Data & Analytics

owid Skill

Create or edit an ETL-authored Grapher chart — a single-chart `.config.yml` in `etl/steps/viz/chart/`. Use when the user wants to author a chart from ETL, edit one, change its title/subtitle/colors/map settings, or preview an ETL-authored chart on staging. For charts with dropdowns (multi-dimensional), use the `create-multidim` skill instead.

owid Skill

Profile and optimize ETL step performance — CPU time, memory usage, and I/O bottlenecks. Use when an ETL step is slow, uses too much memory, or when the user asks to profile, optimize, or speed up a step. Covers profiling commands, categorical dtype optimization, vectorization, SUBSET filtering for fast dev runs, and iterative diagnose→fix→reprofile workflow.

owid Skill

Resolve Dependabot security alerts on owid/etl by upgrading vulnerable dependencies. Use when the user mentions "dependabot", "security alerts", "vulnerability", "CVE", "security fixes", "dependabot alerts", or wants to fix vulnerable packages. Also trigger when the user pastes a GitHub Dependabot URL or asks about outdated/insecure dependencies.

owid Skill

Author or modify an Our World in Data explorer (multi-dimensional dashboard with dropdown selectors, published from ETL via `viz://explorer/<ns>/latest/<short>`). Trigger when the user wants to build a new explorer, add/remove views or dimensions on an existing one, change the explorer's chart text or selection defaults, or finish an explorer migration once the snapshot/garden/grapher chain is already in place.

owid Skill

Create vanilla meadow, garden, and grapher ETL step files by invoking the wizard's cookiecutter templates, given a snapshot path.

owid Skill

Query the grapher MySQL database (local dev, a branch's staging server, or production via the public Datasette) and verify indicators and charts on a staging server. Use when you need to run SQL against grapher, find which charts use an indicator, assess the blast radius of a data fix, or check that a chart/indicator renders correctly on staging-site-<branch>.

owid Skill

Draft answers for OWID's data-updates-comms Slack template using snapshot DVC + garden metadata + staging DB queries. Use when the user wants to fill the "Message about new data update" form, announce a dataset update to the internal #data-updates-comms channel, or generate the FAQ-style Slack post after an ETL update. Mechanical fields (producer, dates, coverage, chart count, search URL) are filled directly; editorial fields (why it matters, caveats, what's interesting about this update) get prompts seeded with extracted context for the user to refine. This is the INTERNAL Slack form only — for the public reader-facing "Data update" post on ourworldindata.org/latest, use /data-update-announcement instead.

owid Skill

Sync upstream grapher schema changes (new chart types, config fields, enum values) into the ETL repo — vendored schema, multidim-schema, dataset-schema, and regenerated Python types. Use when the scheduled sync workflow opened a draft PR or issue that needs completing, when the web team announces a grapher schema change ("new chart type in Grapher", "I added a field to the grapher config"), when someone asks to "sync the grapher schema", or when grapher configs fail ETL validation on fields that work fine in the grapher admin.

owid Bundle

Check user-facing indicator and chart metadata (titles, subtitles, descriptions, description_key/WYSK, display names) against OWID's Writing and Style Guide. Use when the user mentions the style guide, writing guide, chart copy quality, title/subtitle/WYSK review, or after editing any .meta.yml under etl/steps/data/ — garden or grapher. Most user-facing text is authored in garden and inherited by grapher; this skill reads the resolved metadata off the built grapher dataset, so garden-authored text is in scope.

owid Bundle

Take (soon-to-sunset) OWID explorers to redirected MDIMs, end to end. Maps each explorer's views to the views of one or more replacement MDIMs, writes ONE apply-ready JSON payload per explorer for the admin bulk-redirect endpoint, audits every article that links or embeds each explorer (with the view each link will land on) plus the featured metrics pointing at it, preflights every validation the endpoint performs — including site redirects that would block it — and covers retiring the explorer's ETL step afterwards. Trigger when the user says "map explorer <slug> to mdim(s) <...>", "suggest explorer->MDIM redirects", "we're sunsetting the <slug> explorer, map its views to the new multidims", "redirect these explorers to MDIMs", or similar.

owid Skill

Migrate a non-ETL CSV-based explorer (data lives in a static CSV hosted in `owid-grapher/public/explorers/` or on GitHub; explorer config has `tableSlug`/`table` blocks) into ETL by adding a snapshot → meadow → garden → grapher chain, then handing off to `/create-explorer` for the explorer step. Trigger when the user says "bring CSV explorer <slug> into ETL", or refers to fish-stocks (the only remaining target).

owid Bundle

Find every OWID surface that references a chart, indicator, MDIM, or explorer — articles (links vs embeds), explorers, narrative charts, data insights, static viz, key-chart slots, MDIM views. Answers "what breaks or goes stale if this changes or goes away", and distinguishes surfaces a URL redirect fixes from surfaces that render the object themselves. Read-only, pure SQL. Trigger when the user asks "what references this chart/indicator", "where is this chart embedded", "what's the blast radius of this change", "which articles link to X", "what do I have to update if I retire this chart", or when another skill needs the surface sweep (map-charts-to-mdim, check-empty-entities, check-hardcoded-years, update-dataset).

owid Skill

Check rendered metadata (titles, subtitles, footnotes, descriptions, display names) for spacing issues caused by Jinja/Jinja2 templates. Use when user mentions spacing, whitespace, Jinja rendering, or wants to verify metadata renders cleanly after editing any .meta.yml under etl/steps/data/ — garden or grapher.

owid Skill

Adversarially review an ETL dataset's data and metadata for factual accuracy — verifies metadata claims against the producer's own documentation (fetched from the links in snapshot .dvc files and metadata texts) and cross-checks anomalous plus anchor values against independent sources online, to catch unit errors, wrong-year values, and hard-to-detect mistakes made by the source itself. Use when the user asks to "adversarially review a dataset", "fact-check this dataset", "verify the data against the source", "cross-check the values", or as the factual-accuracy step inside /update-dataset, /create-dataset, and /review-data-pr.

owid Skill

Check ETL step files for outdated coding patterns and offer to fix them. Use when user mentions outdated practices, legacy code patterns, modernizing steps, or wants to check code quality of ETL steps.

owid Skill

Translate a non-ETL explorer (lives in MySQL `explorers` table; TSV mirrored in `owid-grapher/explorers/`) whose `graphers` block references variable IDs or chart IDs into the inputs `/create-explorer` needs. Resolves IDs to catalog paths, pulls per-chart config when needed, and produces the dimension + view layout. Trigger when the user says "bring <slug> explorer into ETL", "migrate grapher explorer <slug>", or refers to one of: energy, co2, democracy, global-health, food-prices, fertilizers, natural-disasters, food-footprints, plastic-pollution, conflict-data, conflict-data-source, countries-in-conflict-data.

owid Skill

Use when creating or enriching metadata for OWID ETL datasets - generates comprehensive YAML metadata from dataset inspection, data exploration, and web research following OWID metadata standards. Trigger when writing or editing *.meta.yml files, when a garden step has empty or minimal metadata, or when user asks to improve/add/enrich metadata.

owid Bundle

Log the analytics reports sent to OWID's data producers, and the producers' replies, into the shared Notion reports log: one row per email, incrementally and without duplicates. Use after sending a round of producer analytics reports, or when the user says "log the report emails" or asks whether a producer ever replied to a report. Searches only the addresses recorded in the contacts table, only for report threads, and asks before writing anything. Runs against the caller's own mailbox only.

owid Skill

Fix ghost variable warnings by remapping charts from old to new variable IDs. Use when ETL grapher step shows "Variables used in charts will not be deleted automatically", when indicator short_names were renamed and charts still reference old variables, or when the user mentions ghost variables, orphaned indicators, or chart variable remapping.

krzysztofsurdy Bundle

Application security principles and OWASP Top 10 for building secure web applications. Use when the user asks to review code for security vulnerabilities, implement authentication or authorization, handle secrets or API keys, configure security headers, prevent injection attacks (SQL, XSS, CSRF), prepare for a security audit, or respond to a vulnerability report. Covers input validation, data protection, secrets management, session handling, and common security antipatterns.

natuleadan Bundle

Builds a contact-product-organization CRM using CSV files with UUID linking, phone validation, and auto-export to PDF and XLSX.

natuleadan Bundle

Drizzle ORM schema patterns — domain factories, prd_/sys_/tst_ prefixes, FK constraints, vector+HNSW, JSONB+GIN, raw SQL, and the as any bridge.

phazurlabs Bundle

Desktop and enterprise application patterns: data-dense interfaces, dashboards, data tables, keyboard-first interaction, multi-window layouts, and data visualization. Use when designing an admin panel, analytics dashboard, or professional tool with complex workflows.

navanithans Bundle

Laravel maintenance with Zero Data Loss policy, Mongo/SQL debugging.

navanithans Bundle

Laravel scaffolding for SQL or Mongo (Official/Jenssegers), SoftDeletes, API standards.

roodlicht Skill

Rails security review — Brakeman integration, mass-assignment via strong_parameters, SQL injection in ActiveRecord, template injection via html_safe/raw, Devise hardening, credentials.yml.enc, force_ssl and CSP config, recent Rails/Rack CVE patterns.

vchelaru Skill

TMX map file creation and editing for FlatRedBall2. Use when creating or modifying Tiled .tmx level files, placing collision tiles, resizing maps, or adding layers. Covers the base template, StandardTileset tile IDs, layer conventions, and CSV tile data format.

calle-ai Bundle

Create directly usable outbound phone-call Agent Skills that bind source and durable result-output contracts at the right level, connect data such as Google Forms, TikTok Ads, Notion, Airtable, local CSV, or custom systems to an MCP one-off call provider route, compile per-record call goals, enforce safety rules, and configure source writeback, source-adjacent result artifacts, or new local result CSV output.

hallucinaut Skill

Design and document database schemas, migrations, relationships, and constraints. Use when creating database models, designing tables, defining relationships, or working with SQL/NoSQL databases.

igmarin Skill

Use when conducting a security audit, security review, vulnerability assessment, vulnerability check, or secure coding review on Hanami 2.x applications — validate params via the Params DSL in every Action, verify CSRF protection is enabled in config/app.rb, audit authentication checks via explicit `before :authenticate!`, check authorization with role/permission checks, never log passwords/tokens/secrets, use ROM query interface to prevent SQL injection (no string interpolation in `where("...")`), never use `raw` on user input in templates, store secrets in settings not hardcoded, and return generic error messages for auth failures. Validates parameter handling, CSRF, auth integration, XSS, session configuration, and hardening posture.

luizedupp Skill

Master 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.

dirnbauer Bundle

TYPO3 v14 API reference: how to write v14 code. Covers controllers, building a view with ViewFactory, Fluid templates, PSR-14 events that replaced old hooks, backend modules, TCA, QueryBuilder queries without SQL injection, CLI commands and tests. Use when the user asks what a v14 API looks like, which event replaced a hook, how to build or write a specific piece of v14 code, or which class, interface or namespace to use. Does NOT run upgrades or migrations: for a whole project or site upgrade use typo3-upgrade-run, which owns the version constraint, the PHP target and the process.

eoash Skill

**엑셀 업무 자동화**: 한국 직장인이 가장 많이 쓰는 엑셀의 반복 업무를 자동화합니다. 매출 집계표, 급여 계산, 거래처 관리, 데이터 정리/병합, 피벗 분석, 대시보드 생성을 지원합니다. - MANDATORY TRIGGERS: 엑셀 자동화, 매출 집계, 급여 계산, 거래처 관리, 데이터 정리, 피벗, 엑셀 양식, 스프레드시트 자동화, 재고 관리, 매출 분석

eoash Skill

**데이터 분석 리포트 생성기**: 엑셀/CSV 데이터를 분석하여 한국식 보고서 양식의 시각화 리포트를 자동 생성합니다. 경영진 대상 요약 보고서, KPI 대시보드, 인사이트 분석을 포함합니다. - MANDATORY TRIGGERS: 데이터 분석, 데이터 리포트, KPI, 대시보드, 데이터 시각화, 분석 보고서, 매출 분석, 성과 분석, 데이터 보고서, 통계 분석, 트렌드 분석

lovstudio Bundle

微信公众号文章抓取与导出。自动处理 mp.weixin.qq.com 的登录态获取与续期， 支持按公众号搜索、抓取文章列表与正文、按日期窗口导出 Markdown / JSON / CSV。 Trigger when the user wants to crawl a WeChat public account, export recent articles, or 提到 "wcx"、"微信公众号"、"公众号文章"、"mp.weixin"、"抓公众号"、 "crawl wechat official account"、"wxmp"、"最近十天的文章"。

lovstudio Bundle

Extract invoice data from images or text descriptions and generate a categorized Excel expense report. Supports receipt photos, scanned invoices, and manual text input. Auto-classifies into: business entertainment (客户餐费), travel-transport (机票/火车票/打车), travel-accommodation (酒店), travel-meals, office supplies, communication, and other. Use when the user mentions "发票报销", "expense report", "报销单", "发票整理", "invoice", "报销汇总", "发票分类", "reimbursement", or has invoice images to process.