Data & Analytics

lazyisefficient Bundle

Use when tuning the numbers in a game — economy curves, progression rates, difficulty pacing, drop tables, win/loss odds, time-to-X targets, and currency velocities. Triggers on "balance pass", "tune the economy", "progression curve", "difficulty curve", "drop rate", "XP curve", "TTK", "time-to-content", "balance the economy", "spreadsheet model", "economy sim", or a system spec from game-systems-designer with `TBD` placeholders. Produces an economy spreadsheet, balance pass plan, sim outputs, and per-system balance tables. Stops at the numbers — does not change system rules or pricing. For systems design see game-systems-designer; for store catalog see iap-manager.

lazyisefficient Bundle

Use when implementing analytics with PostHog in a TypeScript app — capturing events, identifying users, adding feature flags, tracking errors, or wiring API lifecycle telemetry. Triggers on edits to analytics integration files, or mentions of "PostHog", "analytics", "feature flag", "event tracking", "capture", "identify", "A/B test", or "experiment".

morningstar0709 Bundle

Convert supported local documents to Markdown through the local MinerU API in Trae, including PDF, images, DOCX, PPTX, and XLSX, and save the output to a chosen Windows-accessible directory. Use when the user asks to 转 Markdown, 提取 PDF, 解析文档, 图片转 md, 保存为 markdown, or batch-convert supported files. Do not use for web pages, plain text rewriting, or summarization tasks without file conversion.

mte90 Bundle

Security standards for Go backend services (Input Validation, Crypto, SQL Injection Prevention).

christopheralphonse Skill

Implement secure coding practices following OWASP Top 10. Use when preventing security vulnerabilities, implementing authentication, securing APIs, or conducting security reviews. Triggers on OWASP, security, XSS, SQL injection, CSRF, authentication security, secure coding, vulnerability.

iankiku Skill

(forwward) Designs analytics systems, writes SQL queries, plans event tracking, and builds dashboards for product and user metrics. Triggers on SQL, analytics, dashboards, tracking, data pipelines, or user behavior analysis.

the-hugin Skill

KPI framework for business dashboards — metric selection, hierarchy (strategic/tactical/operational), SQL templates for MRR/retention, Streamlit examples. Use when designing or reviewing business dashboards and metrics.

thettwe Skill

Regenerate the nyann-managed block in CLAUDE.md from the current profile, stack detection, and doc plan — without re-running a full bootstrap or retrofit. TRIGGER when the user says "regenerate CLAUDE.md", "update CLAUDE.md", "refresh CLAUDE.md", "rebuild CLAUDE.md", "re-gen CLAUDE.md", "my CLAUDE.md is stale", "CLAUDE.md doesn't match my profile", "sync CLAUDE.md with the profile", "/nyann:gen-claudemd". Do NOT trigger on "optimize CLAUDE.md" / "trim CLAUDE.md" / "what's unused" — that's the `optimize-claudemd` skill (usage-analytics-driven). Do NOT trigger on "explain CLAUDE.md" / "what's in CLAUDE.md" — that's `explain-state`. Do NOT trigger on initial project setup — that's `bootstrap-project`.

captainflasmr Skill

Database design, optimization, and query construction across SQL databases. Trigger on phrases like "database help", "sql help", "database design", "sql query", "database optimization", "postgresql help".

tianque6916 Skill

安全 — OWASP Top10/XSS/CSRF/SQL注入, OAuth2/JWT/RBAC, 加密/合规

tianque6916 Skill

数据分析 — pandas/numpy 数据清洗/聚合/可视化, 统计检验/A-B测试/SQL

nero1688 Skill

把 TEJ 下載的原始 Excel/CSV 洗成可分析的乾淨面板：欄名標準化、日期與年季格式解析、面板長寬轉換、遺漏值分析報告、winsorize 縮尾選項與揭露句。內建品質檢查（不可能值、同值重複紅旗、處理前後列數對帳並解釋差額、抽 3 筆人工核對）。輸出雙件套：清理腳本（R 或 Python）＋清理報告。何時用：RAW 檔已下載、要清理標準化時（清理期）。與 tej-variable-mapper 劃界：mapper 決定『抓哪個欄位』，本技能處理『抓回來的檔怎麼洗乾淨』；洗完接 r-spss-syntax-architect 建模。觸發詞：TEJ 清理、資料清理、資料清洗、洗資料、遺漏值、缺失值、極端值、離群值、縮尾、winsorize、欄名標準化、年季格式、長寬轉換、面板整理、wide to long、資料品質、RAW 檔。

nero1688 Bundle

免費公開揭露資料偵察員(付費資料庫的免費對應+事件研究的事件源)。當研究需要公司『自己說』的官方揭露——重大訊息、年報、股東會決議、法說會、內部人持股異動、裁罰紀錄——或需要乾淨的事件日來做事件研究(event study)時使用。以台灣為例路由到官方免費源:公開資訊觀測站(MOPS,重大訊息/年報/股東會)、TWSE/TPEx 官網、政府開放資料平台、專利檢索(TIPO)、金管會裁罰公開資料。核心用途:(1)當 TEJ 等付費資料庫的免費補充或替代;(2)提供公司治理/揭露事件研究的標準事件源,可直接匯出成 event-study 事件檔;(3)識別碼(統編/公司代號)與付費庫對接。輸出:資料可得性報告、事件源建議、識別碼對接方案、抓取合規與品質檢查清單。何時用:沒有 TEJ 授權想用免費資料、要做事件研究找事件日、要抓重大訊息/年報/裁罰、公開資訊觀測站怎麼抓。觸發詞:公開資訊、公開資訊觀測站、MOPS、重大訊息、重訊、年報、股東會、法說會、裁罰資料、免費資料、官方揭露、事件研究事件源、event study 事件、TWSE、TPEx、政府開放資料、TIPO 專利、統編對接、免費替代 TEJ。與 tej-data-scout 劃界:那個偵察『付費 TEJ 資料庫』有沒有變數,本 skill 偵察『免費官方公開揭露』;兩者互補,識別碼可對接,常搭配使用。與 causal-inference-architect 劃界:那個做事件研究的『識別策略與估計』,本 skill 供給它『乾淨的事件日資料』。與 text-analytics-architect 劃界:年報/重訊的『文字內容探勘』歸那邊,本 skill 管『到哪抓、怎麼抓成事件』。

nero1688 Bundle

文字資料研究架構師(行銷/資管/財金的 text-as-data 前緣):把非結構文字(財報 MD&A、法說會逐字稿、消費者評論、社群輿情、客服紀錄)變成可發表的研究變數。涵蓋:語料與構念的效度論證(這些字真的量到你的構念嗎)、方法階梯選型(字典法→主題模型 LDA/STM/BERTopic→嵌入分類→LLM 標註,由可解釋到黑箱)、LLM 輔助標註的信效度紀律(人工雙編碼基準、一致性係數、prompt 凍結與版本記錄、偏誤稽核)、中文特化(CKIP/jieba 斷詞、繁簡、停用詞、中文情緒詞典)、文字變數的敘述統計與效度報告。何時用:想用文字資料做研究、財報語調、評論探勘、輿情變數、要用 GPT/Claude 幫忙標註資料。觸發詞:文字探勘、text mining、文本分析、text-as-data、主題模型、LDA、STM、BERTopic、情緒分析、sentiment、語調、tone、財報文字、MD&A、法說會、評論分析、社群輿情、LLM 標註、AI 標註、機器編碼、斷詞、詞頻、TF-IDF、embedding、NLP 研究。與 qualitative-thematic-coder 劃界:那個是人工深度詮釋(小語料、理論生成、逐字稿),本 skill 是規模化文字量化(大語料、變數建構、進迴歸);兩者可串:先質化編碼建碼本,再放大為自動分類。與 r-spss-syntax-architect/causal-inference-architect 劃界:文字變數建好之後的建模歸它們。

nero1688 Bundle

文獻語料庫與文獻比較矩陣建置器。把一堆 PDF 變成有結構的文獻資料夾＋一張可比較的 Excel 矩陣：自動從 PDF 抓 DOI、查 CrossRef（免金鑰）取回書目與摘要、**建檔當下就做撤稿查核**（引用撤稿論文是實質學術風險，在進文獻庫時就攔截）、產生 APA7 參考文獻，再組成含理論視角／研究情境／方法／IV／DV／中介調節／主要發現／限制／與本研究關聯／可引用金句的橫向比較表，並自動列出哪幾篇的綜整欄還沒填。何時用：讀文獻讀到散亂、要建文獻庫、要寫文獻回顧前先把文獻排開來比、口試前要交文獻整理表。觸發詞：文獻矩陣、文獻表格、文獻整理、撤稿、撤稿查核、retraction、論文被撤、文獻比較、文獻回顧表、literature matrix、synthesis matrix、文獻資料夾、建文獻庫、APA7 產生、DOI 查詢、CrossRef、抓書目、參考文獻整理、摘要整理、文獻 Excel、讀書筆記表。與 citation-verifier／check-citations 劃界：那兩支做『引用查核』（內文與清單對不對得上、文獻是否真實存在），本 skill 做『文獻庫建置與橫向比較』；查引用真偽找那兩支。與 phd-researcher 劃界：那支做系統性回顧方法論（PRISMA 流程、偏誤風險、meta-analysis），本 skill 只做語料庫與矩陣這件工具活；要做正式 SR/MA 找那支，本 skill 產出的矩陣可餵給它。

abpai Bundle

Bun runtime guidance for JavaScript and TypeScript projects — package management, HTTP servers, Bun-specific APIs (`Bun.serve`, SQL, S3, Redis, `Bun.Image`, `Bun.WebView`, `Bun.$`), testing, bundling, and migrating from Node.js.

andr-ca Skill

Use when designing a database schema, writing migrations, reviewing SQL queries, or choosing between relational and document models — covers naming, index strategy, migration safety, N+1 prevention, and transaction boundaries.

garrettjsmith Skill

When the user wants a technical site audit, crawl data analysis, location page quality checks, duplicate content detection, schema validation at scale, or internal linking analysis. Trigger on "Screaming Frog," "site crawl," "technical audit," "crawl data," "broken links," "duplicate content," "location page audit," or when analyzing exported crawl CSV/Excel files.

garrettjsmith Skill

When the user wants traffic data, conversion tracking, user behavior on location pages, GBP traffic attribution, or geographic traffic patterns. Trigger on "Google Analytics," "GA4," "traffic," "conversions," "how many leads," "phone calls," "form submissions," "where is my traffic coming from," or "is my website converting."

guiziweb Skill

Add a CSV export button to an existing admin grid.

jpoindexter Skill

Use when an analysis, dataset, spreadsheet, model, benchmark, or research claim must be audited before it is trusted or acted on — deciding what to demand from a data supplier, tracing a number back to its measurement, screening for randomization, image, binning, or batch-effect failures, scoring a study's credibility, separating a forensic audit from data cleaning, or naming who paid for the answer.

lukaskellerstein Bundle

This skill should be activated when the user asks to create, edit, read, or analyze Excel spreadsheet files (.xlsx, .xlsm, .csv, .tsv). Triggers for: building financial models, creating data tables, formatting spreadsheets, adding formulas, cleaning tabular data, converting between tabular formats. Also triggers when user mentions 'spreadsheet', 'Excel', 'workbook', or references an .xlsx file. Do NOT trigger when the primary deliverable is a document, presentation, or visualization.

alihusains Skill

Reviews analytical SQL for correctness and cost: the join fan-out and row-loss traps, filters that silently change join semantics, window and grain errors, null and timezone handling, then scan volume, partition pruning, and predicate placement. Use when a query is about to feed a report or model, when results look wrong or duplicated, when a query is expensive or slow, or when reviewing someone else's analytical SQL. Trigger on 'review this query', 'why are my rows duplicated', 'this query is expensive', 'check my SQL', 'the join is wrong', 'why is this so slow'. Not for verifying a finished report's outputs against an independent source — that is data-analytics-report-qa; not for deciding what the metric should mean, which is data-analytics-metric-definition.

alihusains Skill

Turns a metric name into a binding definition contract: the population, the qualifying event, the time grain, the timezone, the deduplication rule, restatement policy, and a single named owner. Use when two teams report different numbers for the same metric, when a new KPI is being introduced, when a dashboard figure cannot be reconciled with a report, or when a definition needs reviewing before it goes into a board pack. Trigger on 'what counts as an active user', 'our numbers do not match', 'define this metric', 'metric definition', 'why is the dashboard different from the report', 'source of truth for X'. Not for checking whether a specific report is correct before it ships — that is data-analytics-report-qa; not for reviewing the query that implements the definition, which is data-analytics-sql-review.

alihusains Skill

Builds a spreadsheet somebody else will maintain: inputs, calculations and outputs on separate sheets, no constants buried inside formulas, a documented assumptions block, a checks sheet that fails loudly, and a written refresh procedure. Use when producing a model, tracker, budget, forecast, pricing sheet, reconciliation or allocation workbook that will be reopened next month by someone who did not build it. Trigger on 'build me a spreadsheet', 'make this into an Excel model', 'turn this into a workbook', 'build a forecast/budget/pricing model', 'can you produce an xlsx', 'this sheet keeps breaking'. Not for checking numbers already produced by a report or dashboard (use data-analytics-report-qa), not for agreeing what a metric means before it is modelled (use data-analytics-metric-definition), and not for writing the narrative that accompanies a variance (use finance-budget-vs-actual-commentary).

bxmaximum Skill

Covers direct database work in Bitrix — Application::getConnection(), Connection, MysqliConnection, SqlHelper, SqlExpression, raw SQL queries via query()/queryExecute()/queryScalar(), transactions (startTransaction/commitTransaction/rollbackTransaction), DDL and schema migrations, bulk operations (insertBatch, addMulti), additional connections via the connections section in .settings.php. Applied when ORM is insufficient — bulk operations, raw SQL, migrations, working with external databases, and building custom queries. Key terms — Connection, SqlHelper, SqlExpression, transaction, raw SQL, bulk insert, DDL, migration.

orientpine Bundle

특허 데이터 다축 분류, 트렌드 분석, 시각화 대시보드 생성. Use when: (1) 수집된 특허 데이터 분류/분석/시각화 시, (2) '특허 분류', 'analyze patent trends', 'visualize patent data', 'create patent dashboard', 'generate patent report' 요청 시, (3) 차트, 히트맵, 트렌드 분석 필요 시, (4) 화이트 스페이스 분석이나 경쟁 인텔리전스 필요 시, (5) Excel/Markdown 특허 데이터 인사이트 추출 시.

orientpine Skill

KIPRIS API 기반 특허 검색 실행, 배치 내보내기, 중복 제거. Use when: (1) 특허 데이터 검색 및 다운로드 시, (2) 검색 계획 실행 시, (3) '특허 검색', 'search patents', 'collect patent data', 'export patents to Excel' 요청 시, (4) 키워드, 출원인, 출원번호, IPC 코드 기반 한국/해외 특허 배치 검색 시.

srobinson Bundle

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

wangjiawei508 Bundle

为 Markdown、纯文本、PDF、DOCX、PPTX 或 XLSX 文档规划并生成可交付配图。适用于文章配图、报告插图、封面图、章节图、概念解释图和演示文稿素材；当用户说“给文档配图”“生成插图”“做封面图”或需要按文档结构批量生成一致风格图片时使用。

wangjiawei508 Skill

Excel 报表生成技能。当需要导出监测数据表、统计汇总表或多期对比表为 .xlsx 文件时加载此技能，获取数据组织规范和工具调用指引。

wangjiawei508 Skill

RAILWISE-OS 经营数据问答、经营简报、指标诊断和项目经营健康检查专项 skill。

omicverse Bundle

Build an ASV-level phylogenetic tree (MAFFT alignment + FastTree GTR+Γ), attach it to a 16S AnnData, and run phylogenetically-aware diversity (Faith PD, weighted / unweighted UniFrac). Use when adding tree-aware metrics on top of the basic 16S amplicon AnnData, or when the cohort needs UniFrac-driven beta-diversity instead of Bray-Curtis.

omicverse Bundle

Run all three differential-abundance methods (Wilcoxon, pyDESeq2, ANCOM-BC) on the same microbiome AnnData, compare their hit sets via 3-way Venn / overlap counts, and decide which to trust on a given cohort. Use when the user wants to benchmark DA methods on a 16S study, when picking between methods on a small or zero-inflated cohort, or when reporting consensus features that survive multiple tests.

omicverse Bundle

Combine multiple per-study microbiome AnnDatas into a single cross-cohort table and run inverse-variance / random-effects meta-analysis on differential abundance. Use when you have 16S studies from multiple cohorts that need joint analysis, when you need a combined log2 fold-change with Cochran's I² heterogeneity, or when you want to find features whose effect replicates across cohorts (vs. cohort-specific signals).

omicverse Bundle

Run the canonical metabolomics preprocessing chain on an AnnData peak table — impute, normalize, transform — and apply LC-MS-specific drift / batch / sample QC corrections (drift_correct, SERRF, ComBat, sample_qc). Use when converting `t_metabol_01_intro` or `t_metabol_06_batch_correction` into a reusable skill, when a user has a MetaboAnalyst CSV / LC-MS peak table to clean before differential or multivariate analysis, or when choosing among PQN/TIC/median sample-normalization, log/Pareto feature-transformation, and qrilc/knn/half_min/zero imputation strategies.