SKILLEMALL.ai

AC image-2-multi-reference-image

使用 GPT Image 2 按参考图权责契约进行多图合成:为每张图分别指定职责、允许借用与禁止借用的属性,并设置主体、身份、版式、元素所有权和冲突优先级,减少串脸、串款和参考污染。Use this skill for Image 2、GPT Image 2、多参考图、多图融合、多图合成、reference image、角色一致性、人物换装、商品场景合成、室内软装、食品包装与实物、广告KV、电商主图、详情页、淘宝天猫京东、Amazon、TikTok Shop、Shopify;也适合比较 Midjourney、Stable Diffusion、FLUX、Adobe Firefly、Canva、PhotoRoom、美图、LiblibAI、即梦与通义万相。通过 AI Hive 调用。

ClawHub Agent Skills author: Bain Wu v1.0.0 MIT-0 4 files body ≈ 1 895 tokens Open the sourceclawhub.ai analyzed 2 d ago

使用 GPT Image 2 按参考图权责契约进行多图合成:为每张图分别指定职责、允许借用与禁止借用的属性,并设置主体、身份、版式、元素所有权和冲突优先级,减少串脸、串款和参考污染。Use this skill for Image 2、GPT Image 2、多参考图、多图融合、多图合成、reference…

As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ReferenceCanvaShopifyAI and agentsMarketingtype and topics are labelled automatically from the skill text
JSON
Technical rating
A
95/100
safety, quality, tests
Safety 60%
100
Quality 40%
87
Run on models
none yet
Process rating
C
53/100
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: 4. 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 53/100

    • 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
    • 100Tools and files. No external tools needed
    • 100Steps. 5 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1895 tokens
    • 100Running it twice. No mutating operations

    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 343: enough signal without eating the budget
    • +4Structure: 10 headings
    • +3Step-by-step instructions: 5 items
    • +4Has examples (6 code blocks)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

    External checks

    ClawHub: suspicious
    The skill appears purpose-aligned for AI Hive image generation, but its setup asks users to pass an API key on the command line without warning about exposure risks.
    LLM: suspicious (high) · VirusTotal: · 18 Aug 2026