Data Analysis Quality Gate

Data Analysis Quality Gate is an AI Engineering skill for Claude Code, published by byteseek in Mira.

262 stars45 forkson byteseek/MiraAdded 2026/09/02+1% in starsRepository updated 2026/07/05

agent-workflowai-agentsclaude-codecodexdecision-logearnings-analysisequity-researchevidence-logfinancial-researchinvestment-researchmacro-analysismarket-researchportfolio-managementresearch-workflowsource-trackingthesis-tracking

Install in seconds

Install Data Analysis Quality Gate

Copy Data Analysis Quality Gate into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/byteseek/Mira/tree/main/skills/data-analysis-quality-gate ~/.claude/skills/data-analysis-quality-gate

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/byteseek/Mira.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/data-analysis-quality-gate/SKILL.md in byteseek/Mira
Installs to: ~/.claude/skills/data-analysis-quality-gate
Collection: One of 10 skills cataloged from this repository
Category: AI Engineering — 2631 skills

What Data Analysis Quality Gate does

Data Analysis Quality Gate requires reproducible inputs, formulas, and calculation ledgers for quantitative Mira conclusions. Use it when numbers affect thesis, actionability, or scenario judgments, and downgrade unsupported claims.

Data Analysis Quality Gate is cataloged under AI Engineering on DirSkills. Data Analysis Quality Gate comes from a repository tagged agent-workflow, ai-agents, claude-code, codex and decision-log.

Documentation

README

Excerpt

Data Analysis Quality Gate

这个 skill 用于在 Mira 研究中判断数量型结论是否需要可复算数据、工具计算或显式降级。

它不是一个独立数据分析插件，也不绑定 Data Analytics、Python、Spreadsheet 或外部 API。它的职责是把 LLM 从“直接给数字结论”约束为：

先提出数据需求
再判断是否必须计算
决定是否需要征求用户同意动用工具
记录公式、口径、来源和限制
对没有完成计算的数量型结论降级

Use When

当研究结论涉及以下任一内容时，必须进入本 gate，或明确写明 waived reason：

同比、环比、CAGR、run-rate、margin bridge
peer comparison、peer ranking、相对估值、相对财务质量
valuation implied expectation、base / bull / bear scenario math
市场规模、渗透率、份额、TAM / SAM / SOM
三表交叉校验、现金流质量、营运资本异常
宏观、商品、价格、库存、利率、就业或通胀时间序列
多来源数字冲突或口径不一致
任何会影响 thesis_impact、research_action、actionability_bridge 或 durable conclusion 的数量判断

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Data Analysis Quality Gate

What else does byteseek publish alongside Data Analysis Quality Gate?
Data Analysis Quality Gate is one of 10 skills that DirSkills catalogs from byteseek/Mira, the repository it ships in. Its siblings there include Commodity Cycle Analysis, ETF Listing Analysis and ETF Listing Discovery. Each one is a separate skill with its own page in this directory, installs the same way Data Analysis Quality Gate does, and is maintained by byteseek in that same repository. The rest of the collection is listed on the byteseek/Mira page.
How does Data Analysis Quality Gate compare to other AI Engineering skills?
Data Analysis Quality Gate ranks #2258 by stars among the 2631 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Data Analysis Quality Gate against them. Open each page to compare what they document and how they install.