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 PNGTRID/AnvilWiki --skill anvil-batch-articlesgit clone --depth 1 https://github.com/PNGTRID/AnvilWikiWrote 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/pngtrid/anvilwiki/anvil-batch-articles)<a href="https://agentmods.dev/skills/pngtrid/anvilwiki/anvil-batch-articles"><img src="https://agentmods.dev/badge/skills/pngtrid/anvilwiki/anvil-batch-articles/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/pngtrid/anvilwiki/anvil-batch-articles"><img src="https://agentmods.dev/badge/skills/pngtrid/anvilwiki/anvil-batch-articles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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 61 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]
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 | $0.00100 | $0.01409 |
| Opus 5 | $0.00050 | $0.00705 |
| Sonnet 5 | $0.00020 | $0.00282 |
| Haiku 4.5 | $0.00010 | $0.00141 |
Grade A, and why
anvil-batch-articles 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 9d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AnvilWiki 批量内页生成
把一份关键词清单变成一批构建必过的 MDX 页面。单篇规范与 anvil-new-article 完全一致——本技能只解决「批量」的产能与一致性。先读规范再动手(与 anvil-new-article 相同):
docs/content-format.md(frontmatter 字段表 + 正文规则)src/content.config.ts(Zod schema——构建时硬校验)src/config/navigation.ts(category 必须是这里的 key)docs/handbook/zh/batch-pages.md(方法论来源:批量≠灌水)
工作流
Step 1 — 意图归类(照抄 anvil-new-article 的分类表)
用户给的关键词清单(每行一个搜索词),先逐行判断搜索意图:
| 关键词特征 | category 建议 | 页面形态 |
|---|---|---|
| 兑换码 / codes / redeem / 奖励码 | codes |
codes: frontmatter 数组 + Active/Expired 自动分区 + FAQPage JSON-LD |
| Boss 名 / 打法 / 属性 / how to beat | bosses |
boss: 结构化数据卡 + 按阶段 H2 |
| 教程 / 路线 / 怎么 / how to | guides |
问题式 H2 + 每节首段 40-60 词直答 |
| 排名 / 对比 / best / tier | guides(或 tier-list 分类若存在) |
表格为主 |
清单里意图不明的词列出来问用户,不要猜。
Step 2 — 生成清单文件 new-posts.csv
- 列:
locale,category,slug,title,description(description 可后补,脚本会写 TODO 占位)。 - slug 规则:小写、连字符、只留游戏名允许的字符(
bulk-new-posts会自动规范化并报告改动)。 - title 含游戏名 + 关键词,≤80 字符。
- 先跑
pnpm bulk-new-posts --dry-run看计划(已存在的文件会被跳过,绝不覆盖),确认后去掉--dry-run真实写入——全部是draft: true草稿,不会进 build。
Step 3 — 按统一提示词模板批量填充正文
不要每篇临时想结构。 每类意图用同一份固定结构,逐篇填素材:
- 通用骨架(所有意图):
- 首个 H2 = 该关键词的问题式改写("How do I …?")
- 每个 H2 后第一段 40-60 词直答(Quick Answer / AI 摘要候选)
- 数据进 Markdown 表格,步骤用有序列表
- 至少 1 条内链指向真实存在的相关文章(
grep或pnpm build后pnpm check-links验证),无合适页面就不加 - frontmatter 硬规则同 anvil-new-article:description 40-165 字符、summary 40-60 词直答、tags 复用已有词汇表、不写 H1
- 非默认语言(如 ja)正文里的站内链接必须带语言前缀(
/ja/bosses/x/)——裸/bosses/x/会静默跳到英文页
- codes 页额外:
codes:数组逐条登记(code/reward/status/expiryDate/source),正文只写怎么兑换 - bosses 页额外:
boss:数据卡(hp/weakness/resistant/location)+ 按阶段 H2 - 同批反重复:同一批文章之间,开头句式、小节命名、表格列头不允许模板化复用——每篇从关键词本身的问法出发组织语言
Step 4 — 全批验收(必须执行)
pnpm check-content # H1/alt/跳级/尾斜杠 lint(页面内链必须以 / 结尾)
pnpm build # Zod schema + 全站构建
任何一篇失败就修复后重跑,两个命令全绿才算完成。然后把「仍是 draft、素材不足待补」的篇目列成清单告诉用户。
可选(anvilwiki-ops ≥0.1):批量完成后
npx anvilwiki-ops submit --title "batch: <N> pages"走校验→分支→PR。
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.
- 9d ago First seen · 70 lines · 100 tokens per session scan A e46584005fae
anvil-batch-articles is a skill published in the GitHub repository PNGTRID/AnvilWiki (130 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 1,409 once invoked, about $0.0005 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
astro
Build content-focused websites with Astro — zero JS by default, islands architecture, multi-framework components, and Markdown/MDX support.
specification-website
Query and apply The Website Specification — a platform-agnostic specification of what a good website does, with each item tagged required, recommended, optional, or avoid. Use when the user asks what their site should have, whether something is required, how to audit a URL, what's missing for agent readiness, or…
polyglow-content
Use this skill to discover and read Polyglow's public multilingual editorial content.
cocktails-from-my-bar
Turn a photo of a home bar, or a list of bottles, into the cocktails you can make right now using cocktail.glass.
substitute-an-ingredient
Decide whether a cocktail ingredient can be swapped for one on hand, and find adjacent drinks with cocktail.glass.
instrument-ui
The visual system for this project — an instrument, not a dashboard. Covers density, monospaced numerals, colour as signal, motion tied to real values, and the specific patterns that are banned because they read as machine-generated. Use this skill for every frontend task: components, layout, typography, colour…