메뉴
Generate a PPTX presentation explaining code changes on the current branch, with matplotlib diagrams and dark theme slides.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/JetBrains/youtrackdb --skill create-presentation명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | create-presentation |
| description | Generate a PPTX presentation explaining code changes on the current branch, with matplotlib diagrams and dark theme slides. |
| argument-hint | [base-branch] |
| user-invocable | true |
Generate a PPTX presentation explaining the changes on the current branch.
If "$ARGUMENTS" is non-empty, use it as the target branch to compare against.
Otherwise, default to origin/develop.
You are creating a technical presentation for a team of developers. The output
is a .pptx file in the project root that the user can open in Google Slides.
git log --oneline <base>..HEAD to list all commits on this branch.git diff --name-only <base>..HEAD to find changed source files.sql/parser/YouTrackDBSql*.java) from hand-written code.Create a slide outline (15–25 slides) covering:
python3 -m venv .tmp/pptx-venv
.tmp/pptx-venv/bin/pip install python-pptx matplotlib
If the venv already exists, skip creation and just verify imports work.
For every diagram (flowcharts, architecture, data flow, record layouts, before/after
comparisons), generate a matplotlib figure rendered to a PNG BytesIO stream.
Follow these conventions:
MPL_BG = '#121224' # figure/axes background
MPL_FG = '#e0e0e0' # default text
MPL_BLUE = '#64B5F6' # titles, primary boxes
MPL_LBLUE = '#81D4FA' # secondary highlights
MPL_GREEN = '#A5D6A7' # success/safe elements
MPL_ORANGE = '#FFB74D' # accent/new/warning
MPL_RED = '#EF5350' # delete/danger
MPL_BOX_BG = '#1a2a44' # box fill
MPL_BOX_BORDER = '#3a5a8a' # box stroke
Use matplotlib.patches.FancyBboxPatch for boxes and ax.annotate with
arrowprops for arrows. Helper pattern:
def make_box(ax, x, y, w, h, text, facecolor, edgecolor, text_color,
fontsize=11, weight='normal'):
box = FancyBboxPatch((x, y), w, h, boxstyle="round,pad=0.15",
facecolor=facecolor, edgecolor=edgecolor, linewidth=1.5)
ax.add_patch(box)
ax.text(x + w/2, y + h/2, text, ha='center', va='center',
fontsize=fontsize, color=text_color, weight=weight, family='monospace', wrap=True)
def make_arrow(ax, x1, y1, x2, y2, color='#81D4FA', style='->', lw=2):
ax.annotate('', xy=(x2, y2), xytext=(x1, y1),
arrowprops=dict(arrowstyle=style, color=color, lw=lw))
matplotlib.use('Agg') before importing pyplot.fig.savefig(buf, format='png', dpi=200, bbox_inches='tight', facecolor=fig.get_facecolor()).ax.axis('off').figsize appropriate for widescreen (e.g. (12, 5) for wide diagrams, (10, 7) for tall ones).ImageDraw.text() to render ASCII art — the default bitmap
font has broken glyph coverage for box-drawing characters (U+250x) and the
output is unreadable in presentations.dot binary which
may not be installed.Use python-pptx to assemble slides. Follow these conventions:
prs.slide_width = Inches(13.333) # widescreen 16:9
prs.slide_height = Inches(7.5)
BG_COLOR = RGBColor(0x1B, 0x1B, 0x2F) # slide background
TITLE_COLOR = RGBColor(0x64, 0xB5, 0xF6) # slide titles
HEADING_COLOR = RGBColor(0x81, 0xD4, 0xFA) # subtitles
TEXT_COLOR = RGBColor(0xE0, 0xE0, 0xE0) # body text
ACCENT_COLOR = RGBColor(0xFF, 0xB7, 0x4D) # bold highlights
CODE_BG = RGBColor(0x12, 0x12, 0x24) # code block fill
TABLE_HEADER_BG = RGBColor(0x1A, 0x3A, 0x5C) # table header row
TABLE_ROW_BG = RGBColor(0x15, 0x15, 0x2A) # odd table rows
TABLE_ALT_BG = RGBColor(0x1D, 0x1D, 0x35) # even table rows
BORDER_COLOR = RGBColor(0x3A, 0x3A, 0x5C) # code block border
prs.slide_layouts[6] (blank layout) for all slides.slide.background.fill.solid(); slide.background.fill.fore_color.rgb = BG_COLOR.(0.5", 0.3").**bold** parsing to apply ACCENT_COLOR.ROUNDED_RECTANGLE shape with CODE_BG fill, Consolas 13pt, green text.slide.shapes.add_picture(stream, left, top, width).Write the entire generator as a single Python script saved to .tmp/gen-presentation.py.
Structure it as:
set_slide_bg, add_title, add_bullet_text, add_code_block, add_table, add_image).prs.save(output_path) at the end.Run with: .tmp/pptx-venv/bin/python .tmp/gen-presentation.py
Save the PPTX to the project root as <branch-name>-presentation.pptx.
Tell the user the file path and total slide count.
Also leave the Python script at .tmp/gen-presentation.py so the user
can tweak and regenerate.