Looking for the best data skills for Claude Code and other AI coding agents? This collection ranks 134 open-source data skills by a blend of GitHub popularity, licensing clarity, and how well each one documents what it does. Skills — sometimes called Agent Skills — are small, shareable bundles of instructions that an agent loads on demand to become better at a specific job, so a strong data skill can save you from re-explaining the same context in every session. The highest-ranked entries here, including observability-and-instrumentation, html-ppt-weekly-report, html-ppt-zhangzara-long-table, pair an active repository with a real open-source license, which matters if you plan to adapt or redistribute them. Every listing links straight back to its original repository so you can read the source, check recent activity, and copy the exact install command. We refresh this ranking every week as stars, forks, and new releases change across the ecosystem.
Instruments code so production behavior is visible and diagnosable. Use when adding logging, metrics, tracing, or alerting. Use when shipping any feature that runs in production and you need evidence it works. Use when production issues are reported but you can't tell what happened from the available data.
OpenDesign's weekly growth review: stars, installs, activation — the number, the driver, and the recommended move. Built as a decision-grade data & finance deck for growth & product team.
OpenDesign's unit-economics and BYOK cost model: the assumptions, the sensitivity, and why it scales. Built as a decision-grade data & finance deck for CFO, investors.
Review Archify issues, PRs, or code through value, cost, and impact to support evidence-based maintenance decisions. Use for issue triage, change reviews, and code quality assessments.
Runs Antigravity CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Antigravity CLI or compare its result with another coding agent.
Runs Claude Code non-interactively for code analysis and implementation tasks. Use when the user asks to delegate repository work to Claude Code or compare its result with another coding agent.
Runs Codex CLI non-interactively for code analysis and implementation tasks. Use when the user asks to delegate repository work to Codex or obtain a second coding-agent result.
Runs DeepSeek Harness headlessly for bounded repository tasks. Use when the user asks to delegate analysis or implementation to DeepSeek Harness.
Runs Gemini CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Gemini CLI or compare its result with another coding agent.
Runs OpenCode non-interactively for repository analysis and coding tasks. Use when the user asks to delegate work to OpenCode or compare OpenCode with another coding agent.
Runs Pi non-interactively and parses its JSON event stream for repository tasks. Use when the user asks to delegate a bounded analysis or implementation task to Pi.
