llm-data-research

llm-data-research is a skill for Claude Code from AgenticAIPlan/AgenticAISkills. It costs 471 tokens per session (5,882 once invoked), scanned D, original, MIT.

A recurring research workflow for tracking the large-language-model data market, including training data, data-labeling recruitment, and expert recruitment. It collects recent information from Chinese social and media platforms, organises it in Excel, and produces market insight reports.

In plain words
What is it for?
Use it to monitor model companies and data providers, analyse recruitment patterns, infer areas of model development, connect findings to leads, and create Excel or Word reports.
Why use it?
This market changes quickly, so relying only on older background knowledge can miss current hiring and business signals.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the agentic-ai-skills plugin — 54 skills shipped together

Good fit Use it to monitor model companies and data providers, analyse recruitment patterns, infer areas of model development, connect findings to leads, and create Excel or Word reports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agenticaiplan/agenticaiskills/llm-data-research
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 AgenticAIPlan/AgenticAISkills --skill llm-data-research
Clone the repo
git clone --depth 1 https://github.com/AgenticAIPlan/AgenticAISkills

Made for: Claude Code.

Or install agentic-ai-skills, the plugin that ships this one along with the rest of its 54 skills.

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 llm-data-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/llm-data-research/github.svg)](https://agentmods.dev/skills/agenticaiplan/agenticaiskills/llm-data-research)
Your own site
<a href="https://agentmods.dev/skills/agenticaiplan/agenticaiskills/llm-data-research"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/llm-data-research/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 llm-data-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/agenticaiplan/agenticaiskills/llm-data-research"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/llm-data-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 471 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,882 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00471 $0.05882
Opus 5 $0.00235 $0.02941
Sonnet 5 $0.00094 $0.01176
Haiku 4.5 $0.00047 $0.00588

Measured 9d ago against content hash 5bb04ba6f63a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade D, and why

llm-data-research scanned grade D with 3 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/generate_excel.py, scripts/generate_report.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -s -X POST "http://localhost:3456/click?target=$XHS_ID" -d '.close-icon' > /dev/null

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s http://localhost:3456/targets | python3.11 -c "import json,sys; t=json.load(sys.stdin); print(f'CDP就绪,{len(t)}个Tab')"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:3456/targets | python3.11 -c "import json,sys; t=json.load(sys.stdin); print(f'CDP就绪,{len(t)}个Tab')"
skills/llm-data-research/SKILL.md · 478 lines

How it starts

The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.

大模型数据动态定期洞察 Skill

本 Skill 自动执行完整的大模型数据市场调研流程,涵盖数据采集、Excel 整理、合作线索关联、市场洞察报告输出、定时任务设置、Word 报告生成共六个步骤。

新增核心能力:监控头部厂商和外部数商的招募动态(数据标注任务招募、专家招募画像),通过招募信号反推:

  • 头部大厂下一代模型的发力方向(招募什么样的专家 → 在训练哪个能力方向)
  • 外部数商(Talents AI、一面千识等)的生产能力和专家储备质量
  • 海外大厂(OpenAI、Google、Meta 等)的数据战略动向

环境前置检查

在开始前确认以下环境就绪:

# 1. 确认 CDP Proxy 运行(web-access skill 依赖)
curl -s http://localhost:3456/targets | python3.11 -c "import json,sys; t=json.load(sys.stdin); print(f'CDP就绪,{len(t)}个Tab')"

# 2. 确认 Python 版本(openpyxl 安装在 python3.11)
python3.11 -c "import openpyxl; print('openpyxl', openpyxl.__version__)"

若 CDP Proxy 未启动,运行:node ~/.claude/skills/web-access/scripts/check-deps.mjs

关键约束

  • 所有浏览器操作必须在主线程用 Bash 直接执行,不得启动子 Agent 执行网络操作(子 Agent 无法继承工具权限)
  • Excel 生成使用 python3.11(不是 python3 或 python)
  • 小红书详情页需登录才能看正文,搜索结果列表页关闭弹窗后可读取卡片信息

工具受限时的降级策略

如果 Bash/Write 工具被拒绝,不要停止,切换到「知识合成 + 内联输出」模式继续执行所有6步

  1. 继续完成所有6步,文件输出改为内联 Markdown 输出,并在每步开头注明:> ⚠️ 工具受限:以下为内联输出,建议手动保存
  2. Step 1:列出将执行的具体搜索关键词,从训练知识中综合近期信息(明确标注「来源:训练知识,截止至 XXXX 年」)
  3. Step 2 Excel:输出各 Sheet 的列名 + 至少5条真实数据行(Markdown 表格格式)
  4. Step 4 报告:完整输出所有8节内容,各节有实质分析,不留空节
  5. Step 6 Word:输出完整 /tmp/llm_report_data.json JSON 内容(代码块包裹),提示用户可手动运行 node scripts/generate_report.js --data /tmp/llm_report_data.json

用户真正需要的是分析质量,不只是文件存在。在工具受限时,高质量的内联分析报告比「无法执行」更有价值。


Step 1:多平台信息采集

1.1 小红书采集

小红书有反爬机制,必须通过 CDP 操作:

# 打开搜索页
XHS_ID=$(curl -s "http://localhost:3456/new?url=https://www.xiaohongshu.com/search_result?keyword=大模型专家标注招募" | python3.11 -c "import json,sys; print(json.load(sys.stdin)['targetId'])")
sleep 4

# 关闭登录弹窗(弹窗选择器)
curl -s -X POST "http://localhost:3456/click?target=$XHS_ID" -d '.close-icon' > /dev/null
sleep 1

# 提取搜索结果卡片
curl -s -X POST "http://localhost:3456/eval?target=$XHS_ID" -d '
JSON.stringify(Array.from(document.querySelectorAll("section.note-item, [class*=\"note-item\"]")).map(el => {
  const title = el.querySelector("a[class*=\"title\"] span, [class*=\"title\"] span")?.innerText?.trim() || "";
  const author = el.querySelector("[class*=\"author\"] span")?.innerText?.trim() || "";
  const time_text = el.innerText?.match(/\d{4}-\d{2}-\d{2}|\d+天前|\d+小时前|[0-9]{2}-[0-9]{2}/)?.[0] || "";
  const href = el.querySelector("a[href*=\"explore\"]")?.href || "";
  return {title, author, time_text, url: href};
}).filter(x=>x.title).slice(0,20))
'

Read the full file on GitHub · 478 lines

Files

What ships with it

5 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.

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. 9d ago First seen · 478 lines · 471 tokens per session scan D 5bb04ba6f63a

Subscribe to this mod's changes

llm-data-research is a skill published in the GitHub repository AgenticAIPlan/AgenticAISkills (11 stars, last pushed 3mo ago), licensed MIT. It adds 471 tokens to every session and 5,882 once invoked, about $0.0024 per session on Opus 5. A static security scan graded it D with 3 findings (sends data to an external url, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.