Full research pipeline from idea to paper. Orchestrates all phases — interview, literature review, data discovery, identification strategy, analysis, paper drafting, and peer review. Use when starting a new research project from scratch.
Launch a full research pipeline from idea to paper, orchestrated through the dependency graph.
Input: $ARGUMENTS — a research topic or interactive for a guided start via /interview-me.
This skill orchestrates the full v3 dependency graph. Each phase activates when its dependencies are met. The orchestrator manages agent dispatch, three-strikes escalation, and quality gates.
Phase 1: Discovery
├── /interview-me → Research Spec + Domain Profile
└── /lit-review → Literature Synthesis + BibTeX
Phase 2: Strategy (depends on Phase 1)
├── /find-data → Data Assessment
└── /identify → Strategy Memo + Robustness Plan
Phase 3: Execution (depends on Phase 2)
├── /data-analysis → Scripts + Tables + Figures
└── /draft-paper → Paper Sections
Phase 4: Peer Review (depends on Phase 3)
├── /review-paper → Referee Reports + Editorial Decision
└── /paper-excellence → Aggregate Score
Phase 5: Submission (depends on Phase 4, score >= 95)
├── /target-journal → Journal Recommendations
├── /data-deposit → Replication Package
└── /submit → Final Verification
If interactive or no research spec exists:
Run /interview-me to produce:
quality_reports/research_spec_*.md).claude/rules/domain-profile.md) — if still templateRun /lit-review with the research topic:
Gate: Research spec and literature review must exist before proceeding.
Run /find-data to identify and assess datasets:
Run /identify to design the empirical strategy:
Gate: Strategy memo must pass Econometrician review (score >= 80).
Run /data-analysis to implement the strategy:
Run /draft-paper to write up results:
Gate: Code must pass Debugger review. Paper sections must exist.
Run /paper-excellence for comprehensive review:
Run /review-paper for simulated peer review:
Gate: Aggregate score >= 80 (commit-ready). Score >= 90 for submission.
/target-journal for journal recommendations/data-deposit for replication package/submit for final verificationThe pipeline pauses for user input at these points:
Between pauses, the orchestrator runs autonomously per orchestrator-protocol.md.
/new-project always runs through the full pipeline.