一键在 Manus 中运行任何 Skill

data

Data analysis skill hub. Routes to the right specialist subskill depending on the request — exploration, query writing, end-to-end analysis, visualization, validation, dashboard planning plus assembly, or recurring snapshot refresh.

在 Manus 中运行

概览

安装命令

npx skills add https://github.com/plc1220/HelpUDoc --skill data

复制此命令并粘贴到 Claude Code 中以安装该技能

来源

plc1220/HelpUDoc

星标10

分支1

更新时间2026年5月25日 18:54

文件资源管理器

8 个文件

SKILL.md

readonly

name	data
description	Data analysis skill hub. Routes to the right specialist subskill depending on the request — exploration, query writing, end-to-end analysis, visualization, validation, dashboard planning plus assembly, or recurring snapshot refresh.
tools	["data_agent_tools","get_table_schema","run_sql_query","materialize_bigquery_to_parquet","export_sql_query","generate_summary","generate_dashboard"]
mcp_servers	["toolbox-bq-demo"]

data — Skill Hub

This hub describes when to use each subskill in the data/ family. Load the most specific subskill that matches the request; fall back to data/analyze for general analysis tasks.

Subskill routing

Request type	Load skill
"What tables / columns / data do I have?"	`data/explore`
"Write me a SQL query to…"	`data/query`
"Analyze / what's happening with…" (general)	`data/analyze`
"Chart / visualize this…"	`data/visualize`
"Check / validate this analysis before I share it"	`data/validate`
"Build me a dashboard"	`data/dashboard`
"Refresh this every day / keep this report in sync"	`data/refresh`

Connector selection (apply in every subskill)

Choose the right data connector for the source:

Warehouse (managed datasets, large tables) — use the BigQuery MCP server (toolbox-bq-demo) for discovery and the initial scoped query. If the task will require iterative follow-up analysis, materialize the scoped result with materialize_bigquery_to_parquet and continue in DuckDB. Treat BigQuery as the system of record and DuckDB over workspace snapshots as the local serving layer.
Local files (CSV / Parquet in the workspace) — use data_agent_tools. Available tools: get_table_schema, run_sql_query, materialize_bigquery_to_parquet, generate_summary, generate_dashboard.
Recurring dashboards / canned reports — use data/refresh to publish a stable snapshot such as datasets/<slug>/latest.parquet, optionally mirror it to CSV, and regenerate a stable HTML artifact in dashboards/ or reports/.
Dashboard creation — data/dashboard is review-first. It should inspect the tagged dataset/report context, propose a dashboard plan, wait for approval, then generate the dashboard package.
Do not attempt cross-source SQL joins in v1. Orchestrate at the workflow level (query each source separately; combine in Python / summary prose).

Guardrails that apply to every subskill

Inspect schema / metadata before executing SQL.
Always cite concrete numbers (counts, averages, %, deltas). No speculation.
Maximum 10 SQL queries per run (enforced in code).
Maximum 5 charts per run (enforced in code).
One generate_summary OR one generate_dashboard per run.
Reports and dashboards only include artifacts from the current run — never from prior runs.
Dashboard requests should prefer a tagged dataset artifact as the source of truth and avoid fresh warehouse rediscovery unless the tagged inputs are unusable.
In data/dashboard, prefer structured chart bindings over generate_chart_config on the main path.

同仓库更多 Skills

同仓库

frontend-slides

plc1220/HelpUDoc

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

2026-06-0410

xlsx

plc1220/HelpUDoc

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

2026-06-0210

pptx

plc1220/HelpUDoc

Handle slide decks and PowerPoint files cautiously; avoid binary reads, prefer companion PDFs or outlines for analysis, and be explicit about PPTX parsing limits.

2026-05-2910

data-dashboard

plc1220/HelpUDoc

Plan, review, and then assemble a stakeholder-ready dashboard package from the current analysis run, with a native interactive canvas experience.

2026-05-2510

sheets

plc1220/HelpUDoc

Handle spreadsheets and tabular files safely; use text reads only for text tables and avoid treating Excel or Parquet binaries as UTF-8 files.

2026-05-2510

research

plc1220/HelpUDoc

Produce a sourced research report in the user's language using a structured, evidence-first workflow. Supports quick, standard, deep, and exhaustive research modes. Prioritizes evidence quality, entity disambiguation, claim verification, contradiction checking, uncertainty handling, and clear synthesis before final writing.

2026-05-1110

来源

plc1220

plc1220/HelpUDoc

打开 GitHub 仓库查看创作者相关仓库

安装命令

下载

在 Manus 中运行

适用职业SOC

软件开发工程师计算机与数学类职业15-1252L4

name	data
description	Data analysis skill hub. Routes to the right specialist subskill depending on the request — exploration, query writing, end-to-end analysis, visualization, validation, dashboard planning plus assembly, or recurring snapshot refresh.
tools	["data_agent_tools","get_table_schema","run_sql_query","materialize_bigquery_to_parquet","export_sql_query","generate_summary","generate_dashboard"]
mcp_servers	["toolbox-bq-demo"]

data — Skill Hub

This hub describes when to use each subskill in the data/ family. Load the most specific subskill that matches the request; fall back to data/analyze for general analysis tasks.

Subskill routing

Request type	Load skill
"What tables / columns / data do I have?"	`data/explore`
"Write me a SQL query to…"	`data/query`
"Analyze / what's happening with…" (general)	`data/analyze`
"Chart / visualize this…"	`data/visualize`
"Check / validate this analysis before I share it"	`data/validate`
"Build me a dashboard"	`data/dashboard`
"Refresh this every day / keep this report in sync"	`data/refresh`

Connector selection (apply in every subskill)

Choose the right data connector for the source:

Warehouse (managed datasets, large tables) — use the BigQuery MCP server (toolbox-bq-demo) for discovery and the initial scoped query. If the task will require iterative follow-up analysis, materialize the scoped result with materialize_bigquery_to_parquet and continue in DuckDB. Treat BigQuery as the system of record and DuckDB over workspace snapshots as the local serving layer.
Local files (CSV / Parquet in the workspace) — use data_agent_tools. Available tools: get_table_schema, run_sql_query, materialize_bigquery_to_parquet, generate_summary, generate_dashboard.
Recurring dashboards / canned reports — use data/refresh to publish a stable snapshot such as datasets/<slug>/latest.parquet, optionally mirror it to CSV, and regenerate a stable HTML artifact in dashboards/ or reports/.
Dashboard creation — data/dashboard is review-first. It should inspect the tagged dataset/report context, propose a dashboard plan, wait for approval, then generate the dashboard package.
Do not attempt cross-source SQL joins in v1. Orchestrate at the workflow level (query each source separately; combine in Python / summary prose).

Guardrails that apply to every subskill

Inspect schema / metadata before executing SQL.
Always cite concrete numbers (counts, averages, %, deltas). No speculation.
Maximum 10 SQL queries per run (enforced in code).
Maximum 5 charts per run (enforced in code).
One generate_summary OR one generate_dashboard per run.
Reports and dashboards only include artifacts from the current run — never from prior runs.
Dashboard requests should prefer a tagged dataset artifact as the source of truth and avoid fresh warehouse rediscovery unless the tagged inputs are unusable.
In data/dashboard, prefer structured chart bindings over generate_chart_config on the main path.