Install
$ agentstack add skill-weitzu-com-ai-article-factory-article-visuals ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
article-visuals (P6 — 图文并茂)
Make figures that serve three readers at once: humans (understanding), search engines (image SEO / rich results), and AI engines (multimodal citation). ≥3 figures per article: 1 cover + ≥2 content figures. This skill is self-contained — it uses the bundled scripts, no external pack needed.
Type decision tree (pick type → tool)
| To express | Type | Tool | Source file | |---|---|---|---| | flow / structure / relationship | diagram | Mermaid | assets/src/*.mmd | | data / comparison / trend | chart | matplotlib (import figlib) | assets/src/*.py | | concept / cover | illustration | AI image (prompt → human fills) | assets/src/cover-prompt.md → assets/img/cover.png | | real UI / object | screenshot/photo | manual | — | | tabular comparison | Markdown table (preferred — AI-extractable) | in prose | — |
Rule: if data fits a Markdown table, use a table; only draw when relationships/trends need it.
Workflow
- From the outline's figure intent, write figure sources into
assets/src/and logassets/图清单.md(caption + alt + placement). - Render:
``bash bash /scripts/render-figures.sh # mermaid + matplotlib → assets/img/ ` figlib.py provides the brand palette (scripts/palette.json) + registered CJK fonts (Chinese won't box) + save() / bar_compare() helpers. If mmdc is missing, .mmd` is skipped gracefully.
- Embed with `
+ a caption carrying the source[C#]`. - Cover: a placeholder is used so it never blocks; generate the real one from
cover-prompt.mdand drop it atassets/img/cover.png.
Image SEO + GEO checklist (each figure must pass)
- Descriptive English kebab-case filename with keywords (not
image1.png). - Alt text describing the figure + naturally containing the keyword.
- Caption is a complete sentence with the data source.
- Compressed (<200KB chart / <400KB cover).
- Every data figure has an equivalent sentence/table nearby (AI reads text; the figure corroborates).
- Don't rely on color alone (color-blind safe); in-figure font ≥ body.
Full detail: ../../references/visuals-spec.md (the repo-root references/ folder).
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: weitzu-com
- Source: weitzu-com/ai-article-factory
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.