菜单
Convert documents into business stories and infographics. Use for turning reports, documents, or text into visual summaries or infographics.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Extract visual, video, and audio features from media. Use for pixel features (Pillow), video frames (FFmpeg+Pillow), speech/audio features (openSMILE), music features (librosa), and visual semantic analysis (Gemini API batch or standard).
Orchestrate end-to-end academic manuscript preparation following APA 7th edition. Use for writing papers, drafting sections, or academic writing support.
Capture session decisions, conventions, and lessons into plan files, auto-memory, and CLAUDE.md so a fresh session resumes cleanly. Use for "hand off," "wrap up," "update docs for next session," or before /compact.
Run exploratory data analysis on tabular datasets with measurement-appropriate statistics. Use for EDA, descriptive statistics, data exploration, or preparing data summaries for reports and manuscripts.
Generate professional slide deck images from content with smart logo branding. Use for creating slides, presentations, decks, or PPT output.
Stage and commit uncommitted changes with conventional commit messages. Use for committing changes or grouping commits by topic.
| name | q-infographics |
| description | Convert documents into business stories and infographics. Use for turning reports, documents, or text into visual summaries or infographics. |
Transform source documents into business stories and infographic images.
If in plan mode: write a brief plan — "Run q-infographics skill: convert source document to markdown, generate business story via Gemini, generate infographic image." — then exit plan mode immediately. Do NOT attempt document conversion, story generation, or image generation while plan mode is active.
Agent execution instructions:
SKILL_DIR.${SKILL_DIR}/scripts/<script-name>.${SKILL_DIR}/references/<prompt-name>.| Resource | Purpose |
|---|---|
scripts/gen_story.py | Generate business story from document via Gemini API |
scripts/gen_image.py | Generate infographic image via GPT Image 2 (default) or Gemini |
references/story.txt | Story generation prompt template |
references/image.txt | Infographic generation prompt template |
openai
google-genai
Pillow
markitdown
Install: pip install openai google-genai Pillow markitdown
Default infographic model is gpt-image-2 (requires OPENAI_API_KEY). Set IMAGE_MODEL=gemini or pass --model gemini to gen_image.py to use gemini-3-pro-image-preview (requires GEMINI_API_KEY). Story generation (gen_story.py) always uses Gemini.
Load keys from .env:
PowerShell (Windows):
$env:GEMINI_API_KEY = (Get-Content path\to\.env | Where-Object { $_ -match '^GEMINI_API_KEY=' } | Select-Object -First 1).Split('=',2)[1]
Bash (macOS/Linux):
export $(cat /path/to/.env | xargs)
_INFO suffix (e.g., MY_REPORT.pdf → MY_REPORT_INFO.jpg)assets/Logo_Q.png| Step | Action | Command / Reference |
|---|---|---|
| 1 | Convert source document to markdown; show first ~50 lines for confirmation | markitdown <input_file> -o <OUTPUT.md> |
| 2 | Generate business story; show prompt and full output for review | python "${SKILL_DIR}/scripts/gen_story.py" <INPUT.md> "${SKILL_DIR}/references/story.txt" > STORY_OUTPUT.md |
| 3 | Generate infographic image; display result for review | python "${SKILL_DIR}/scripts/gen_image.py" STORY_OUTPUT.md "${SKILL_DIR}/references/image.txt" <SOURCE_NAME>_INFO |
${SKILL_DIR}/references/story.txt — see references/prompts_reference.md${SKILL_DIR}/references/image.txt — see references/prompts_reference.mdInclude: Document-to-story conversion, infographic generation, logo branding. Exclude: Slide decks (use q-presentations), data visualization, chart generation.