菜单
Write and execute Python scripts in this workspace, installing any packages they need with conda or pip. Use for data analysis, charts, quick computations, scraping/parsing research sources, validating numbers cited in the book, or any one-off automation that benefits from running real Python.
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
Build and publish the book from one Markdown source to a GitHub Pages website, a print-quality PDF, and a reflowable ePub, using Quarto. Covers where content/art/tokens live (book/, images/, theme.yml), regenerating the Quarto pages, local render/preview, Mermaid + GFM-alert + numbering handling, cover and chapter-art generation, and the GitHub Actions deploy. Use when rendering, previewing, exporting, deploying, or restyling the book.
Bump the book's edition ("Edition X.Y") and add a Changelog entry, keeping the version string in sync across the web landing page, the PDF copyright page, the ePub colophon, and the Changelog. Use whenever the user wants to release/cut a new edition, bump the version, or update the changelog — e.g. "release Edition 1.1", "bump the version", "cut a new edition", "upgrade the version".
Apply and audit APA 7 citations across a Markdown book. Rewrites in-text citations to hyperlinked author–year (author + title on first mention, plain on later mentions), regenerates a per-chapter References section, and audits for internal-download links, orphans, and broken link text. Use when adding or reformatting citations, adding a source, or building the reference lists.
Given a plain-language description, find the best-matching open-source illustration on undraw.co, recolour it to the book's Rosely palette, save it, and (if a section is named) place it in the book. Use whenever the user wants to "find an image/illustration/graphic for" a spot, "add a picture to §X", "get an undraw image of …", or otherwise illustrate a passage. Because an exact match is unlikely, the skill is deliberately resilient: it tries several search terms, downloads a shortlist of ~3 candidates, renders a preview of each, looks at them, and picks the one that actually matches the description — not just the closest slug. undraw illustrations are flat vector SVGs released free for commercial use with no attribution, and every accent is one recolourable colour, so the winner can be restyled to the book's per-chapter accent automatically. The chain for one image: description → several search terms → pooled candidates → download 3 SVGs → render PNG previews → evaluate and select the best → recolour the win
Ingest a single cutting-edge article, post, or talk — an X (Twitter) link, a blog post, a newsletter, a LinkedIn piece, or a YouTube video (transcript) — and weave it into the book as one well-placed, honestly-flagged citation. Use whenever the user hands you a link (especially an opinion piece, a practitioner thread, an industry-leader post, or a conference talk) and says "treat this as a source", "ingest this", "add this article", or "cite this". These sources are usually emerging opinion rather than verified research, so the citation must say so. The skill runs the whole chain for one link: fetch (web pages via download-source; X/Twitter via the fxtwitter JSON mirror; YouTube via the youtube-transcript-api tool) → save to sources/ → summarise into summaries/ → find the single best home in book/*.md → cite it (flagged as emerging opinion) → update references.json → run the book-style loop on just that section → verify and build. It is the lightweight, single-link cousin of research-topic, and it reuses down
Number Markdown section and subsection headings as N.M and N.M.K per chapter (e.g. 1.2, 2.3.1), leaving chapter titles and the References section unnumbered and skipping code fences. Idempotent — safe to re-run after adding, removing, or reordering sections. Use when adding numbered headings to a book or renumbering after edits.
| name | python-scripts |
| description | Write and execute Python scripts in this workspace, installing any packages they need with conda or pip. Use for data analysis, charts, quick computations, scraping/parsing research sources, validating numbers cited in the book, or any one-off automation that benefits from running real Python. |
| argument-hint | Describe what the script should do, any input/output files, and which libraries (if known). Mention whether you want a reusable script saved or a one-off run. |
| user-invocable | true |
Author, install dependencies for, and run Python scripts inside the aidou workspace.
Use this skill when a task benefits from executing real Python, for example:
Trigger phrases: "run a python script", "compute", "plot", "parse this data", "check these numbers", "scrape", "generate a chart".
| Item | Value |
|---|---|
| Package manager | conda 26.3.2 (Miniconda at C:\Users\ctham\AppData\Local\miniconda3) |
| Active env | base (the only environment) |
| Python | 3.13.13 |
| pip | 26.0.1 |
| conda channels | conda-forge, defaults |
| Platform | Windows, win-64, PowerShell |
Both pip install and conda install work. PyPI and the conda channels are reachable.
[!IMPORTANT] TLS verification is disabled on this machine (corporate proxy / self-signed certificate). conda commands print
InsecureRequestWarningforconda.anaconda.organdrepo.anaconda.com. Installs still succeed, but over unverified HTTPS. This is expected here — do not treat the warning as a failure.
[!IMPORTANT] PowerShell exit-code quirk. conda writes warnings to stderr, which makes PowerShell raise a
RemoteExceptionand return exit code 1 even when the command succeeded. Never judge success by exit code alone — inspect stdout (the package list, "Would install…", or solved-environment block) to confirm.
python -c "…".
Anything reusable or longer than a few lines: save a .py file (see layout below).conda list <pkg> or
python -c "import <pkg>" — it may already be present.conda install -c conda-forge <pkg>
for scientific/binary packages (numpy, pandas, matplotlib, scipy, lxml).
Use pip install <pkg> for pure-Python or PyPI-only packages.Check first, then install only if missing:
conda list pandas # already installed?
conda install -c conda-forge pandas # binary/scientific deps -> conda
pip install some-pure-python-pkg # PyPI-only -> pip
To confirm an install actually worked despite the exit-code quirk, verify by import:
python -c "import pandas, sys; print(pandas.__version__)"
If conda's stderr noise makes terminal output hard to read, filter the warnings:
conda install -c conda-forge pandas 2>&1 |
Select-String -Pattern "InsecureRequestWarning|warnings.warn" -NotMatch
For an unattended install, add -y to skip the conda confirmation prompt.
Inline one-off:
python -c "print(sum(range(101)))"
Saved script:
python scripts/<name>.py
scripts/ (e.g. scripts/check_numbers.py), matching
the existing scripts/html2md.ps1.research/, sources/, or book/ with relative paths so
scripts are portable.requirements.txt or new env unless the user asks — install into base.Count words in a chapter:
# scripts/wordcount.py
from pathlib import Path
text = Path("book/02-productivity.md").read_text(encoding="utf-8")
print(f"{len(text.split()):,} words")
python scripts/wordcount.py
| Symptom | Cause | Fix |
|---|---|---|
| Exit code 1 but output looks fine | PowerShell + conda stderr warnings | Ignore exit code; check stdout / verify by import |
InsecureRequestWarning flood | TLS verification disabled (proxy) | Expected; filter with Select-String … -NotMatch |
Solving environment: failed for a real package | Package not on configured channels | Try -c conda-forge, or fall back to pip install |
ModuleNotFoundError after install | Installed into a different interpreter | Run python -c "import sys; print(sys.executable)" to confirm it's the Miniconda base python |