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 agentscope-ai/QwenPaw-Data --skill fetch-datagit clone --depth 1 https://github.com/agentscope-ai/QwenPaw-DataWrote 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/agentscope-ai/qwenpaw-data/fetch-data)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw-data/fetch-data"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/fetch-data/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/agentscope-ai/qwenpaw-data/fetch-data"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/fetch-data.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 | $0.00276 | $0.05635 |
| Opus 5.5 | $0.00110 | $0.02254 |
| Sonnet 5.5 | $0.00055 | $0.01127 |
| Haiku 4.5 | $0.00028 | $0.00564 |
Grade A, and why
fetch-data 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 1mo 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fetch-data
将用户的数据分析问题转为结构化意图，并补全取数所需完整语义上下文，生成 NL2SQL prompt 与 SQL，执行后返回查询结果供下游分析。
前置条件
- 确认用户的数据分析问题明确（要分析什么、大致时间/范围）。
- 检查
{workdir}是否已包含全部所需分析数据：- 已全部存在 → 直接使用这些文件，结束取数，不执行取数流程。
- 有缺失 → 继续。
取数流程
存储约定：落盘生成 NL2SQL prompt 所必需的产物，以及据此产出的 prompt / SQL 本身。文件命名由各步骤自行决定（建议语义清晰、便于追溯），但目录不能错位。
Step 产物 存储路径 性质 1 结构化问题（含 Step 3 改写后的版本） {workdir}/steps/prompt 输入 2.1 指标信息 {workdir}/data/raw/prompt 输入（语义层 / 上下文） 2.2 数据表元数据 {workdir}/data/raw/prompt 输入（语义层 / 数据湖仓元数据） 4 NL2SQL prompt {workdir}/steps/prompt 产出 5 生成的 SQL {workdir}/steps/prompt 下游代码
Step 1. 问题结构化
从用户的自然语言分析问题中抽取字段，结构化产物落盘到 {workdir}/steps/（属于步骤过程产物）。
Schema（缺失字段填 null，不要省略键）：
{
"question": "<原始用户问题>" # 用户原始问题
"domain": "<业务域>", # 用户问题面向的业务领域/数据来源，如 产品A、产品B 等
"metrics": [ # 数据分析问题中涉及的关键指标
"<关键指标1>", # 如 DAU
"<关键指标2>" # 如日均访问用户数
],
"intention": "<分析意图>", # 用户想要完成的最终分析问题，如“数据在不同端的分布情况”
"scope": [ # 数据的限定范围，如时间范围、维度等
"<时间限定>", # 数据分析针对的时间范畴，如上个月、近3个月等
"<地域限定>" # 数据分析针对的地域范畴，如“中国以及俄罗斯用户”
]
}
| 字段 | 含义 | 示例 |
|---|---|---|
question |
原始问题 | 上个月，中国与俄罗斯用户对某产品的日均访问用户数在各个端的分布情况 |
domain |
业务领域 | 产品A / 产品B / 产品C |
metrics |
关键指标 | DAU、日均访问用户数、次日访问留存率 |
intention |
最终分析问题 | 数据在不同端的分布情况 |
scope |
数据限定范围（时间、地域等） | ["上个月", "中国以及俄罗斯用户"] |
- 用户未提及的字段 →
null（scope中未知项也用null占位或省略该元素，保持数组语义清晰）。 metrics写法：尽量使用数据分析问题中已存在的标准指标名（如DAU/对话用户数/次日访问留存率），不要用自由发挥的同义改写，以免造成歧义，导致后续步骤理解出错。
例如，对于用户输入问题「5月 app端某模型对话用户数，人均对话次数和点赞率分别是多少？」，可解析出如下信息：
{
"question": "5月 app端某模型对话用户数，人均对话次数和点赞率分别是多少？",
"domain": "产品A",
"metrics": ["对话用户数", "人均对话次数", "点赞率"],
"intention": "查询5月app端某模型的三个指标值：对话用户数、人均对话次数和点赞率",
"scope": [
"5月",
"app端",
"某模型"
]
}
Step 2. 业务数据信息补全
将 Step 1 的结构化问题作为输入，从可用知识源补全取数所需的业务语义。本步骤的产物全部落盘到 {workdir}/data/raw/。
What ships with it
7 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.
- 1mo ago First seen · 286 lines · 276 tokens per session scan A dcd21e059dbf
fetch-data is a skill published in the GitHub repository agentscope-ai/QwenPaw-Data (166 stars, last pushed 2d ago), licensed Apache-2.0. It adds 276 tokens to every session and 5,635 once invoked, about $0.0011 per session on Opus 5.5. 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
stripe-projects
Use when the user wants to provision infrastructure or third-party services using Stripe Projects. Triggers: "I need a database", "set up auth", "add caching", "give me a Postgres", "provision Redis", "I need hosting", "add a vector DB", "get me an API key for X", "get credentials for X", "sign up for a service", "set…
alembic-migration
Create, review, and apply database schema changes with Alembic. Use whenever a SQLAlchemy model is added or changed, a column/index/constraint needs to change, or a data backfill is required — anything that alters the PostgreSQL schema.
knowledge_graph_skill
Skill for searching and evolving the SQLite-backed Knowledge Graph. Use this when you need structured fact/concept/link search across one or more teams, NPCs, or directory scopes. The Knowledge Graph (KG) is stored in the application's database (not YAML). It is scoped by (teamname, npcname, directorypath). Facts and…
tageszeitung
Creates a personalised daily newspaper from RSS feeds and web sources. Ported from the BACH news system (news.py + newspapergenerator.py). Own SQLite store (no Origin-DB). feedparser optional — XML fallback via stdlib. PDF export via Edge Headless (msedge.exe).
claude-memory
Access the persistent memory database (PostgreSQL claudememory) for long-term context across Claude Code sessions. Triggers on "what do I know about", "memory lookup", "recall", "memory db", "what did we decide about", "similar conversations", "lookup context", "/memory". Provides semantic search, SQL queries and the…
nextcloud-ingest
Natively ingest Nextcloud files into the epistemic-graph knowledge graph via the nextcloud-agent MCP server — fetch a file over WebDAV and store its raw bytes as a content-addressed :Blob/:AssetOccurrence plus its extracted text (pdf/office/txt or image OCR) as a linked :Document. Use when the agent must make a…