菜单
Process every unanalysed .eml file in the user's corpus inputs/emails/ directory through the full analyse-email pipeline. Skips files that already have a corresponding analysis report. Use when the user has dropped many .eml files into the corpus at once.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/danielrosehill/Claude-SpamHole-Plugin --skill bulk-analyse命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
One-time setup for AdGuard Home integration. Captures the AdGuard Home base URL, credentials, and target blocklist filename, validates connectivity, and persists to corpus/config.json. Use before adguard-push.
Push the user's accumulated tracking-pixel + ad-tracker domains from the SpamHole corpus into a self-hosted AdGuard Home instance, using the credentials configured by adguard-configure. Network-layer block — every device on the LAN benefits, not just one mailbox. Use when the user wants to apply their corpus findings at the DNS layer.
Run the full SpamHole analysis pipeline on a single email — semantic spam reasoning, tracking-pixel detection, sender block, processed-emails log, markdown report. Use when the user wants a deep dive on one email rather than the lighter capture-spam-sample flow.
基于 SOC 职业分类
正在显示 SKILL.md
| name | bulk-analyse |
| description | Process every unanalysed .eml file in the user's corpus inputs/emails/ directory through the full analyse-email pipeline. Skips files that already have a corresponding analysis report. Use when the user has dropped many .eml files into the corpus at once. |
Drain queue. Runs analyse-email on every .eml in the corpus that doesn't already have a report.
Standard resolver.
List <corpus>/inputs/emails/*.eml (skip the sanitised/ subdirectory).
For each file, check <corpus>/outputs/analyses/<basename>-analysis.md. If it exists, skip.
For each unanalysed file, run the same pipeline as analyse-email/SKILL.md — don't re-implement, refer to that skill.
Print a summary table:
If the batch is > 30 files, prompt the user once: "This will run the analyst agent N times. Continue?". Otherwise just run.
