菜单
Validate replication package by dispatching the replication-verifier agent in submission mode (checks 1-10). Runs master script, cross-references tables and figures against paper, verifies README completeness for AEA Data Editor compliance. Use before data deposit or journal submission.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
| name | audit-replication |
| description | Validate replication package by dispatching the replication-verifier agent in submission mode (checks 1-10). Runs master script, cross-references tables and figures against paper, verifies README completeness for AEA Data Editor compliance. Use before data deposit or journal submission. |
| disable-model-invocation | true |
| argument-hint | [replication package directory OR 'here' for current project] |
| allowed-tools | ["Read","Grep","Glob","Write","Bash","Task"] |
Run end-to-end validation by dispatching the replication-verifier agent in submission mode (all 10 checks).
Input: $ARGUMENTS — directory containing the replication package. Use here or no argument for the current project.
$ARGUMENTS is a directory path: use it$ARGUMENTS is here or empty: use Replication/ if it exists, otherwise project rootDelegate to the replication-verifier agent via Task tool:
Prompt: Audit the replication package at [directory].
Mode: Submission (all 10 checks).
Paper location: paper/main.tex (if exists).
Standard Checks (1-4):
1. LaTeX compilation
2. Script execution
3. File integrity
4. Output freshness
Submission Checks (5-10):
5. Package inventory (scripts numbered, master script exists)
6. Dependency verification (renv.lock, sessionInfo, package versions)
7. Data provenance (sources documented, no hardcoded paths)
8. Execution verification (run master script end-to-end)
9. Output cross-reference (every table/figure traced to script)
10. README completeness (AEA format)
Save report to quality_reports/replication_audit_[date].md
If execution errors are found (Check 8):
# Replication Audit Report
**Date:** [YYYY-MM-DD]
**Mode:** Submission
## Check Results
| # | Check | Status | Details |
|---|-------|--------|---------|
| 1 | LaTeX compilation | PASS/FAIL | |
| 2 | Script execution | PASS/FAIL | |
| 3 | File integrity | PASS/FAIL | |
| 4 | Output freshness | PASS/FAIL | |
| 5 | Package inventory | PASS/FAIL | |
| 6 | Dependencies | PASS/FAIL | |
| 7 | Data provenance | PASS/FAIL | |
| 8 | End-to-end execution | PASS/FAIL | |
| 9 | Output cross-reference | PASS/FAIL | |
| 10 | README completeness | PASS/FAIL | |
## Summary
- Checks passed: N / 10
- **Overall: PASS / FAIL**
- Blocking issues: [list]
- Positive findings: [list]