AD ppt-vision-replica
将PPT截图或信息图转换为可编辑的PPTX文件。此技能基于Images2Slides论文(arXiv:2602.07645)实现， 利用视觉-语言模型(VLM)进行区域理解，通过坐标映射算法将像素坐标转换为PPTX坐标。 支持复杂形状降级处理策略（custGeom/渐变/透明等无法直接还原的形状转为PNG嵌入）。 触发场景：用户上传PPT截图并要求复刻、用户要求分析PPT结构、用户希望将图片PPT转换为可编辑版本。
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
ReferencePowerPointInfrastructureResearchtype and topics are labelled automatically from the skill text
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "requires"
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, node) that frontmatter does not declare
- 100Steps. 51 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3867 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
- +1No license
- +2Single-language instructions
- +3Description length 209: enough signal without eating the budget
- +4Structure: 32 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (18 code blocks)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.
External checks
ClawHub: clean
This is a disclosed PPT screenshot-to-PPTX helper whose main risk is that slide images may be sent to a configured vision-model service.
LLM: benign (high) · VirusTotal: · 29 May 2026