--- title: Top Data & Analytics Skills slug: data-analytics type: primary-category canonical: https://top-agent-skills.com/top-skills-for-data-analytics skills: 21 rubric: 1.0 updated: 2026-09-02 --- # Top Data & Analytics Skills **docling** is the top-ranked data & analytics Skill at 66/100: One skill covering every document format the category exists for — including scanned PDFs and RAG chunking — from the maintainers of the parser itself. Data sources, scientific datasets, BI dashboards, D3 viz patterns, structured extraction. 21 Skills indexed, ranked by a published composite score (https://top-agent-skills.com/about/methodology). Content last changed 2026-09-02. ## The ranking ### 1. docling — score 66/100 (verified-org) One skill covering every document format the category exists for — including scanned PDFs and RAG chunking — from the maintainers of the parser itself. - Best for: Reading or converting documents the agent cannot open directly, at 65K stars and MIT: scanned PDFs, Office formats, tables, and chunking a corpus for retrieval. - Not ideal for: Producing polished Office files. Docling is a reader and converter — for generating a styled DOCX, XLSX or PPTX, the Anthropic document skills are the better fit. - Publisher: Docling project (LF AI & Data) · MIT - Verified on: claude-code, cursor, codex ```bash pip install docling && uvx library-skills --claude ``` Full entry: https://top-agent-skills.com/skill/docling (https://top-agent-skills.com/skill/docling.md) ### 2. azure-ai-contentunderstanding-py — score 56/100 (verified-org) Multimodal extraction across documents, images, audio and video through one Azure client — Microsoft-authored, with an explicit trigger list. - Best for: Teams already on Azure that need structured extraction from mixed media, not just PDFs — the case where a single-format parser leaves half the corpus unread. - Not ideal for: Local or offline processing. It teaches an agent to write correct Azure SDK code, so it needs Azure credentials and sends content to the service. - Publisher: Microsoft · MIT - Verified on: claude-code ```bash npx skills add microsoft/skills --skill azure-ai-contentunderstanding-py ``` Full entry: https://top-agent-skills.com/skill/azure-content-understanding (https://top-agent-skills.com/skill/azure-content-understanding.md) ### 3. speech-to-text — score 56/100 (verified-org) Transcription and subtitle generation as a first-class skill — the media job agents are asked for most and could not previously do well. - Best for: Turning recorded audio or video into text you can act on: subtitles, meeting notes, or a searchable transcript of a media archive. - Not ideal for: Confidential audio that cannot leave your infrastructure — it is a hosted API, so the audio is uploaded. - Publisher: ElevenLabs · MIT - Verified on: claude-code ```bash npx skills add elevenlabs/skills --skill speech-to-text ``` Full entry: https://top-agent-skills.com/skill/elevenlabs-speech-to-text (https://top-agent-skills.com/skill/elevenlabs-speech-to-text.md) ### 4. gtm-eng-skills — score 52/100 (verified-org) Waterfall enrichment as a procedure, not a single provider call. - Best for: GTM engineers who already know no single data provider covers more than 60-75% of contacts and want the chaining, cost-per-hit ordering and identity validation written down. - Not ideal for: Anyone not on Deepline. The skills drive the Deepline CLI and its provider network, so without that account they read as documentation rather than run as workflows. - Publisher: Deepline · MIT - Verified on: claude-code ```bash npx skills add getaero-io/gtm-eng-skills --all ``` Full entry: https://top-agent-skills.com/skill/gtm-eng-skills (https://top-agent-skills.com/skill/gtm-eng-skills.md) ### 5. visualize-data — score 51/100 (verified-org) OpenAI's chart-design skill: the judgement layer that decides which chart the question actually needs before any plotting code is written. - Best for: Getting a chart that answers the question rather than one that displays the data — chart-type choice, encoding, and a QA pass on a figure you already have. - Not ideal for: Library-specific implementation help. It carries visual judgement, not D3 or Vega syntax, so pair it with a plotting library skill when the code is the hard part. - Publisher: OpenAI · MIT - Verified on: codex ```bash npx skills add openai/role-specific-plugins --skill openai-visualize-data ``` Full entry: https://top-agent-skills.com/skill/openai-visualize-data (https://top-agent-skills.com/skill/openai-visualize-data.md) ### 6. build-dashboard — score 51/100 (verified-org) Dashboards with source definitions and a QA step — the parts that separate a monitoring view from a wall of charts nobody trusts. Full entry: https://top-agent-skills.com/skill/openai-build-dashboard (https://top-agent-skills.com/skill/openai-build-dashboard.md) ### 7. deep-research — score 50/100 (official-anthropic) Cited research reports from fanned-out web search with adversarial verification. Full entry: https://top-agent-skills.com/skill/deep-research (https://top-agent-skills.com/skill/deep-research.md) ### 8. firecrawl — score 49/100 (verified-org) Web scraping, search, and browser automation built to be agent-friendly. Full entry: https://top-agent-skills.com/skill/firecrawl (https://top-agent-skills.com/skill/firecrawl.md) ### 9. mapbox-data-visualization-patterns — score 49/100 (verified-org) The geospatial gap, filled by the vendor that defines it: data on a map, done properly. Full entry: https://top-agent-skills.com/skill/mapbox-data-visualization (https://top-agent-skills.com/skill/mapbox-data-visualization.md) ### 10. xlsx — score 48/100 (official-anthropic) Excel spreadsheets with real formulas, charts, and formatting — not flat CSV exports. Full entry: https://top-agent-skills.com/skill/xlsx (https://top-agent-skills.com/skill/xlsx.md) ### 11. life-sciences — score 48/100 (official-anthropic) The official entry point for biomedical research workflows in Claude Code. Full entry: https://top-agent-skills.com/skill/life-sciences (https://top-agent-skills.com/skill/life-sciences.md) ### 12. vibe-prospecting — score 48/100 (verified-org) The top of the funnel: find the company, find the person, enrich the row. Full entry: https://top-agent-skills.com/skill/vibe-prospecting (https://top-agent-skills.com/skill/vibe-prospecting.md) ### 13. mongodb-patterns — score 47/100 (verified-org) MongoDB aggregations and indexing without the foot-guns. Full entry: https://top-agent-skills.com/skill/mongodb-patterns (https://top-agent-skills.com/skill/mongodb-patterns.md) ### 14. carta-cap-table — score 47/100 (verified-org) The equity stack: cap table, 409A history, conversions, exit waterfall. Full entry: https://top-agent-skills.com/skill/carta-cap-table (https://top-agent-skills.com/skill/carta-cap-table.md) ### 15. research-synthesis — score 47/100 (official-anthropic) Turn raw research into themes, segments, and a prioritized next-steps list. Full entry: https://top-agent-skills.com/skill/research-synthesis (https://top-agent-skills.com/skill/research-synthesis.md) ### 16. performance-report — score 47/100 (official-anthropic) Executive-ready performance reports with next-period priorities. Full entry: https://top-agent-skills.com/skill/performance-report (https://top-agent-skills.com/skill/performance-report.md) ### 17. valyu — score 46/100 (verified-org) Web search + 36 authoritative data sources. SEC, PubMed, ChEMBL, FRED — agent-grade research. Full entry: https://top-agent-skills.com/skill/valyu (https://top-agent-skills.com/skill/valyu.md) ### 18. duckdb-skills — score 46/100 (verified-org) In-process analytical SQL over CSV, Parquet, and Excel — no warehouse, no server. Full entry: https://top-agent-skills.com/skill/duckdb-skills (https://top-agent-skills.com/skill/duckdb-skills.md) ### 19. scientific-skills — score 45/100 (community) Scientific computing + dataset APIs. Reproducible research workflows for agents. Full entry: https://top-agent-skills.com/skill/scientific-skills (https://top-agent-skills.com/skill/scientific-skills.md) ### 20. netsuite-finance-analyst — score 43/100 (verified-org) Oracle's own FP&A analyst: variance decomposition, close readiness, board narratives. Full entry: https://top-agent-skills.com/skill/netsuite-finance-analyst (https://top-agent-skills.com/skill/netsuite-finance-analyst.md) ### 21. d3js-skill — score 40/100 (community) D3.js patterns for interactive viz that does not look stock. Full entry: https://top-agent-skills.com/skill/d3js-skill (https://top-agent-skills.com/skill/d3js-skill.md) ## About this category The best agent skills for data and analytics in 2026 are Anthropic's official xlsx Skill for spreadsheet work — preserving formulas, charts, and conditional formatting that pandas drops — and the BI dashboard Skills (Looker, Metabase, Hex) for turning live data into published reports. Data & analytics Skills give agents the chops to handle the full data-team workflow — from messy CSV cleanup to dashboard authoring to scientific dataset analysis. The category covers BI dashboard generation (Looker, Metabase, Hex), structured extraction from PDFs and scraped pages, D3 visualization patterns, jupyter notebook authoring, and ETL Skills that wire data sources together. Common workflows include cleaning malformed spreadsheets into proper datasets, generating SQL for a question, building a chart from a dataset, exploratory analysis in a notebook, extracting tables from PDFs for analysis, and authoring repeatable data pipelines. Several Skills pair with Supermetrics, Ahrefs, Datadog, or other analytics MCP servers so the agent has live data access. The xlsx Skill — Anthropic-authored — anchors the spreadsheet half of this category and frequently shows up in non-analytics workflows too. Data scientists, analytics engineers, BI leads, and product managers running their own analyses use these. Composite scoring weights install count (xlsx and the BI Skills dominate), provenance (Anthropic, well-known data orgs), and how well the Skill handles the messy real-world cases: misplaced headers, encoding issues, mixed types, merged cells. ## Common questions **What does the xlsx Skill do that pandas does not?** It preserves formulas, conditional formatting, merged cells, and chart objects — things pandas drops on read. For analysis, pandas is fine. For creating or editing existing spreadsheets that humans will open, xlsx is the right tool. **Can these Skills query my warehouse?** Pair them with a Supabase, BigQuery or Snowflake MCP server and yes. Standalone Skills generate SQL but do not run it. **Do they handle large datasets?** For multi-gigabyte data, Skills generate the right tooling (DuckDB, polars, Spark snippets) rather than loading everything into the agent's context. **Which Skill is best for jupyter notebooks?** The Anthropic-authored notebook-edit tool plus the data-analysis Skills cover the common cases — read all cells with outputs, edit specific cells, run targeted analyses. **Are BI dashboard Skills cross-platform?** Most target one tool (Looker, Metabase, Hex). Cross-platform support is rare and a sign of a mature Skill — check the compatibility filter. --- _Top Agent Skills. Machine-readable twin of https://top-agent-skills.com/top-skills-for-data-analytics._ _JSON: https://top-agent-skills.com/top-skills-for-data-analytics.json · whole catalog: https://top-agent-skills.com/skills.json (CC BY 4.0)_