Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/lovstudio/skills/article-creatornpx skills add lovstudio/skills --skill article-creatorgit clone --depth 1 https://github.com/lovstudio/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lovstudio/skills/article-creator)<a href="https://agentmods.dev/skills/lovstudio/skills/article-creator"><img src="https://agentmods.dev/badge/skills/lovstudio/skills/article-creator.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00075 | $0.04348 |
| Opus 5 | $0.00037 | $0.02174 |
| Sonnet 5 | $0.00015 | $0.00870 |
| Haiku 4.5 | $0.00007 | $0.00435 |
Grade A, and why
lov-article-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lov-article-creator
把零散事实、研究材料或现有草稿变成一套可交付的公众号文章包,而不只是写出一段 Markdown。
每次完整交付同时包含:经过事实约束的正文、题材适配的编辑模板、品牌化横版封面、独立的 4:3 横向正文首图、来源与发布元数据,以及一份可回读的验收报告。
Triggers
Activate when
- “按我的文风写一篇公众号文章,并配好封面和正文首图。”
- “把这些研究材料做成统一品牌的公众号长文。”
- “Create a branded WeChat article package from these notes.”
- “Turn this draft into a publish-ready WeChat article with a wide cover and a 4:3 body hero.”
- “把这篇现有 Markdown 做成完整的品牌化公众号版本。”
- “忠实转载这篇合作方文章,保留原文并加入我们的开场和收尾。”
Do not activate when
- 只要求改写一段文字或匹配个人语气,不需要公众号模板与视觉包;使用写作风格能力。
- 只要求读取、修改或核验公众号后台已有草稿;使用
lov-publish-wechat-article的 existing-draft 管线。 - 只要求把现成文件写入草稿箱或正式发布;使用公众号发布能力。
- 只要求生成一张孤立图片,且不需要文章级命题、品牌与双比例验收。
Product contract
- One article, one package. 正文、来源、封面、首图和验收记录位于同一文章目录。
- Facts before voice. 先建立事实账本,再套用文风;不得用第一人称补造经历、数字或判断变化。
- Objective before outline. 先明确创作条件、动机、传播目标与
desired_reader_change,再决定结构。用户给出的命题、开头、章节或草稿是重要约束和证据,不自动等于已经充分、正确的传播策略。 - One writing owner. 新写与改写必须调用
lov-writing-style;其内部调用唯一的反 AI / 作者性规则源lov-human-writing。本 Skill 只拥有公众号题材、结构、品牌和制品规则,不复制通用文风规则。 - Template is semantic. 固定的是信息顺序、证据门槛与品牌组件,不强迫所有题材使用同一组空洞标题。
- Heading roles stay separate. 文件名、平台标题、正文 H1、章节 H2/H3 与 TOC 标签是不同制品。章节标题负责划分读者的认知阶段并逐步引人进入,不负责压缩段落;TOC 只镜像最终章节结构,不反向决定正文。
- Brand comes from Profile. 发布主体、Logo、官网、色彩和禁用信息从共享 Profile 解析,不把用户私有路径写入公开文章或 Skill 源码。
- Two image roles are mandatory. 完整管线必须输出
2.35:1分享封面和独立的4:3横向正文首图;不得把分享封面成品直接当正文首图。 - Benchmark claims require benchmark evidence. 文章一旦给出排名、雷达图或量化优劣,就必须在结果之前公开测试对象、输入、完整 Prompt、执行环境、评价指标、评分规则、至少一个逐项算分示例和复现方法;分数不得先于方法出现。
- Publication identity wins. 公众号发布主体与母品牌分开;封面只使用发布主体官方白色横向 lockup,方形图标、母品牌 Logo 和橙色变体都不能替代。
- Generated is not accepted. 文件存在不等于完成;必须通过尺寸、引用、事实、品牌和移动阅读质量门。
- Publishing is separate. 默认止于本地可发布文章包;写入草稿箱或正式发布需要明确授权,并交给下游发布能力。
- Platform title is not body content. canonical Markdown 保留唯一 H1 作为标题真源;写入微信公众号时,标题进入平台标题字段,正文默认隐藏该 H1,避免首图前重复出现同名标题。
- References stay quiet. 正文中穿插的资料来源、补充链接和引申阅读默认使用低对比度的小字斜体资料注,不与章节标题、正文论点或主要行动入口争夺视觉层级。
- Repost source is frozen. 转载时来源正文是逐字冻结区;作者性优化只作用于发布方新增区块,且
copyrightMode固定为reprint。
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitignore 84 B
- assets/article-template.md 838 B
- cases/agent-harness-system-prompt/article-manifest.json 1.6 KB
- cases/agent-harness-system-prompt/article.md 29 KB
- cases/agent-harness-system-prompt/article.uploaded.md 30 KB
- cases/agent-harness-system-prompt/assets/agent-harness-cards/agent-harness-radar.png 172 KB
- cases/agent-harness-system-prompt/assets/agent-harness-cards/claude-code.jpg 218 KB
- cases/agent-harness-system-prompt/assets/agent-harness-cards/claude-code.png 2921 KB
- cases/agent-harness-system-prompt/assets/agent-harness-cards/codex.jpg 220 KB
- cases/agent-harness-system-prompt/assets/agent-harness-cards/codex.png 2793 KB
- cases/agent-harness-system-prompt/assets/agent-harness-cards/dsh.jpg 202 KB
- cases/agent-harness-system-prompt/assets/agent-harness-cards/dsh.png 2433 KB
- cases/agent-harness-system-prompt/assets/agent-harness-cards/pi.jpg 168 KB
- cases/agent-harness-system-prompt/assets/agent-harness-cards/pi.png 2219 KB
- cases/agent-harness-system-prompt/cover/art-master.png 2306 KB
- cases/agent-harness-system-prompt/cover/art-prompt.md 1.3 KB
- cases/agent-harness-system-prompt/cover/art-source.png 2394 KB
- cases/agent-harness-system-prompt/cover/article-opening-vertical.jpg 389 KB
- cases/agent-harness-system-prompt/cover/article-opening-vertical.png 2509 KB
- cases/agent-harness-system-prompt/cover/cover-manifest.json 1.3 KB
- cases/agent-harness-system-prompt/cover/wechat-cover-wide.jpg 313 KB
- cases/agent-harness-system-prompt/cover/wechat-cover-wide.png 1984 KB
- cases/agent-harness-system-prompt/prompts/claude-code-2.1.88-system-prompt-builder.ts 53 KB runs code
- cases/agent-harness-system-prompt/prompts/codex-gpt-5.6-sol-base-instructions.txt 17 KB
- cases/agent-harness-system-prompt/prompts/dsh-0.1.0-rc.8-rendered-system-prompt.md 3.4 KB
- cases/agent-harness-system-prompt/prompts/pi-0.73.1-system-prompt-builder.ts 5.9 KB runs code
- cases/agent-harness-system-prompt/quality-report.json 1.1 KB
- cases/agent-harness-system-prompt/sources.md 423 B
- cases/cases.json 3.2 KB
- CHANGELOG.md 2.6 KB
- kit.yaml 883 B
- LICENSE 1.0 KB
- pricing-card.yaml 763 B
- prompts/cover-art.md 1.1 KB
- README.md 3.6 KB
- references/article-template.md 3.8 KB
- references/brand-edition.md 1.7 KB
- references/brand-system.md 2.2 KB
- references/cover-system.md 2.6 KB
- references/editorial-strategy-and-headings.md 4.1 KB
- references/output-contract.md 2.7 KB
- references/quality-gate.md 4.4 KB
- references/repost-authorship-integrity.md 2.6 KB
- references/repost-editorial-overlay.md 1.7 KB
- references/repost-publication-handoff.md 1.5 KB
- references/repost-source-fidelity.md 1.6 KB
- references/skill-card-standard.md 660 B
- references/skill-composition.md 3.5 KB
- references/user-profile.md 2.7 KB
- references/writing-style.md 970 B
- scripts/audit_repost.py 5.4 KB runs code
- scripts/build_article_package.py 6.3 KB runs code
- scripts/compose_covers.py 7.8 KB runs code
- scripts/profile_store.py 8.3 KB runs code
- scripts/validate_article_package.py 16 KB runs code
- scripts/validate_skill.py 25 KB runs code
- skill-card.md 3.2 KB
- skill-card.yaml 5.8 KB
- skill.yaml 3.2 KB
- skills/article-writing/CHANGELOG.md 283 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 256 lines · 75 tokens per session scan A b41e7f126c5b
lov-article-creator is a skill published in the GitHub repository lovstudio/skills (64 stars, last pushed 2d ago), licensed MIT. It adds 75 tokens to every session and 4,348 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
illustration:popa
Generate intricate hand-drawn sketchnote illustrations starring Popa, a cute pink blob with a green sprout and a notepad, on soft pastel scenes. One busy page of many linked boxes, notes, arrows and icons — busy but fully legible. Use for dev/product/system explainers, how-it-works, architecture, walkthroughs, and…
illustration
Generate intricate hand-drawn sketchnote illustrations starring Popa (a pink blob with a green sprout and a notepad). Use when the user wants illustrations/diagrams/explainer images/shot lists for an article, post, README, deck, system, or idea. Alias of illustration:popa.
poster-style-transfer
Analyze an uploaded or local reference poster, extract its reusable design system, and transpose that system to an original poster with a new theme, title, subtitle, or campaign copy.
ambitious-implementation
Write large, thorough implementations instead of minimal ones. Use for UI, animation, art/graphics, sound design, theming, and any craft-driven work where richness and detail are the point — and whenever output quality has been called cheap, flat, simple, or generic.
build-and-look
Prefer building and looking at variations over prolonged reasoning. Use when work is visual, aesthetic, or hard to predict from first principles — UI, art, animation, sound, layout, colour — and whenever you notice yourself planning at length without producing anything to look at.
comfyui-assets
Generate game/app art assets locally with ComfyUI and SDXL — seamless tileable textures, transparent-background cutouts, ornament stamps, wallpaper patterns. Use when producing material textures or sprite elements for a rendering pipeline, or when asked to create art assets with a local image model.