CF linkpix
调用青虎 AI 媒体能力：AI 生图（套图/电商详情图/自定义生图家族实时清单：智慧模型、图片 5.0 Lite、专图模型、图片 5.0 Pro 等 + 提示词润色）、批量生图玩法（批量生图/批量改图/批量替换/主图复刻/姿势套图/批量译图）、AI 生视频（模型清单实时读取线上目录，含 Seedance2.5、Seedance2.0、阿里wanx3.0、MiniMax H3、全能电商2.0、Happy Horse、可灵3.0 Omni、品牌质感大片等多模型多时长 5–30 秒，支持多参考视频与参考音频）、一键成片、角色替换/模特换脸、视频翻译、去水印/去字幕/画质提升、复刻爆款视频出脚本、爆款视频转图文、分镜脚本与分镜图、广告素材模板批量出片（视频/图片）、POD 印花素材（印花提取/贴合/裂变 + 产品图库）、青虎工作台「AI 应用」的 AI 工作流（电影质感 TVC 广告大片、爆款视频模仿与仿拍、模特换装高一致性还原、超清修复与去 AI 感、图像去水印、短视频与达人数据引擎），均含任务状态查询。当用户要求生成/制作商品图、主图、详情图、营销图、广告视频、带货视频、口播视频，或要求批量出图、批量改图、把产品换进参考图、复刻别人的主图风格、生成服装模特多姿势套图、翻译图片上的文字，或要求翻译视频、去水印、去字幕、提升画质、换人物/换脸、复刻某条爆款视频、把视频转成图文笔记、写分镜脚本，或要求做电影质感 TVC 广告大片/品牌广告片、仿拍某条爆款视频、给模特换装、把图片超清修复/去 AI 感、跑短视频或达人数据引擎分析时必须触发。支持关键词：LinkPix、linkpix、qhkit、青虎、爆款素材、电商素材、量产素材、生图、AI绘图、商品图、主图、套图、详情图、批量生图、批量改图、批量替换、主图复刻、套图复刻、姿势套图、服装套图、批量译图、图片翻译、译图、白底图、提示词润色、广告素材、投放素材、POD素材、POD、印花、印花提取、印花贴合、印花裂变、生视频、AI视频、带货视频、广告片、一键成片、成片、换脸、换模特、数字人替换、视频翻译、翻译配音、去水印、去字幕、画质提升、超分、复刻爆款、对标视频、视频转图文、图文笔记、分镜、脚本、storyboard、AI应用、AI工作流、工作流、workflow、TVC、TVC广告、广告大片、品牌广告片、电影质感、爆款视频模仿、仿拍、模特换装、换装、超清修复、去AI感、图像去水印、数据引擎、短视频数据、达人数据。
调用青虎 AI 媒体能力：AI 生图（套图/电商详情图/自定义生图家族实时清单：智慧模型、图片 5.0 Lite、专图模型、图片 5.0 Pro 等 + 提示词润色）、批量生图玩法（批量生图/批量改图/批量替换/主图复刻/姿势套图/批量译图）、AI 生视频（模型清单实时读取线上目录，含…
As a process F 31/100 · Will not run — References files that are not bundled: url
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1042 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5607 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: url - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 31/100
- 0Tools and files. 1 referenced file(s) missing: url
- 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. 4 mutating operations with no state check
- 70Execution cost. Instruction body is 5607 tokens
- 100Steps. 60 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 1042: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 20 headings
- +3Step-by-step instructions: 60 items
- +4Has examples (17 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 27.