Data & Analytics
Data agent skills make AI agents useful for data work: writing SQL, cleaning datasets, building pipelines, working with spreadsheets, and producing analyses. Each skill is a reviewed SKILL.md file that teaches the agent one workflow well, ready to install in seconds.
-
kyrie66nb Skill Excel XLSXExcel, XLSX, CSV, and spreadsheet analysis/editing alias.
-
kyrie66nb Bundle Er Diagram ExtractorUse when extracting ER diagrams from papers, SQL schemas, or ORM code; when analyzing database table structures; when converting database designs to visual ER diagrams
-
kyrie66nb Bundle Officecli XLSXofficecli xlsx workflow.
-
kyrie66nb Bundle Officecli Data DashboardCreate Excel dashboards.
-
kyrie66nb Bundle Officecli Financial ModelCreate Excel financial models.
-
maxrave-dev Skill Polymorphic Load Media Entry PointOne generic "load this item and start playing" function normalizes several item types into a single internal shape, routes the queue-seeding strategy off a discriminator, and gates every pre-enqueue policy at that one place. Use when playback can start from many screens and a rule (content filter, dedup, analytics, resume-without-autoplay) keeps getting forgotten on one of the paths.
-
maxrave-dev Skill Bucket Local Time In Code Not In SQLGroup events by local hour or local day in application code from one raw scan, not in SQL — the engine's local-time modifier answers from the process time zone rather than the user's, and four local-time aggregates mean four scans that can disagree with each other. Covers where the line sits between an aggregate that belongs in SQL and one that does not, and what the single scan has to return to stay correct. Use when an hour-of-day or weekday chart differs between platforms or between a device and a desktop build, when adding a fourth "group by day" query, or before writing a date function into a query string.
-
modu-ai Skill Doc XLSX엑셀(.xlsx) 문서를 만들어 드립니다 — 데이터 표, 차트, 수식, 조건부 서식이 들어간 KPI 대시보드·매출 분석표·예산표·간트차트를 바로 쓸 수 있게 출력합니다. 다음과 같은 요청 시 사용하세요: - "KPI 대시보드 엑셀로 만들어줘" - "월간 매출 분석표 생성해줘" - "프로젝트 일정 간트차트 엑셀로 작성해줘" - "예산 대비 실적 추적표 만들어줘" - "급여 계산 시트 만들어줘" - "데이터 집계표 엑셀로 정리해줘" - "손익계산서 엑셀로 만들어줘" 한국 비즈니스 표준 서식(천 단위 구분·원화 표시·날짜 형식)과 차트·수식을 자동 적용합니다. 데이터를 엑셀(.xlsx) 파일로 만들 때는 Claude 기본 생성 대신 이 스킬을 사용하세요 (수식·차트·서식 보존).
-
modu-ai Skill Doc Reader한국 공문서(HWP 3.0/5.x·HWPX·HWPML·PDF·XLSX·DOCX)를 마크다운으로 파싱해 드립니다 — 표 완벽 재현, 신구대조표, 양식 필드 추출/자동 채우기, 문서 비교, DRM 배포용 문서 복호화, OCR 연동까지. kordoc MCP의 8개 도구를 호출하므로 별도 설치·API 키가 필요 없습니다(Node.js 18+ 권장). 다음과 같은 요청 시 사용하세요: - "이 HWP 파일 읽어줘", "HWP 문서 내용 알려줘", "한글 파일 텍스트 추출" - "공문서 PDF 마크다운으로 변환", "PDF 표 그대로 가져와줘" - "두 문서 신구대조표 만들어줘", "개정판 달라진 부분 비교" - "신청서 양식 자동 채우기", "공문서 빈칸 채워줘", "양식 필드 추출" - "판결문 HWP 텍스트 추출", "엑셀 양식 파싱", "워드 문서 읽어줘" - "배포용 HWP 잠금 해제", "DRM 문서 읽기", "스캔 PDF 텍스트화(OCR)" 본 스킬은 "읽기(파싱)" 전담입니다. 문서 "생성(쓰기)"은 doc-pdf·doc-hwp·doc-docx·doc-xlsx를 사용하세요.
-
modu-ai Bundle Data ExplorerCSV·Excel 데이터의 프로파일링·품질 보고서를 만들어 드립니다. 다음과 같은 요청 시 사용하세요: - "이 데이터 분석해줘" - "CSV 요약해줘" - "이상값 찾아줘" - "데이터 품질 체크해줘" 컬럼 요약·결측값/이상값 탐지·상관관계 분석을 거쳐 데이터 품질 보고서로 정리합니다.
-
modu-ai Bundle Korean HumanizeAI(ChatGPT·Claude·Gemini 등)가 쓴 한국어 텍스트의 "AI 티"를 정밀하게 제거해 사람이 쓴 글처럼 윤문하는 한국어 특화 스킬입니다. 번역투(~를 통해/~에 있어서/이중 피동), 영어 인용 과다, 기계적 병렬(첫째·둘째·셋째), AI 특유 관용구(결론적으로/시사하는 바가 크다/혁신적인), 피동태 남용, 문두 접속사 남발, 형식명사 과다, 이모지·불릿·볼드 남용 등 10대 카테고리 × 40+ 패턴을 S1/S2/S3 심각도로 탐지·윤문하고, 의미는 한 글자도 건드리지 않습니다(고유명사·수치·날짜·인용 100% 보존, 변경률 30% 초과 시 경고·50% 초과 시 강제 중단). 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: - "AI 티 없애줘", "GPT 문체 제거해줘", "ChatGPT 티 제거" - "사람이 쓴 것처럼 윤문해줘", "AI 같은 글 자연스럽게" - "한글 AI 윤문", "AI 글 사람처럼", "AI 글 티 안 나게" - "번역투 제거", "영어 인용 많은 글 윤문" - "휴머나이저", "humanize Korean", "AI detector bypass 한글" - 후속 작업: "특정 카테고리만 다시", "이 문단만", "2차 윤문", "강도 조정", "장르 바꿔서" 적용 대상 — 모든 한국어 텍스트 산출물(블로그·뉴스레터·카피·사업계획서·제안서·보고서·이메일·랜딩 카피·칼럼·리포트). ai-slop-reviewer가 1차 일반 후처리를 마친 뒤 2차 한국어 정밀 윤문으로 호출하는 것을 권장합니다. 적용 제외 — 단순 맞춤법·오탈자 교정(직접 처리), 번역(번역 스킬), 내용 추가·삭제 동반 재작성(별도 집필 스킬), 코드·JSON·CSV·차트·표. v1.4.0 — **판정 주체가 규칙에서 정독으로 바뀌었습니다.** 윤문 전(Phase 2.5)과 후(Phase 6)에 LLM이 글 전체를 세 번 읽어(독자로서·편집자로서·소리 내어) 맥락과 리듬을 판단하고, 규칙표는 정독이 지목한 자리를 고치는 도구로 씁니다. 기준은 표준 한국어(어문 규범·영한 번역투 3유형)와 한국
-
netvar1337 Skill FunctionsUse as the idasql SQL function reference catalog (signatures, params, examples).
-
netvar1337 Skill IdapythonUse when SQL is insufficient and direct IDA SDK access via Python is needed.
-
netvar1337 Skill Pentest Tools主动渗透测试工具链。覆盖信息收集、端口扫描、漏洞扫描、Web 渗透、SQL 注入、目录爆破、密码破解等场景。 通过 MCP server(pentestMCP / mcp-security-hub)将 20+ 安全工具暴露给 AI agent。 触发关键词:渗透测试、端口扫描、Nmap、漏洞扫描、Nuclei、SQL 注入、SQLMap、目录爆破、FFUF、密码破解、Hashcat、信息收集、子域名、Web 渗透、ZAP、Burp。
-
pavel-kravchenko Skill Python Bio PandasManipulate bio DataFrames with pandas — loc/iloc selection, boolean/query filtering, groupby agg vs transform, left-join annotation merges, CSV/TSV expression-matrix I/O, wide/long melt. Use when indexing/filtering a gene or sample table, merging expression data with an annotation or clinical table, computing group-wise statistics (per-condition mean/z-score), or reading a counts.csv/counts.tsv into a DataFrame.
-
pavel-kravchenko Skill Python Advanced SQLWrite Python decorators/context managers/dataclasses and query gene/variant tables with sqlite3/pandas SQL (JOIN, GROUP BY, HAVING). Use for retry/caching/validation wrappers or SQL against Ensembl/UCSC-style schemas.
-
acaprino Skill Senior Review Data Integrity AuditorPersistence-layer reviewer: impossible or inconsistent stored state. TRIGGER WHEN: the diff or target touches schemas, models, ORM entities, repositories, raw SQL, caches, or transaction boundaries; or the concern is partial writes, read-modify-write races, uniqueness enforced in code but not in the database, cache and database divergence, or eventual consistency consumed as strong. DO NOT TRIGGER WHEN: the concern is domain rules and state machines (use logic-integrity-auditor), migration mechanics (the data-migrations dimension), or cross-service message flows (use distributed-flow-auditor).
-
thinkfleetai Skill SnowflakeQuery Snowflake data warehouse — execute SQL, manage warehouses, and query metadata via the SQL API.
-
thinkfleetai Skill CloudflareManage Cloudflare — zones, DNS records, Workers, and analytics via the REST API.
-
thinkfleetai Skill Excel OnlineRead and write Excel files via Microsoft Graph API. Manage workbooks, worksheets, and cells in OneDrive/SharePoint.
-
thinkfleetai Skill Database QueryExecute SQL queries against PostgreSQL (psql) or MySQL (mysql) databases using their CLI clients.
-
thinkfleetai Skill Fitbit AnalyticsFitbit health and fitness data integration. Fetch steps, heart rate, sleep, activity, calories, and trends from Fitbit Web API. Generate automated health reports and alerts. Requires FITBIT_CLIENT_ID, FITBIT_CLIENT_SECRET, FITBIT_ACCESS_TOKEN, FITBIT_REFRESH_TOKEN.
-
thinkfleetai Skill Google AnalyticsQuery Google Analytics 4 — reports, realtime data, dimensions, and metrics via the Data API.
-
thinkfleetai Skill RevolutRevolut Business API CLI — accounts, balances, transactions, counterparties, payments, FX exchange, CSV export. Auto-refreshes OAuth tokens. Business accounts only (not personal).
-
thinkfleetai Skill Database MigrationManage database schema migrations with Flyway, Alembic, Prisma, Knex, and raw SQL migration patterns.
-
dnyoussef Bundle SQL Database SpecialistSql Database Specialist
-
fluxonlab Skill Python Project ReviewUse when you need to review a Python project for environment management correctness, dependency pinning and CVEs, pytest/coverage structure, ruff linting, mypy type checking, and common security anti-patterns including subprocess shell injection, eval/exec, pickle deserialization, and SQL string concatenation.
-
fluxonlab Skill SQL Optimization PatternsMaster SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.
-
fluxonlab Skill Analytics Tracking ReviewUse when you need to review analytics events, tracking plans, privacy, attribution, dashboards, and conversion instrumentation.
-
wgpsec Bundle Sqlmap Advancedsqlmap 高级用法完整参考。当确认存在 SQL 注入需要用 sqlmap 自动化利用时使用。覆盖 POST/Cookie/Header 注入、tamper 脚本选择、--technique 精确控制、二次注入、OS shell/文件读写、数据库提取优化
-
pavel-kravchenko Skill Python Bio Data WranglingClean/reshape bio pandas tables — impute NaNs, dedupe replicates, coerce clinical strings to numeric/categorical, melt/pivot wide-long, regex-parse GTF attrs. Use for cleaning expr/clinical dataframes or reshaping.
-
pavel-kravchenko Skill Python Bio File OperationsRead/write FASTA, FASTQ, CSV/TSV (BED), JSON, and pickle files in Python using open()/context managers, csv.DictReader/DictWriter, and streaming generators for large genomics files. Use when parsing a FASTA/FASTQ file, writing sequences back out with line wrapping, reading/writing gene expression CSV or BED/TSV files, loading GenBank ORIGIN sequence, saving Python objects with pickle, or handling files too large to fit in memory.
-
pavel-kravchenko Skill Bio Applied Virtual ScreeningDock ligand libraries with AutoDock Vina/meeko, filter hits by ADMET (Lipinski, LogS, hERG), rank by composite docking+QSAR score in pandas. Use when docking SMILES/SDF vs a target or prioritizing virtual screening hits.
-
pavel-kravchenko Skill Bio Applied Data HarmonizationHarmonize multi-omics data (RNA-seq, proteomics, methylation, metabolomics) before integration — per-layer normalization, KNN/half-minimum missing-value imputation, PCA/PVCA batch-effect detection, and ComBat correction with pandas/scikit-learn. Use when prepping matrices for MOFA2/DIABLO/mixOmics, fixing missing values in proteomics MS data, or removing batch effects confounded with sequencing date/site before joint analysis.
-
pavel-kravchenko Skill Python Bio Python IntroductionFoundational Python for biology - count nucleotides, compute GC content, use f-strings/loops/functions, and set up biopython/pandas/numpy via pip/venv/conda. Use when a beginner asks how to start with Python for bioinformatics, write a first DNA-parsing script, calculate GC content from a raw string, or install BioPython/scanpy/pysam in a virtualenv or conda environment.
-
pavel-kravchenko Skill AI Science LLM Training SystemsTrack LLM fine-tuning runs with pandas/dataclasses + W&B/MLflow/TensorBoard: log per-epoch loss, run one-factor ablations (LoRA rank, LR), build a run registry. Use for hyperparameter ablations or picking an early-stop epoch.
Frequently asked questions
What are Data & Analytics agent skills?
Data agent skills make AI agents useful for data work: writing SQL, cleaning datasets, building pipelines, working with spreadsheets, and producing analyses. Each skill is a reviewed SKILL.md file that teaches the agent one workflow well, ready to install in seconds.
Which Data & Analytics skills are most installed?
Popular Data & Analytics skills on SkillMD right now include excel-xlsx, er-diagram-extractor, officecli-xlsx. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Data & Analytics skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.