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 skills add balabalabalading/huuuuuuho-skills --skill mp-article-writorgit clone --depth 1 https://github.com/balabalabalading/huuuuuuho-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/balabalabalading/huuuuuuho-skills/mp-article-writor)<a href="https://agentmods.dev/skills/balabalabalading/huuuuuuho-skills/mp-article-writor"><img src="https://agentmods.dev/badge/skills/balabalabalading/huuuuuuho-skills/mp-article-writor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/balabalabalading/huuuuuuho-skills/mp-article-writor"><img src="https://agentmods.dev/badge/skills/balabalabalading/huuuuuuho-skills/mp-article-writor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00072 | $0.07341 |
| Opus 5 | $0.00036 | $0.03671 |
| Sonnet 5 | $0.00014 | $0.01468 |
| Haiku 4.5 | $0.00007 | $0.00734 |
Grade A, and why
mp-article-writor 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 2d ago.
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 — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.
公众号文章生成
帮助作者将素材整理为一篇可直接进入微信公众号编辑和配图流程的静态图文长文。
本 Skill 只处理微信公众号。所有交给归藏 Skill 的任务都必须显式传递「微信公众号、静态图文」;禁止生成 Live Photo、MOV、PVT、GIF、MP4、视频替代品、小红书图片或其他平台封面。
文章类型路由
开始写作前,根据用户目的和素材特征选择一个主类型:新闻和软件更新简报、产品体验和工具测评、个人实践和工作流复盘、技术解析和教程、生活叙事和观点文章。
根据作者希望文章回答的核心问题选择类型,日期、版本、发布记录等只作为辅助特征。用户已经明确类型,或创作目的足够清楚时直接选择,不重复询问。只有类型会实质改变文章结构且无法判断时,才询问一次。完整判断标准和各类型写法见 references/文章类型路由.md。选定类型后,在 Step 3、Step 4、Step 5 和 Step 8 持续应用对应规则。
工作流
严格按以下 11 个步骤顺序执行,不可跳步、不可合并。每一步完成后再进入下一步。
Step 1:理解作者意图
先读取 references/文章类型路由.md,确定并记录本次文章的主类型。新闻和软件更新简报不得套用个人故事、情绪曲线或价值升华要求。
先检查当前环境是否能够读取 guizang-social-card-skill 和 guizang-material-illustration。两个 Skill 都是完整静态视觉工作流的推荐前置条件,但不得自动安装、不得声明为强制依赖。
读取环境变量 MP_ARTICLE_IMAGE_MODE,只接受 local 或 picgo:
- 未设置时,使用 ask_user 工具询问一次图片发布方式,推荐并默认选择
local。 - 设置为
local时,只生成本地图片,不探测 PicGo,不产生云端写入。 - 设置为
picgo时,视为作者已经持久授权本工作流通过 PicGo 上传最终图片,再检查本机 PicGo Server 是否可访问。 - 值不合法时停止图片发布分支,提示改为
local或picgo,文章写作和本地视觉生产仍可继续。
如果任一 Skill 缺失,只提示一次并给出 references/视觉路由.md 中的安装命令,同时说明:文章写作仍可继续;Step 10 只能生产当前已安装 Skill 覆盖的视觉素材,缺失部分在 Step 11 标记为「待安装依赖后完成」。不要生成旧版题图或插图 prompt 作为替代,也不要在后续步骤重复提示安装。
使用 ask_user 工具向作者确认以下信息:
- 文章类型:先根据素材自动判断;只有无法判断且会改变文章结构时才询问。
- 切入角度:这篇文章想从什么视角写?(技术拆解 / 个人体验 / 横向对比 / 叙事故事 / 其他)
- 深度偏好:读者应该获得什么程度的理解?(入门科普 / 中度解析 / 深度技术)
- 核心主旨:用一句话描述文章写完后读者应该记住什么
- 素材补充:素材中有哪些是作者的真实经历?有哪些细节需要特别保留或避免?
- 正文解释性插图风格:询问作者选择
guizang-social-card-skill或guizang-material-illustration。前者生成杂志或瑞士风格的完整排版卡片,后者生成 3D 瑞士编辑风格的材质插图。推荐选项应结合文章内容说明理由,但最终由作者确认。所选 Skill 缺失时,明确说明安装后才能生产对应插图。 - 现有视觉素材:确认可用的截图、照片、图表、数据和本地路径;真实素材优先承担证据作用。
- 输出目录:根据「视觉生产与交付」确定本次文章和图片的明确目录,并向作者展示。不得将归藏 Skill 的
local-tests目录作为最终交付目录。 - 图片发布方式:
local只生成本地图片并使用相对 Markdown 路径;picgo上传到作者已经配置的图床并替换为 HTTPS 地址。环境变量未设置时只询问一次。 - 授权方式:本次对选定归藏 Skill 的首次渲染授权,同时授权后续自动执行静态图片检查和必要修复。只有作者选择
picgo,或环境变量明确设置为picgo时,才包含云端上传授权。
正文解释性插图风格只询问一次。同一篇文章默认只使用一种归藏插图风格,作者明确要求混用时除外。真实截图和照片不计入风格混用。
篇幅按文章类型确定。新闻和软件更新简报推荐 1500-3000 字,其他类型通常推荐 4000-8000 字。优先保证文章结构完整、前后逻辑连贯,无需为凑字数而注水。如果素材不足,主动说明需要补充的内容,不自行编造。作者的可信度建立在真实性之上,编造细节或数据是不可接受的。
What ships with it
7 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.
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.
- 2d ago Changed · +28 lines · +1 tokens per session 64bc1f8e0a9d
- 11d ago First seen · 340 lines · 71 tokens per session scan A f60fdfedf19a
mp-article-writor is a skill published in the GitHub repository balabalabalading/huuuuuuho-skills (117 stars, last pushed 3d ago), licensed MIT. It adds 72 tokens to every session and 7,341 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 2026-08-30.
Other skills, from other repositories
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
officecli-data-dashboard
Use this skill to build a multi-element Excel dashboard — Dashboard sheet on open, multiple formula-driven KPI cards, multiple charts, sparklines, and conditional formatting — from CSV or tabular input. Trigger on: 'dashboard', 'KPI dashboard', 'analytics dashboard', 'executive dashboard', 'metrics dashboard', 'CSV to…
A set of instructions for working with PDF files, which are documents designed to preserve their layout across devices.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
gpt-image-2
A skill for generating or editing images with GPT Image 2 across local, host-provided, or advisory setups.
new
Create a new project to start development quickly.