Research & Analysis Agent Skills
Compare the best open-source agent skills for research & analysis. Deep research, reports and insight generation. Ranked by GitHub stars, with install commands, what each one can touch and scan reports where available.
SDYJ Multi Agents
A LangGraph-powered multi-agent deep research system featuring task planning, human-in-the-loop review, multi-source retrieval, evidence-grounded report generation, full tracing and reproducible evaluation.
Claude Skills Supercharged
A "supercharged" implementation of Claude Code Skills – using Haiku prompt analysis/critical skill scoring and skill auto-injection for friction-free, context-driven workflows.
Unhinged Claude Skills
25 Claude Code skills with names that sound like a police report and uses that save real hours.
Claude Mountaineering Skills
Automates mountain route research for North American peaks. Aggregates data from 10+ mountaineering sources to generate detailed route beta reports with weather, avalanche conditions, and trip reports.
Trustabl Cursor
Agent Reliability Analyzer MCP server for Cursor: find agent reliability issues in MCP servers
Nicar2026 Skills In Codex Claude
Materials for NICAR 2026 session on using "skills" to aid in more reliable, reproducible analysis tasks when using Codex and Claude Code
Q Claude Skills
A collection of Claude skills organized by how I think, decide, research and build.
Claude Skills Collection
Custom skills and agents for Claude Code - codebase research, context management, and implementation planning workflows
List refreshed November 15, 2026. Data comes from public GitHub repositories.