Evolving The Data Model
TriliumNext/Trilium
A skill your agent uses when adding a DB migration or a new column/field to a Becca entity in Trilium ("add a migration", "new column on notes/attributes", "ALTER TABLE", "add a field to…
取数 / 查数据 / 拉数据 / 跑 SQL。把自然语言取数需求转为 SQL,经数据湖仓执行后返回查询结果供下游分析。任何需要业务数据的任务在工作区缺少对应文件时都必须先调用此技能——覆盖 BI 业务分析、留存 / 转化 / 同期群分析、数据探索 EDA、统计建模、定量计算、元数据查询、数据查询。命中任一即触发:(1) 直接索要指标或记录,如「DAU 多少」「上月销售额」「3…
$ npx skills add agentscope-ai/QwenPaw-Data --skill fetch-data -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install agentscope-ai/QwenPaw-Data fetch-data --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/workflows/fetch-data .claude/skills/fetch-data && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "fetch-data" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/workflows/fetch-data into .claude/skills/fetch-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fetch-data", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/workflows/fetch-dataType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add agentscope-ai/QwenPaw-Data --skill fetch-data -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install agentscope-ai/QwenPaw-Data fetch-data --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/workflows/fetch-data .agents/skills/fetch-data && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "fetch-data" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/workflows/fetch-data into .agents/skills/fetch-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fetch-data", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agentscope-ai/QwenPaw-Data --skill fetch-data -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install agentscope-ai/QwenPaw-Data fetch-data --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/workflows/fetch-data .cursor/skills/fetch-data && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "fetch-data" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/workflows/fetch-data into .cursor/skills/fetch-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fetch-data", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/agentscope-ai/QwenPaw-Data.git --path packages/qwenpaw-data-skills/skills/workflows/fetch-data--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add agentscope-ai/QwenPaw-Data --skill fetch-data -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install agentscope-ai/QwenPaw-Data fetch-data --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/workflows/fetch-data .gemini/skills/fetch-data && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "fetch-data" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/workflows/fetch-data into .gemini/skills/fetch-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fetch-data", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install agentscope-ai/QwenPaw-Data fetch-dataInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add agentscope-ai/QwenPaw-Data --skill fetch-data -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/workflows/fetch-data .github/skills/fetch-data && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "fetch-data" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/workflows/fetch-data into .github/skills/fetch-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fetch-data", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agentscope-ai/QwenPaw-Data --skill fetch-data -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install agentscope-ai/QwenPaw-Data fetch-data --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/workflows/fetch-data .opencode/skills/fetch-data && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "fetch-data" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/workflows/fetch-data into .opencode/skills/fetch-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fetch-data", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
fetch-data取数 / 查数据 / 拉数据 / 跑 SQL。把自然语言取数需求转为 SQL,经数据湖仓执行后返回查询结果供下游分析。任何需要业务数据的任务在工作区缺少对应文件时都必须先调用此技能——覆盖 BI 业务分析、留存 / 转化 / 同期群分析、数据探索 EDA、统计建模、定量计算、元数据查询、数据查询。命中任一即触发:(1) 直接索要指标或记录,如「DAU 多少」「上月销售额」「3…
Fetch Data is an agent skill from agentscope-ai/QwenPaw-Data. 取数 / 查数据 / 拉数据 / 跑 SQL。把自然语言取数需求转为 SQL,经数据湖仓执行后返回查询结果供下游分析。任何需要业务数据的任务在工作区缺少对应文件时都必须先调用此技能——覆盖 BI 业务分析、留存 / 转化 / 同期群分析、数据探索 EDA、统计建模、定量计算、元数据查询、数据查询。命中任一即触发:(1) 直接索要指标或记录,如「DAU 多少」「上月销售额」「3 月留存率」「这个客户的订单」;(2) 取数口语,如「查 / 查一下 / 取一下 / 拉一下 / 抓数据 / 找数据 / 搜数据 / 跑 SQL / 写 SQL / 导出 / 缺数据 / 没数据 / 数据不够」;(3) 涉及数据来源,如「从语义层 / 数据湖仓 / 仓库 / 数据库取」;(4) 问元数据 / 口径,如「字段含义 / 表结构 / 这两张表怎么关联 / 可用数据源 / 指标怎么算」;(5) 下游任务在工作区找不到所需数据。
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts and reference files (for example `prompts/nl2sql.md`, `references/data_source_ambiguity.md` and `references/intent_ambiguity.md`).
It sits in Databases, covering SQL. It works with SQL. The repository describes itself as: Agentic enterprise data analytics: governed facts (DataBridge), reusable methodology (Skill-Hub), and controllable execution (Host). The licence is Apache-2.0.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e0bae36. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Fetch Data loads about 2.5k tokens when it runs, and up to ~5.4k if it reads all its reference files. Until then it costs about 106 tokens; SKILL.md has 615 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from agentscope-ai/QwenPaw-Data at commit e0bae36, republished under its Apache-2.0 licence (© agentscope-ai). 615 words, ~2,506 tokens.
.claude/skills/fetch-data/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.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。
{workdir} 是否已包含全部所需分析数据: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
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"] |
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"
]
}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/。
知识源优先级(Step 2.1 和 Step 2.2 都遵循):
- 语义层——首选。语义层维护了被业务方校准过的指标 / 维度 / 表语义,结果可直接使用。
- 数据湖仓元数据——语义层缺失或不可用时回退。数据湖仓元数据提供的是表 / 列级别的物理事实(表名、列名、dtype、注释),用它补全 Step 2.2 的字段;对于 Step 2.1 的指标语义,需自行结合列注释 / 命名推断。
- 上下文信息(如对话历史、用户先前提供的口径说明等)——仅当上述两者都拿不到时才允许使用,并且必须满足下面两条硬约束:
- 精确对应:上下文里出现的指标名 / 表名 / 列名必须与本次要探查的目标完全一致(同名同义、口径一致),不允许拿"看起来差不多"的旧上下文凑数;
- 来源标注:在落盘的 JSON 中,每个来自上下文的字段都要在产物文件里以注释 / 同级
source: "context"字段或同名旁注的方式显式标出,便于 Step 3 复核。任一字段若三个来源都拿不到,按"留空"处理,不得用模型先验或想象填充。
针对 Step 1 中的关键指标,按上述优先级查询其业务定义与计算口径。若 Step 1 中没有成功获取明确的意向指标,则将分析意图作为指标名进行查询。若分析意图也不存在,则回退使用原问题进行查询。
本步骤所需探查到的信息(每个关键指标至少应得到如下关键字段):
{
"metrics": [ # 查询中所需的指标
{
"metric_name": "<指标1名称>", # 语义层中存储的标准指标名
"synonyms": [ # 指标的同义词
"<同义词1>",
"<同义词2>"
],
"metric_type": "<指标类型>", # 指标的类型,如 "quantity" / "ratio" / "percentage"
"is_north_star": true, # 是否是北极星指标
"is_display": true, # 是否在数据分析中展示
"formulas": [
{
"dataset": "<数据表名1>", # 能够支持指标计算的数据表
"formula": "<指标计算方式>" # 在该数据表中,该指标计算方式
},
{
"dataset": "<数据表名2>",
"formula": "<指标计算方式>"
}
]
}
]
}把获取到的指标信息落盘到 {workdir}/data/raw/,不遗漏任何探查到的字段信息;若不存在的字段信息,则补充为空,不可捏造不存在的信息。
针对 Step 2.1 中所有数据表,按上述优先级查询表与列级别的元信息。
本步骤所需探查到的信息(每张数据表至少应得到如下关键字段):
[
{
"table_name": "<table name>", # 查询相关的表名
"description": "<description of the table>", # 表的描述
"columns": [ # 表中列的元信息
{
"column_name": "<column name>", # 列名
"dtype": "<type of data>", # 列中值的类型
"description": "<description of the column>", # 列的描述
"topline_value": "<topline value for the volumn>", # 列的 topline 值
"sample_values": "<samples from the column>" # 列中的采样数值
}
]
}
]注意:
sample_values 仅提供部分采样数值,用于辅助理解列的含义,并非精确取值,请查看实际取值时以实际数据为准。把获取到的数据表的完整表元数据信息落盘到 {workdir}/data/raw/。
完成指标 / 表元数据补全后,回头检查 Step 1 结构化问题产物中的 domain 字段。domain 必须唯一确定且非空才能进入后续步骤。
逐项核对:
domain 不是 null / 空串 / 占位符。domain 取值唯一,没有出现"多个业务域并存 / 取值含糊"的情况。可借助 Step 2 探查到的指标 / 表元数据(如表名前缀、schema.json 中各表的 domain 标注)反向印证结构化问题里的 domain 是否自洽。按校验结果处理:
domain 不一致,按"取值含糊"处理(见下)。domain 字段,并在回复正文中记录该补充。不要替用户臆测 domain。domain。domain 校验通过是进入后续步骤的前置条件;
domain仍为空时不得继续往下走。
Step 2 完成后,先停下来对照原始问题与新得到的指标信息 / 表元数据核一遍:用户的指标 / 维度 / 时间口径在补全后的数据语义里是否还存在多解或其他理解偏差。有歧义就先消除,再进入 Step 4。本过程严格遵循搜索到的数据,不可捏造不存在的信息。
输入:Step 1 的结构化问题 + Step 2.1 的指标信息 + Step 2.2 的表元数据 + 原始问题 产物:
{workdir}/steps/ 下的结构化问题产物:把模糊词替换成确认后的标准 metric_name / <列名>=<值> 形式(改写的原值 / 新值在回复正文中说明)常见分析意图歧义模式与解决方案:参见 references/intent_ambiguity.md。逐项检查:
用结构化问题中 metrics 里的每一项分析指标去和 Step 2.1 探查到的指标信息中的可用指标对比。若多条指标可对应同一分析指标(如“留存率”同时命中“访问留存率”、“使用留存率”)→ 有歧义。
metric_name 写回 Step 1 的结构化问题产物。metric_name 是否已存在于 Step 2.1 现有产物中;若不存在(改名 / 切换到新指标),则按 Step 2.1 的指标信息补全步骤重新执行指标信息补全(并按 Step 2.2 补齐新指标所需的表元数据),详见 Step 3.3 的联动说明。对每个已能对齐到标准 metric_name 的指标,检查 Step 2.1 现有产物中是否存在某个 metric_name 所需聚合粒度不明(如“一段时间的对话用户数”同时命中“日均对话用户数”“时段总和对话用户数”),且原始问题未明确选择哪一种 → 有歧义。
references/intent_ambiguity.md 章节 2 中的默认解决方案。常见数据来源歧义模式与解决方案:参见 references/data_source_ambiguity.md。逐项检查:
数据中多个数据表在指标计算、数据维度选择等都满足数据分析需求。例如,分析“计算某产品不同端 dau 指标”,表 xxx_index 和 xxx_distribution 都包含可用于计算 dau 指标都数据,且包含指向不同端的字段,即两张表都可用于数据分析。
references/data_source_ambiguity.md 章节 1 中的解决方法。数据中多个维度可用于数据筛选。例如,分析“文本对话的点赞率”,“对话模式”和“对话类型”两个维度都包含“文本对话”的维度取值。用结构化问题中 scope 里每一项数据维度去和 Step 2.2 探查到的表元数据中的可用维度对比。若多列都能取到该值(如“文本对话”既在 dialog_mode 也在 dialog_type 里出现)→ 有歧义。
上述只是最常见的情况,遇到其他模糊(如时间口径——“近 30 天”含不含今天、“上月”按自然月还是滚动 30 天;如统计口径——“用户数”是
visit_usercnt还是visit_login_usercnt)也要在本步骤一并提出。
无论是否触发消歧,都要在回复正文中说明以下内容:
metric_name / formula>留存率 → 访问留存率;对话用户数 → 日均对话用户数(按默认);文本对话 → dialog_mode=文本对话)联动:出现下列任一情况,都意味着 Step 2 的指标信息 / 表元数据可能缺失对应元数据 → 回到 Step 2 重新拉,再进入 Step 4:
- 消歧后写回的
metric_name未出现在 Step 2.1 现有产物中(无论是改名、新增还是切换聚合粒度);- 消歧后选定的数据表(组合)未出现在 Step 2.2 现有产物中,或其在 Step 2.1 指标
formulas里缺少对应dataset的计算口径(换表 / 新增表场景)。若写回的
metric_name已存在于 Step 2.1 现有产物中(包括 1.2 聚合粒度消歧切到同一指标的另一个聚合粒度版本),且选定数据表的元数据与指标口径均已齐备,则无需重跑 Step 2。
使用 {skill-dir}/scripts/generate_nl2sql_prompt.py 将 Step 2 探查到的指标信息和表元数据信息渲染成 NL2SQL prompt,落盘到 {workdir}/steps/:
python {skill-dir}/scripts/generate_nl2sql_prompt.py \
--problem <{workdir}/steps/ 下 Step 1 结构化问题产物路径> \
--metrics <{workdir}/data/raw/ 下 Step 2.1 指标信息产物路径> \
--schema <{workdir}/data/raw/ 下 Step 2.2 表元数据产物路径> \
--output <{workdir}/steps/ 下的输出路径>参数说明
| 参数 | 含义 | 默认值 |
|---|---|---|
--problem | 问题结构化 JSON 路径(Step 1 的产物,位于 {workdir}/steps/;Step 3 可能就地改写过) | 必填 |
--metrics | 关键分析指标信息 JSON 路径(Step 2.1 的产物,位于 {workdir}/data/raw/) | 必填 |
--schema | 相关数据表元数据信息 JSON 路径(Step 2.2 的产物,位于 {workdir}/data/raw/) | 必填 |
--output | NL2SQL prompt 输出路径(须位于 {workdir}/steps/ 下) | 必填 |
{workdir}/steps/ 下产出的 NL2SQL prompt 的完整内容,不允许对其内容做更改。references/partition-query.md 中的分区与查询策略,根据表后缀确定分区字段和 WHERE 写法,结合表类型确定查询范围。SELECT。sql 代码围栏、Markdown 注释、解释段),保存到 {workdir}/steps/ 下(以 ; 结尾)。通过数据湖仓执行 Step 5 产出的 SQL。执行结果按下述规则处理:
scope(特别是日期)/ metrics 是否对齐;error 信息透传回去做迭代:SQL 语法 / 列不存在 / 类型不匹配等 → 回到 Step 5;表 / 列名查不到 → 回到 Step 2 重新拉表元数据。不要绕过数据湖仓的标准执行通道(如改走 shell / psql 自行取数),那样拿到的结果既不可复现也无法被评测器审计。© agentscope-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 7 other files (scripts, references) in packages/qwenpaw-data-skills/skills/workflows/fetch-data of agentscope-ai/QwenPaw-Data.
Open the folder on GitHubat commit e0bae36
Fetch Data next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Fetch Data this skillagentscope-ai/QwenPaw-Data | 113 | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | |
| Evolving The Data ModelTriliumNext/Trilium | 38k | — | ~2.1k | Automated safety check: Pass | AGPL-3.0 | |
| Orchardcore Data MigrationOrchardCMS/OrchardCore | 8.2k | — | ~1.7k | Automated safety check: Pass | BSD-3-Clause | |
| SQL Optimization Patternsynulihao/AgentSkillOS | 617 | 11 repos | ~3.3k | Automated safety check: Pass | None | |
| SQL PortabilityHL7/sql-on-fhir | 150 | — | ~512 | Automated safety check: Pass | Custom licence | |
| StmoSAP/project-foxhound | 180 | 2 repos | ~1.8k | Automated safety check: Pass | GPL-3.0 |
TriliumNext/Trilium
A skill your agent uses when adding a DB migration or a new column/field to a Becca entity in Trilium ("add a migration", "new column on notes/attributes", "ALTER TABLE", "add a field to…
OrchardCMS/OrchardCore
Creates and updates OrchardCore data migrations (DataMigration classes with CreateAsync/UpdateFromX).
ynulihao/AgentSkillOS
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries.
HL7/sql-on-fhir
Analyse whether a SQL query is portable across database implementations using sqlglot transpilation.
SAP/project-foxhound
Manage Redash queries and dashboards on Mozilla's STMO (sql.telemetry.mozilla.org) using stmo-cli.
kurealnum/dotfiles
A skill your agent uses when generating or regenerating Drizzle migration files, changing database schema tables or columns, resolving migration sequence conflicts after rebase, reviewing migration…
agentscope-ai/QwenPaw-Data
将 BI 数据分析结果组织成可视化 HTML 报告。当分析完成、需要生成报告时调用. An agent skill from agentscope-ai/QwenPaw-Data.
agentscope-ai/QwenPaw-Data
通过量化历史数据的自然波动幅度,自适应计算判定阈值。当需要从数据本身确定阈值(如波动阈值、影响度阈值等)、而非使用固定值时调用。仅适用于日/周粒度阈值确定。
agentscope-ai/QwenPaw-Data
基于阈值检测时间序列中的显著异常波动点。当需要找出指标异常波动日期、识别数据异动时调用. An agent skill from agentscope-ai/QwenPaw-Data.
agentscope-ai/QwenPaw-Data
计算各维度(组)值对指标变动的贡献度,支持可加型量值指标和加权平均型/率值指标。当需要计算贡献度、解释指标"为什么涨/跌"时调用。
agentscope-ai/QwenPaw-Data
从运营周报、活动文档、对话输入或文档工具 API 中提取业务事件,与指标异常时间窗口对齐,生成有证据支撑的因果归因假设并排序。当已知指标存在异常波动、需要从外部文档证据中解释"为什么"时调用。
agentscope-ai/QwenPaw-Data
对用户、产品等业务对象做分群:用波士顿矩阵法做象限分群,或用分层聚类、K-means、DBSCAN 等聚类技术分群。当需要做客群/产品分群、象限策略、画像或密度型子结构发现时调用。触发条件:当对话中出现“分群”、“分类”、“聚类”、“不同类型”、“不同场景”等体现分群分析词语时触发。
Works with
Categories
取数 / 查数据 / 拉数据 / 跑 SQL。把自然语言取数需求转为 SQL,经数据湖仓执行后返回查询结果供下游分析。任何需要业务数据的任务在工作区缺少对应文件时都必须先调用此技能——覆盖 BI 业务分析、留存 / 转化 / 同期群分析、数据探索 EDA、统计建模、定量计算、元数据查询、数据查询。命中任一即触发:(1) 直接索要指标或记录,如「DAU 多少」「上月销售额」「3…. Fetch Data is an agent skill from agentscope-ai/QwenPaw-Data.
Fetch Data fits situations like: tasks that involve SQL.
Run `npx skills add agentscope-ai/QwenPaw-Data --skill fetch-data -a claude-code`. Or copy the skill folder (packages/qwenpaw-data-skills/skills/workflows/fetch-data in agentscope-ai/QwenPaw-Data) into .claude/skills/fetch-data in your project. Claude Code loads it when a task matches its description.
Run `npx skills add agentscope-ai/QwenPaw-Data --skill fetch-data -a codex`. Or copy the skill folder (packages/qwenpaw-data-skills/skills/workflows/fetch-data in agentscope-ai/QwenPaw-Data) into .agents/skills/fetch-data in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agentscope-ai/QwenPaw-Data --skill fetch-data -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fetch-data, .gemini/skills/fetch-data, .github/skills/fetch-data and .opencode/skills/fetch-data in your project.
Going by SKILL.md and its folder, Fetch Data needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Fetch Data is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.9k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Fetch Data: Evolving The Data Model (TriliumNext/Trilium, 38k stars), Orchardcore Data Migration (OrchardCMS/OrchardCore, 8.2k stars), SQL Optimization Patterns (ynulihao/AgentSkillOS, 617 stars) and SQL Portability (HL7/sql-on-fhir, 150 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
agentscope-ai (a GitHub organization) maintains it in agentscope-ai/QwenPaw-Data, which has 113 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 5, 2026.
Source: agentscope-ai/QwenPaw-Data on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.