anvil-new-article

anvil-new-article is a skill for Claude Code, Codex from PNGTRID/AnvilWiki. It costs 111 tokens per session (2,354 once invoked), scanned A, original, MIT.

A tool that turns supplied material into MDX article pages for AnvilWiki, a wiki site built from structured content files. It fills in page details and checks that the pages follow the site’s rules.

In plain words
What is it for?
Use it to create game guides, boss pages, reward-code lists, rankings, and other wiki articles from source material.
Why use it?
It reduces the manual work of shaping notes, videos, guides, or data into pages that the website can build successfully.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create game guides, boss pages, reward-code lists, rankings, and other wiki articles from source material.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pngtrid/anvilwiki/anvil-new-article
Install

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.

Any agent
npx skills add PNGTRID/AnvilWiki --skill anvil-new-article
Clone the repo
git clone --depth 1 https://github.com/PNGTRID/AnvilWiki

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for anvil-new-article

README.md
[![agentmods](https://agentmods.dev/badge/skills/pngtrid/anvilwiki/anvil-new-article/github.svg)](https://agentmods.dev/skills/pngtrid/anvilwiki/anvil-new-article)
Your own site
<a href="https://agentmods.dev/skills/pngtrid/anvilwiki/anvil-new-article"><img src="https://agentmods.dev/badge/skills/pngtrid/anvilwiki/anvil-new-article/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.

agentmods 80×15 button for anvil-new-article

Your own site · 80×15
<a href="https://agentmods.dev/skills/pngtrid/anvilwiki/anvil-new-article"><img src="https://agentmods.dev/badge/skills/pngtrid/anvilwiki/anvil-new-article.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,354 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 95
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00111 $0.02354
Opus 5 $0.00056 $0.01177
Sonnet 5 $0.00022 $0.00471
Haiku 4.5 $0.00011 $0.00235

Measured 7d ago against content hash 84658146a62f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

anvil-new-article 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 7d 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.

.agent/skills/anvil-new-article/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AnvilWiki 新文章生成

把用户给的任何素材变成一篇构建必过的 MDX 页面。先读规范再动手:

  1. docs/content-format.md(frontmatter 字段表 + 正文规则)
  2. src/content.config.ts(Zod schema——这是构建时硬校验,不过就 build 失败)
  3. src/config/navigation.tsCONTENT_TYPES(category 必须是这里的 key)
  4. 参考一篇同类文章(如 src/content/wiki/en/bosses/emberfang.mdx)对齐结构

工作流

Step 0 — 视频转文字素材(素材是 YouTube 视频时)

字幕是素材不是成文——口语流水账必须重构成问题式 H2 + 直答结构,不许整段照搬。

拿字幕(三选一,按依赖从少到多):

  1. 用户直接粘贴字幕/文字稿(零依赖,优先要)
  2. yt-dlp --skip-download --write-subs --write-auto-subs --sub-langs "en.*" -o "transcript" "<视频URL>"(产出 transcript.*.vtt,时间戳行自己剥;yt-dlp -j "<URL>" 顺带拿标题/频道名,正文引用出处用)
  3. pip install youtube-transcript-api 走 Python API(手动字幕优先、自动生成兜底;YouTube 风控对数据中心 IP 越来越狠,失败就回 1)

从视频/字幕提取什么 → 落到哪里:

从视频/字幕提取 落到 AnvilWiki 契约
核心话题 + 搜索意图 走 Step 1 的 category 判型表
kebab-case slug 文件名 src/content/wiki/<locale>/<category>/<slug>.mdx
标题(≤80 字符,含游戏名+关键词) frontmatter title
meta 描述(40-165 字符) frontmatter description
一句话直答 frontmatter summary(40-60 词——Quick Answer 卡 + AI 搜索摘要候选)
5-8 组问答对 frontmatter faq:({question, answer} 数组——自动渲染可见 <details> 区块 + 并入 FAQPage JSON-LD)
内容大纲 问题式 H2 + 每节首段 40-60 词直答(Step 3 规则)
标签 复用现有 tag 词汇表(Step 2 的 grep)

两条红线(不满足不许转正):

  • 事实红线:视频作者口播的数值/掉率/兑换码一律视为未验证素材,成品必须 draft: true,人工进游戏核实后才能转正;查不到就删,宁缺毋假(编造一个假码毁掉全站信任)。
  • 版权红线:转写自己的视频最干净;拿别人的视频字幕成文属于演绎内容,有 DMCA 与重复内容风险——他人视频只做事实参考,正文必须完全重写;嵌入原视频(frontmatter videos: ["<11位ID>"] + <Video id="..." />,见 Step 3)是标准且合规的做法。

缩略图:https://img.youtube.com/vi/<ID>/maxresdefault.jpg(404 则 hqdefault.jpg)只作 pnpm gen-covers 出品牌封面的视觉参考,抓来的图不要直接发布。

Step 1 — 判断页面类型(按搜索意图)

用户素材特征 category 建议 页面形态
兑换码列表 / 奖励码 codes frontmatter codes: 数组(status/expiryDate/source),页面自动渲染 Active/Expired 分区 + FAQPage JSON-LD
Boss 打法 / 属性 bosses frontmatter 加 boss: 结构化数据卡 + 按阶段 H2
教程 / 路线 / how to guides 问题式 H2 + 每节首段 40-60 词直答
排名 / 对比 guides(或 tier-list 分类若存在) 表格为主

Read the full file on GitHub · 104 lines

Changes

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.

  1. 7d ago Changed · +34 lines · +18 tokens per session 84658146a62f
  2. 11d ago First seen · 70 lines · 93 tokens per session scan A 06d9fb2165f6

Subscribe to this mod's changes

anvil-new-article is a skill published in the GitHub repository PNGTRID/AnvilWiki (133 stars, last pushed today), licensed MIT. It adds 111 tokens to every session and 2,354 once invoked, about $0.0006 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.