Set up a new autonomous research project. Interviews you with 11 questions, then generates the full project scaffold (specs, roadmap, tasks, schemas, execution protocol). Use when starting any research project.
Synthesize research findings into the final deliverable. Reads all data files, generates executive summary, key findings, gaps, and recommendations. Use when all phases are complete.
Show research progress dashboard. Displays completed/failed/remaining task counts, phase status, data completeness, and recent changelog entries.
Self-improvement loop for research quality. Evaluates completed research tasks against binary eval criteria, identifies failure patterns, mutates the researcher subagent instructions, re-runs a sample of failed tasks, and keeps the improved version if score…
Execute the next batch of research tasks autonomously. Reads todo.md, spawns subagents for each task, verifies output, and loops until the current phase is complete or a stop condition is hit. Use after /dr-new has scaffolded the project.
Resume research after a crash or new session. Reads changelog to find last completed task, shows what was done and what remains, then offers to continue.
Validate research data quality. Checks output files against schemas, flags NOT_FOUND clusters, incomplete entries, conflicting sources, and suspicious data. Use after a phase completes.