메뉴
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.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
Sync the overleaf/ folder with the current content of paper/. Copies all LaTeX source, figures, tables, appendix, and bibliography. Puts the model section as overleaf/model.tex (top-level) for easy coauthor access. Run whenever paper/ changes and you want to push to Overleaf.
RA onboarding audit — explore all project folders and code, inspect data files directly, and produce a structured project-state document that enables a clean restart. Use at the start of a project hand-off or when picking up work from multiple prior contributors.
Full bibliography audit for an academic paper. Verifies every citation is (1) structurally correct in the .bib file, (2) actually cited in the paper, and (3) a real publication — author names, year, journal, and title verified via web search. Flags hallucinated or inaccurate references.
Design identification strategy by dispatching the causal-strategist agent (proposer) and identification-critic agent (critic). Produces strategy memo, pseudo-code, robustness plan, and falsification tests. Use when asked to "identify the effect", "design the strategy", or "write the strategy memo".
Show current context status and session health. Use to check how much context has been used, whether auto-compact is approaching, and what state will be preserved.
Show the current research pipeline status for the active project, or display the pipeline guide for a specific project type. Reads the research spec, research journal, and active plans to determine phase, scores, and next steps.
SOC 직업 분류 기준
| name | new-project |
| description | 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. |
| disable-model-invocation | true |
| argument-hint | [research topic or 'interactive' for guided start] |
| allowed-tools | ["Read","Grep","Glob","Write","Edit","Bash","Task","WebSearch","WebFetch"] |
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.
Read project_type from the research spec produced in Step 1, then follow the matching path:
project_type | Skills to Run | Skills to Skip |
|---|---|---|
empirical | /find-data → /identify | /theory-model, /structural-estimation |
theory | /theory-model | /find-data, /identify, /data-analysis, /structural-estimation |
structural | /find-data → /theory-model → /structural-estimation | /identify |
empirical+theory | /find-data → /theory-model → /identify | /structural-estimation |
Branching logic:
empirical:
3. Run /find-data — Explorer + data-quality-surveyor
4. Run /identify — causal-strategist + econometrics-critic
Gate: Strategy memo score >= 80
theory:
3. Run /theory-model — econ-finance-theorist + econometrics-critic
Gate: Theory model score >= 80. Skip to Step 3b (paper drafting only).
structural:
3. Run /find-data — Explorer + data-quality-surveyor
4. Run /theory-model — econ-finance-theorist + econometrics-critic
5. Run /structural-estimation — structural-estimation-expert + econometrics-critic + debugger
Gate: All three scores >= 80
empirical+theory:
3. Run /find-data — Explorer + data-quality-surveyor
4. Run /theory-model — econ-finance-theorist + econometrics-critic (theory predictions drive empirical design)
5. Run /identify — causal-strategist + econometrics-critic
Gate: Theory model and strategy memo both >= 80
3a. Code (skip for theory):
Run /data-analysis — Coder writes scripts, Debugger reviews code.
3b. Paper (all types):
Run /draft-paper — Writer drafts sections, Humanizer pass strips AI patterns.
Gate: Code must pass Debugger review (if applicable). 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.