AC custom-ai-pptx-generator
Custom AI PPTX Generator — Design-driven, editable PowerPoint creation from your content. 可定制化AI 演示文稿（PPT）生成器 · 千题千境 (QianTi QianJing) AI-PPT workflow. This skill should be used when the user asks to create a PPT / presentation / training deck / project briefing / policy explainer from requirement notes, emails, tables or dictated content, and wants a PowerPoint-native editable deliverable (real native shapes and text boxes, not image-slab slides). Pipeline: content analysis → Design Intent Brief → structure confirmation → ASCII storyboard → visual prototype approval → native python-pptx rebuild → COM visual QA. 内容决定设计：先解析内容与设计意图，再经三轮用户确认（结构 / ASCII 草稿 / 样图），最终交付原生可编辑 PPTX 与逐页渲染图。
Custom AI PPTX Generator — Design-driven, editable PowerPoint creation from your content.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Dangerous commands
cmd-execpolicy-bypassreferences/千题千境_项目经验总结.md:149Runs PowerShell with execution policy bypassed (security demo / example; quoted — discussed, not commanded)1. **执行策略禁止直接跑 .ps1** → 必须 `powershell -NoProfile -ExecutionPolicy Bypass -File <path>`。
demoquoted -
low Dangerous commands
cmd-execpolicy-bypassscripts/export_png_template.ps1:3Runs PowerShell with execution policy bypassed (code comment)# powershell -NoProfile -ExecutionPolicy Bypass -File expo…ps1 -PptxPath <ascii path to .pptx> [-OutDir <dir>]
comment -
low Dangerous commands
cmd-execpolicy-bypassSKILL.md:197Runs PowerShell with execution policy bypassed (quoted — discussed, not commanded)`powershell -NoProfile -ExecutionPolicy Bypass -File <path>`
quoted
Files scanned: 16. 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 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
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 69 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2168 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
- -4Absolute local paths (C:\Users, /home/…): not portable
- +2Single-language instructions
- +3Description length 689: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 69 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 8 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.