tunoc2c/workbuddy-experts/databrain-analysis
- community
Checking that the SKILL.md file is still in the repository.
Before execute_e2b_code for attribution, drill-down, or statistical tests, read this SKILL.md then drilldown.md and/or statistical/SKILL.md plus needed references. Does not fetch data.
Install
npx vskill@latest install tunoc2c/workbuddy-experts/databrain-analysisSKILL.md
The same SKILL.md was published earlier as infometa/workbuddyskills/databrain-analysis.
DataBrain Analysis (sandbox)
在 E2B sandbox 里做归因下钻或统计推断。不拉数;先经 databrain-dashboard-service / databrain-intelligence / opinion skills 取数,再分析。
闸门(分析代码前)
用 read_file 读引用文件,再 open_e2b_code_sandbox / upload_to_e2b_code_sandbox / execute_e2b_code。凭记忆写分析代码不算完成。
| 任务类型 | 何时 | 必读 | |
|---|---|---|---|
| 归因 / 下钻 / 驱动因素 | 贡献度、谁导致变化、多维拆解 | 本文件 + `drilldown.md` | |
| 统计检验 / 建模 | A/B、显著性、回归、时序 | 本文件 + `statistical/SKILL.md` + 按需 statistical/references/<name>.md | |
| 两者都要 | 先归因定位再对子集做检验 | 先 drilldown,再 statistical |
未完成闸门:未读对应 md 已 execute_e2b_code 长段分析脚本。
数据进 sandbox
- 优先:取数工具返回的 CSV / 本地路径(
run_skill_script写入/outputs/...或工具说明中的路径)→upload_to_e2b_code_sandbox(local_path=...)→ sandbox 内pd.read_csv(...)。 - `data_id`:若工具结果含
data_id且附完整 CSV 路径,上传该文件;勿编造文件名。 - `/large_tool_results/` spill:当工具返回
Tool result too large且路径为/large_tool_results/toolu_xxx时,先按soul.md§7 尝试 收窄重查;若分析任务需要保留宽表/全量行且收窄会丢维度,则 `upload_to_e2b_code_sandbox(local_path=/large_tool_results/...)`(或execute_e2b_code引用该路径并由宿主自动 staging)后在 sandbox 内解析。不要用read_file整文件塞进上下文;不要在无databrain-analysis闸门时为简单问答默认走 sandbox。 - 包安装:分析前如需
pandas scipy statsmodels,先execute_e2b_codelanguage=bash:pip install pandas scipy statsmodels(勿用!pip)。
执行纪律(react)
execute_e2b_code:短脚本 — 安装依赖 → 读表 →print()表与结论;禁止plt.savefig/ 出图(图表由 `databrain-chart-render` 的scripts/build_chart.py:<dbd>/ echarts_option)。- stdout 即证据:关键统计量、归因表、
ATTRIBUTION_TABLE风格列须print;终稿由 `databrain-summarize` 合成(含 `report.md` 若 §0.2)。 - 同一 query 内 sandbox 复用;分析结束可
close_e2b_code_sandbox(可选)。 - 工具连续失败 ≥3 次:停止分析,向用户说明原因(
soul.md)。
引用文件
| 文件 | 内容 | |
|---|---|---|
| `drilldown.md` | cumulative_joint、30% 规则、directional/L1、归因结论 | |
| `statistical/SKILL.md` | 选型表、workflow | |
| `statistical/references/` | data_cleaning, stat-t-test, experimental_design, … | |
| `../databrain-summarize/report.md` | 终稿如何呈现检验/归因(summarize 阶段) |
无 run_skill_script(分析逻辑在 sandbox 内手写 Python,可参考 references 中的代码模式)。
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/databrain-agent-v2/skills/databrain-analysis/SKILL.md
Popularity
- Repository stars
- 1
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/tunoc2c/workbuddy-experts/databrain-analysis)