt(必填)、size(可选)、watermark(可选)、image(可选)。需 x-api-key(kexiangai.com)。Do NOT use for OCR, video generation, or non-generative image editing.

ClawHub Agent Skills author: cmhan v1.0.0 MIT-0 5 files · 2 scripts body ≈ 612 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

IntegrationAI and agentsInfrastructureWriting and documentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
96/100
safety, quality, tests
Safety 60%
100
Quality 40%
90
Run on models
none yet
Process rating
C
52/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • 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: 5. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)

    Process rating: all ten parameters 52/100

    • 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
    • 40Consistency. Frontmatter name (seedream5.0) differs from the folder (seedream5-official)
    • 50When it triggers. No condition that starts the skill
    • 100Tools and files. No external tools needed
    • 100Steps. 53 steps
    • 100Execution cost. Instruction body is 612 tokens
    • 100Running it twice. No mutating operations
    • low 11 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
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 253: enough signal without eating the budget
    • +4Structure: 18 headings
    • +3Step-by-step instructions: 53 items
    • +4Has examples (2 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)
    • +3All 2 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.

    External checks

    ClawHub: clean
    This is a coherent Seedream image-generation skill that clearly sends prompts to a fixed external API and optionally stores its API key locally for reuse.
    LLM: benign (high) · VirusTotal: · 29 May 2026