Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Teamnpx agentmods add skills/aaaaqwq/agi-super-team/content-extractWrote 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/aaaaqwq/agi-super-team/content-extract)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/content-extract"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/content-extract/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/aaaaqwq/agi-super-team/content-extract"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/content-extract.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 | $0.00092 | $0.01041 |
| Opus 5 | $0.00046 | $0.00521 |
| Sonnet 5 | $0.00018 | $0.00208 |
| Haiku 4.5 | $0.00009 | $0.00104 |
Grade A, and why
content-extract 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 4d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
content-extract — 上层内容解析入口(MCP 语义对齐,但不跑 MCP Server)
- Author: Daniel Li
- Copyright © Daniel Li. All rights reserved.
目标:把“给我一个 URL → 产出可读 Markdown + 可追溯入口”变成一个统一入口,供后续所有业务 skill(github-explorer、写作类 skills、日报等)复用。
核心原则(来自你发的 Excel Skill 拆解文章的启发):
- 行为规约层:永远给出可追溯入口(原文 URL + 解析产物路径/链接),绝不编造来源。
- Token 探针:先用低成本 probe 判断可不可以直接抓;不行再走重解析(MinerU)。
- 反弹机制:失败时返回“下一步动作建议”,而不是一堆异常栈。
工作流(Decision Tree)
输入:url
- Domain Whitelist(跳过 probe):若 URL 属于高概率反爬/动态站点(微信/知乎等),直接走 MinerU
- 白名单文件:
references/domain-whitelist.md - 对命中白名单的 URL:强制
model_version=MinerU-HTML
- Probe(低成本):优先用
web_fetch(url)
- 目标:拿到正文 markdown(便宜、快)
- 判断“失败/不合格”条件(见
references/heuristics.md)包括:- 403/401/反爬
- 只有“环境异常/验证码/请在微信打开”等提示
- 内容极短/明显导航页/丢正文
- Fallback(高保真):走 MinerU 官方 API
- 调用下游 driver:
skills/mineru-extract/scripts/mineru_parse_documents.py - 对 HTML 页面(微信等):强制
model_version=MinerU-HTML
- 输出统一结果合同(Result Contract)
无论用 probe 还是 MinerU,都返回同一套结构:
{
"ok": true,
"source_url": "...",
"engine": "web_fetch" ,
"markdown": "...",
"artifacts": {
"out_dir": "...",
"markdown_path": "...",
"zip_path": "..."
},
"sources": [
"原文URL",
"(如使用MinerU)MinerU full_zip_url",
"(如使用MinerU)本地markdown_path"
],
"notes": ["任何重要限制/失败原因/下一步建议"]
}
注意:
engine可能是web_fetch或mineru。
MinerU 调用(给 agent 的确定性脚本)
当需要 MinerU 时,用这个命令(返回 JSON,且可把 markdown 内联进 JSON,便于下游总结):
python3 mineru-extract/scripts/mineru_parse_documents.py \
--file-sources "<URL>" \
--model-version MinerU-HTML \
--emit-markdown --max-chars 20000
路径说明: 上述命令假设你在 skills 安装根目录下执行。如果 mineru-extract 安装在其他位置,请替换为实际路径。
交付规范(强制)
- 输出必须包含
sources(原文入口 + 解析产物入口)。 - 如果 MinerU 成功:必须把
markdown_path(本地路径)写进sources,方便复查。 - 如果两条链路都失败:必须明确失败原因,并给出下一步(例如:让 Boss 提供可访问镜像链接 / 允许我用浏览器 relay 导出 HTML / 走上传 HTML 文件解析的兜底方案)。
本 skill 自身不做什么
- 不跑 MCP Server(避免常驻服务与运维负担)
- 不试图绕过登录/验证码(这属于访问层问题;我们只做解析层和工作流路由)
References
- MinerU API docs: https://mineru.net/apiManage/docs
- MinerU output files: https://opendatalab.github.io/MinerU/reference/output_files/
What ships with it
3 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.
- 4d ago First seen · 99 lines · 92 tokens per session scan A 3b10f04812b4
content-extract is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 1,041 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 2026-09-05.
Other skills, from other repositories
deslop
The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.
root-cause
Find the mechanism behind a failure instead of patching its symptom - reproduce first, one variable per experiment with the prediction written before the run, exit by naming the mechanism and pinning it with a failing test. Use for a bug, an unexplained red test, or a failure that will not reproduce.
guidance
Add, edit, or audit guidance docs. Default writes guidance for Claude (.claude/guidance/, Markdown, moflo universal rules). -h writes for human readers (docs/, lighter ruleset). --html emits HTML with a minimal default stylesheet instead of Markdown. -a audits the .claude/guidance/ directory.
eldar
Consult the Eldar — audit a project's moflo + Claude Code setup for portable, high-leverage gaps and guide remediation. Default mode is read-only audit with severity-ranked findings; --fix presents an interactive triage menu and walks the user through each chosen fix (healer, missing CLAUDE.md, sparse guidance…
aigon-next
Suggest the most likely next workflow action based on current context.
review-deep
Drive the deep-review phase of an automated PR review. Consumes the walkthrough, runs the deterministic deep-review workflow (parallel lenses → adversarial validation → code-enforced threshold/caps), drafts the surviving findings, and completes the review run.