BF Skywork-ppt
Skywork PPT (skywork) - Use when the user wants to work with PowerPoint presentations. Triggers: (1) Generate a new PPT from a topic — 'generate a PPT', 'create a presentation about X', 'make slides', '帮我做个PPT', '生成演示文稿', 'PPTを作って', 'スライドを作って', 'PPT 만들어줘', '슬라이드 만들어줘'; (2) Imitate an existing .pptx style/template — 'use this template', 'imitate this PPT/style', '用这个模板', '仿照这个PPT', 'このテンプレートを使って', '이 템플릿 써줘'; (3) Edit existing PPT via natural language — 'modify slide N', 'change background', 'add a slide', 'make it more beautiful', '修改第N页', '更换背景', '新增一页', '美化一下', 'N枚目を修正', '背景を変えて', 'きれいにして', 'N번 슬라이드 수정', '배경 바꿔줘'; (4) Convert NotebookLM-exported pptx/pdf into editable pptx — 'make this notebooklm ppt editable', 'convert notebooklm export to editable pptx', '把这个notebooklm导出的pptx改成可编辑pptx', '把这个pdf转成可编辑pptx'; (5) Local .pptx file ops — 'delete slide N', 'reorder slides', 'merge pptx', 'extract slides', 'how many slides', '删除第N页', '调整顺序', '合并PPT', '提取幻灯片', 'スライドを削除/並べ替え/結合/抽出', '슬라이드 삭제/순서 변경/합치기/추출'.
As a process F 58/100 · Will not run — References files that are not bundled: url
How to improve
- 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: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
missing-refreference to a missing file: url
Process rating: all ten parameters 58/100
- 0Tools and files. 1 referenced file(s) missing: url
- 0Result and completion. Does not say what the result is
- 30Running it twice. 4 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 33 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2217 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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)
- +3Description length 1015: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -34 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 19 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.