AD image-forge
画图技能路由中枢（统一入口）。三维路由体系（用途 × 风格 × 主体），双后端调度。 - Signature 风格：10 种有独立 YAML 的视觉方案（构成主义/克莱因/Risograph/故障艺术等） - Rendering 风格：15 种通用渲染技法 modifier（写真/动漫/3D/水彩/赛博朋克等），prompt 源自实战案例 - Logo 展示背景：12 种专业展示场景（来源 logo-generator，已内化） - 用途库：12 类场景 + 全实战 prompt 案例，含推荐风格 + 后端默认 - 后端调度：GPT Image 2（写实/产品/文字/4K）/ Gemini（动漫/艺术/多参考图） - 支持：文生图、风格库生图、参考图风格反推、参考图编辑、多参考图合成、logo 展示图 Use when: 用户想画图/生图/做海报/插画/风格迁移/图片编辑/logo展示图 — 这是唯一的图像生成入口。 【铁律】绝对禁止使用 image_generate 工具（configured: no，不可用）。所有画图请求必须走本 skill。 【注意】SVG logo 代码生成 → 请用专属 logo-generator skill。
As a process D 46/100 · 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Exfiltration
net-redirectable-api-keyscripts/gpt_image2.py:38Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
low Exfiltration
read-dotenvREADME.md:29Reads a .env filecp .env.example .env
Files scanned: 32. 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 46/100
- 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
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 6 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2321 tokens
- 100Running it twice. No mutating operations
- low 10 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 528: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (10 code blocks)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.