Data & Analytics

infometa Skill

This is the required documentation for agents operating on the CloudBase Relational Database through MCP. It defines the canonical SQL management flow with `querySqlDatabase`, `manageSqlDatabase`, `readSecurityRule`, and `writeSecurityRule`, including MySQL provisioning, destroy flow, async status checks, safe query execution, schema initialization, and security rule updates.

infometa Bundle

Review contracts for risk (scenarios C5/C6) — background assessment before signing (counterparty qualification, transaction-mode legality, contract-form fit, special procedures) and clause-by-clause review of a provided contract. Use this skill after the user's standpoint (Party A/B/neutral, strong/weak) is confirmed via intake. Runs an eight-step per-rule action (locate→extract→compare→judge→self-check→grade→legal-basis→suggest), grades risk via an impact×probability matrix into three tiers (high/medium/hint), and applies built-in Formal-Review and General-Substantive playbooks (or the user's playbook with priority). Produces a structured risk list (risk level, description, legal basis, remediation suggestion); optionally a redlined .docx, a review opinion, or — in professional review mode — three deliverables (Excel + Markdown report + Word annotations).

infometa Bundle

Use when the user works with AI-Shifu (AI师傅) courses in any capacity of creating, writing, editing, rewriting, optimizing, reordering, deploying, publishing, previewing, or managing Teaching Prompts (per-lesson) and Course Prompts (course-level) — both written in MarkdownFlow (MDF). Covers the full course lifecycle — from converting raw material into structured lessons, to scripting interactions (single-select, multi-select, input, branching), adding variables, images, and course prompts, to deploying and managing live courses on the AI-Shifu platform. Also covers post-deployment analytics on those courses — learner count, completion rate, stuck lessons, orders, revenue, ratings, credit consumption, audience profiles, and individual learner tracking. Trigger on any mention of AI-Shifu, AI师傅, MarkdownFlow, Teaching Prompt, Course Prompt authoring, course analytics, creator analytics, 学习人数, 完成率, 卡课节, 订单收入, 积分消耗, or learner progress.

infometa Bundle

DataBrain intelligence data query assistant. Translates natural language questions into executable BigQuery SQL for the intelligence domain: market data (Sensortower, Alinea Analytics [Steam raw default], MScience, GSD, Ampere, NPD; Gamalytic legacy), streaming data (Streamhatchet), Steam live CCU (fetch_steam_ccu.py + warehouse spider/Alinea), Roblox CCU rankings & anomaly detection, mini game rankings (微信/抖音/Facebook小游戏榜单), report metadata (external & internal research reports), platform coverage statistics, MobyGames credits, news data, upcoming/未上线 game queries (Alinea live signals + combined_detail.release_date fuzzy-date normalization), game ID lookups (unified_id / combined_id), benchmark / 对标 queries (industry median, top 1%, peer ranking from benchmark.benchmark_detail), and mobile game audience overlap / affinity queries (Sensortower App Overlap). Trigger keywords: intelligence, 情报游戏数据, overlap, affinity, 受众重叠, 重叠度, 亲和力, 亲密度, 共同用户

infometa Skill

轻流图表与门户深度集成——在轻流中搭建人力分析看板，覆盖人员结构、流失率、招聘漏斗、培训完成率等核心HR指标。 触发词：人力看板、流失率、招聘漏斗、培训完成率、人员结构

infometa Skill

Design, specify, implement, revise, and QA quantitative visuals and chart choices. Use when an analytical answer needs visual judgment—comparing values, showing composition, reading concentration, understanding movement over time, or building chart specifications for reports and dashboards.

infometa Skill

Diagnose why a metric changed or differs from expectation, and produce leadership-ready KPI updates. Use when the user needs to understand what drove a metric movement, anomaly, or discrepancy, or when producing WBR/MBR/QBR summaries, scorecards, target pacing readouts, or performance updates.

infometa Skill

Build polished analytical reports, dashboards, and product/business analyses. Use when the user needs a durable report (executive or technical), an analytical dashboard with clear metrics, or a data-backed product/business analysis to inform decisions. Covers report building, dashboard construction, and decision-oriented quantitative analysis.

infometa Bundle

提供标准化的数仓 HTTP 查询接口调用能力。当用户需要从数据仓库获取数据时，根据接口规范生成正确的前端调用代码。⚠️严格限制：数仓接口只能在前端页面（浏览器端）中调用，严禁在任何后端代码（Node.js、Python、Go、Java等后端服务）中调用，因为后端环境没有用户的SSO身份信息，调用会报错。使用场景：1.用户需要在前端页面调用数据仓库接口查询数据。2.用户需要生成前端访问数仓的 HTTP 请求代码。3.用户需要在前端编写数据获取逻辑。4.用户提到"查数据"、"调接口"、"获取数据"、"数据仓库"等关键词

infometa Skill

Assess whether datasets are trustworthy for analysis, modeling, dashboards, or pipelines; and validate finished analyses before sharing. Use for data quality checks (grain, freshness, nulls, duplicates, schema drift, joins, integrity, distributions) and analysis QA (methodology review, calculation verification, visualization checks, confidence assessment).

infometa Skill

查询用户的HR数仓数据权限信息。当用户想了解自己是否有某张表或某些字段的访问权限、或想确认SQL查询结果中某些异常值是否因权限不足被脱敏时，使用本Skill。使用场景：1.用户询问自己有哪些表的数据权限。2.用户想确认是否有某张表的访问权限。3.用户想了解自己对某张表的行权限和列权限范围。4.查询结果中出现疑似脱敏值（如0、*、1970-01-01等），需要确认是否因权限不足导致。5.用户想知道为什么某些字段数据异常或被隐藏。优先级：如果存在权限中台的hr-right SKILL，当用户泛问"我有什么权限"而不指定具体表时，优先使用hr-right SKILL回答用户的权限问题。

infometa Bundle

腾讯探元文博检索工具集（Agentic RAG）。封装两个 HTTP API 为 Node.js 脚本，由 Agent 依据问题特征选择工具并构造 query： - search-relics（文物/世界遗产数据库 NL→SQL）：适合结构化事实的详情、列表、统计与排行查询 - search-knowledge（关键词+向量语义检索）：适合开放/语义问题（背景/原因/工艺/故事/鉴赏/对比论证/攻略/研学） 触发词：文物 / 查文物 / 馆藏 / 朝代 / 年号 / 青铜器 / 瓷器 / 出土 / 世界遗产 / 入选年份 / 评定标准 / 濒危 / 背后故事 / 工艺 / 历史 / 对比 / 参观 / 研学 / 攻略

infometa Bundle

DataBrain 舆情指标查询助手。把游戏舆情/口碑/声量/情感/评分/KOL/直播/新闻/热门视频/热门帖子/Hashtag/热梗/竞品/官号 等问题，以及**游戏广告投放素材/创意取数**（创意数·素材数·素材类型·渠道·国家维度·素材明细列表）翻译成可执行的 BigQuery SQL，覆盖 opinion / intelligence / marketing_hub schema。**只支持游戏维度查询**，不支持公司/开发商/发行商聚合舆情；**不支持** UA 预算/团队规模/未来预测/决策建议/因果归因等问题，遇到会主动路由或拒绝。纯运营指标（独立的下载/收入/DAU/留存）归 databrain-intelligence；但**素材趋势 × DAU/下载时间对齐对比**在本 skill 素材 reference 内有限支持。触发关键词：舆情、口碑、声量、mentions、情感、sentiment、Brand Health、品牌健康度、评分、score、Steam/AppStore/GooglePlay/Xbox/PS/Metacritic/OpenCritic、好评率、KOL、网红、创作者、博主、直播、Streaming、Hours Watched、Peak CCV、新闻、News、PR、Google Trends、热门视频、热门帖子、Trending、Hashtag、TikTok、Meme、热梗、官号、Official Account、Earned、竞品、Competitor、话题、Topic、关键词、词云、市场热度、Channel Share、社媒、互动、Engagement、观看、Views、发帖、Publications、潜在曝光、Impressions、玩家评价、玩家讨论、Steam 评论、商店评论、投放素材、广告素材、广告创意、creatives、materials、素材库、素材列表、广告列表、创意数、素材数、新增素材、新增创意、素材类型、素材分布、渠道创意数、渠道占比、素材曝光、素材互动、素材评分、素材榜单、TopN 素材、国家投放、多游戏素材对比、竞品素材、视频标签

infometa Bundle

Jiayi Ads Analytics Expert Public

infometa Bundle

主机安全CVE漏洞修复验证引擎。从主机漏扫报告(Excel)或CVE编号自动提取漏洞，查询威胁情报(NVD/EPSS/MSRC/OVAL)，生成修复脚本(fix.sh/fix.ps1)，SSH验证脚本可执行性，产出修复验证报告。覆盖 Linux(centos/ubuntu/debian/suse/amazon/fedora/alpine/arch) + Windows + Web-CMS 三类。触发关键词：主机漏扫、CVE验证、漏洞修复验证、host CVE、fix validation。

infometa Skill

将已经通过质量门的园区、证据、任务验收或候选组合结果渲染为用户需要的聊天、Markdown、JSON、CSV或其他受支持工件。仅在确有结构化交付、导出、跨会话续作或外部动作草稿需要时使用；只改格式，不得修改事实、判断、排序、状态或语义。

infometa Bundle

容器安全CVE漏洞修复验证引擎。从容器漏扫报告(Excel)自动提取漏洞，生成修复计划， SSH到测试环境验证OS包(apt/yum/apk)、Python(pip)、Node.js(npm)、Java(JAR)四种包类型的 修复方案，产出修复验证报告。不涉及主机层漏洞修复、不处理容器编排层安全配置。 触发关键词：容器漏扫、CVE验证、漏洞修复验证、container CVE、fix validation。

infometa Skill

End-of-semester case handoff memos — the mirror of /ramp. Produces per-case transition memos and a cohort summary so the departing cohort hands work to the incoming cohort cleanly. Reads deadlines, client-comms, and case history. Use when the professor or departing students need to wrap up the semester, build transition memos, or offboard a graduating/withdrawing student.

theheavenlyd3mon Skill

Use whenever a task involves parametric CAD in FreeCAD — modeling parts and assemblies, editing object properties, technical drawings, importing/exporting STEP/STL/OBJ/DXF, PDF/Excel reports from a model, or finite-element (FEM/CalculiX) analysis. Requires a running FreeCAD instance with the FreeCADMCP addon (see Prerequisite).

ichichuang Bundle

Audit generated Excel reports by enumerating populated output rows, exposing formulas, and checking that each subtotal range includes all visible detail rows.

ichichuang Bundle

Iteratively debug Excel structure with exploratory scripts before writing extraction logic

ichichuang Bundle

Create Excel files with openpyxl by falling back to shell-based Python heredoc when sandbox execution fails

ichichuang Bundle

Use shell_agent as fallback when execute_code_sandbox fails for Excel file operations

ichichuang Bundle

Build complex Excel files through staged, verifiable steps with intermediate CSV outputs for debugging

ichichuang Bundle

Handle Excel files with irregular headers, merged cells, and unknown header row positions using pattern-matching and index-based extraction.

ichichuang Bundle

Create Excel files with openpyxl by falling back to run_shell with inline Python heredoc when execute_code_sandbox fails

ichichuang Bundle

Systematic Python debugging workflow for spreadsheet tasks to isolate environment issues from script logic

ichichuang Bundle

Use direct Python execution for reliable spreadsheet operations instead of shell_agent

ichichuang Bundle

Unmerge merged cells in openpyxl worksheets before writing values to avoid AttributeError

ichichuang Bundle

Use run_shell with inline Python as a fallback when execute_code_sandbox fails for openpyxl/spreadsheet operations

ichichuang Bundle

Unified workflow that delegates failed web searches to shell_agent for resilient data gathering, then applies anchored spreadsheet proof gates for verified Excel output

ichichuang Bundle

Resilient multi-step workflow for spreadsheet processing when execute_code_sandbox fails, using shell_agent exploration, file-based scripts, and verification steps

ichichuang Bundle

Safely update Excel workbooks by first locating candidate files, verifying workbook structure before editing, and running post-write validation against required sheets, populated columns, and sample counts.

ichichuang Bundle

Use a deterministic Python/openpyxl inspection pass to verify workbook structure, counts, marked rows, and output-file existence when delegated spreadsheet summaries seem inconsistent.

ichichuang Bundle

Use run_shell with cd and heredoc syntax for complex Excel operations when read_file fails on XLSX or execute_code_sandbox fails on multi-step workbook creation

ichichuang Bundle

Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports