Best Data & Analytics Skills for Claude Code
Skills for data analysis, SQL, ML pipelines, and experiment statistics. Evaluated on six dimensions with public scorecards — trigger quality through security.
The best data analytics skills for Claude Code, ranked by six-dimension evaluation: vercel-optimize (9.4/10), debugging-wizard (9.3/10), roblox-datastores (9.3/10), roblox-luau (9.3/10), replica-recon (9.2/10). Every score has published rationale. How we score →
Install the top 3 in one line
curl -fsSL https://skill123.me/install/vercel-optimize.sh | bash
curl -fsSL https://skill123.me/install/debugging-wizard.sh | bash
curl -fsSL https://skill123.me/install/roblox-datastores.sh | bash
Verified evaluation, one-line install. Or tell your agent: install the data & analytics skill from skill123.me.
Use for Vercel cost and performance optimization on deployed projects, especially Next.js, Svelte…
Exceptional observability-first pipeline skill: deterministic gates, sub-agent fan-out, verification and sanitizer loops, execFile-only shell-outs with token redaction; only flaws are missing When-Not and bundled README/CONTRIBUTING files.
Parses error messages, traces execution flow through stack traces, correlates log entries to iden…
Excellent debugging skill: five-step workflow backed by a four-phase root-cause methodology, concrete pdb/dlv/git-bisect commands, evidence-required output template; only lacks an explicit When-Not boundary.
Persist player data in Roblox with DataStoreService: GetDataStore, GetAsync/ SetAsync/UpdateAsync…
Script a Roblox experience in Luau: get services, create and parent Instances, connect events, ru…
Reverse-engineers any app into a recon map: screen inventory, user flows, component list, inferre…
Entry stage of the replica-* suite: reverse-engineer an app into a recon map (screen inventory, flows, components, inferred data model with evidence and confidence, feature matrix, honest out-of-scope list, sizing) from public sources and the user's own account, using two bundled templates (recon-map.md, features.csv). The access-ethics guard rails are the strongest of the pack: own account only, never bypass paywalls or logins, no scraping or bulk downloads, no JS bundles or decompiled binaries or endpoint sniffing, explicit ToS check for competing-product clauses, screenshots kept as reference and never shipped. Same structural nit: templates at skill root instead of assets/.
Track which of your LinkedIn comments earned author replies. Flags the 6-24h warm-reply window wh…
Tracks the user is own comments and author replies via no-cookie public Apify actors, classifies hot/warm/cool/dormant with a timing matrix, and routes warm threads to reply-handler. Paste fallback without token; all data stays local with only Apify seeing requests; inline injection defenses.
Maps every competitor and the gap they leave. Finds the direct competitors, indirect ones and the…
Competitor-research skill: 4-step workflow (direct/indirect/substitute mapping, fact table with links, review-complaint themes, positioning map + gap). Strong anti-hallucination discipline (public sources only, every fact linked, never invent, quotes verbatim, thin themes marked). Single-file design; no explicit When-Not in description.
Direct access to Google's own SEO data via Search Console (Search Analytics, URL Inspection, Site…
Designs and implements production-grade ML pipeline infrastructure: configures experiment trackin…
Excellent MLOps reference skill with strong progressive disclosure, runnable templates, validation gates, and clean security; only gap is missing When-Not boundary in description.
Performs pandas DataFrame operations for data analysis, manipulation, and transformation. Use whe…
Well-crafted pandas skill: workflow embeds concrete assess and assert-based validation snippets, merge patterns use validate and indicator checks, and before/after examples enforce vectorized idioms; description lacks When-Not.
Score comparison
How the top 10 compare across the six evaluation dimensions (0–10). Full written rationale for every score is on each skill's page.
| Skill | Overall | Trigger | Structure | Workflow | Content | Engineering | Security |
|---|---|---|---|---|---|---|---|
| vercel-optimize | 9.4 | 8.5 | 8.7 | 10.0 | 9.0 | 10.0 | 10.0 |
| debugging-wizard | 9.3 | 8.5 | 9.3 | 8.8 | 10.0 | 10.0 | 10.0 |
| roblox-datastores | 9.3 | 9.0 | 9.0 | 9.0 | 9.5 | 9.0 | 10.0 |
| roblox-luau | 9.3 | 9.5 | 9.0 | 9.0 | 9.5 | 9.0 | 9.5 |
| replica-recon | 9.2 | 8.0 | 8.0 | 9.6 | 10.0 | 10.0 | 10.0 |
| linkedin-thread-monitor | 9.1 | 9.5 | 9.3 | 8.4 | 9.0 | 9.0 | 9.5 |
| founder-competitors | 9.1 | 8.0 | 8.0 | 9.2 | 10.0 | 10.0 | 10.0 |
| seo-google | 9.1 | 8.5 | 9.0 | 9.0 | 9.5 | 9.0 | 9.5 |
| ml-pipeline | 9.0 | 7.5 | 10.0 | 8.4 | 9.0 | 10.0 | 10.0 |
| pandas-pro | 9.0 | 8.0 | 10.0 | 8.0 | 9.0 | 10.0 | 10.0 |
FAQ
What is a data analytics skill for Claude Code?
A package that teaches your agent a data workflow — pandas analysis, SQL query generation, A/B test statistics. Your agent loads it when your request matches.
Can these skills access my databases?
Only through the credentials and connections you configure. The skills here were scanned: none read credential stores undeclared, none exfiltrate data to external endpoints.
Which one should I start with?
pandas-pro for dataframes, postgres-pro for SQL. Both scored 9+ on workflow design — they verify their own output.
Every skill here was scored on the same six-dimension rubric — the full scorecard with written rationale is on each skill's page. Browse the full Data & Analytics skills collection (including skills outside the top 10), or see all Data & Analytics skills.