quality-gate
Verify that paper claims match analysis outputs before submission.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Verify that paper claims match analysis outputs before submission.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
End-to-end empirical data analysis workflow for R or Python projects.
Find and assess datasets for a research question.
Repository-wide consistency audit for skills, hooks, rules, and docs.
Systematic literature review workflow using parallel librarian agents.
Structured interview and project-spec workflow for new research ideas.
Proofreading workflow for academic manuscripts and papers.
| name | quality-gate |
| description | Verify that paper claims match analysis outputs before submission. |
Cross-check every numerical claim in the paper against analysis output files. Reports only — never edits.
Input: $ARGUMENTS — path to the paper draft, or leave blank to auto-detect.
If $ARGUMENTS is provided, use that path. Otherwise glob for:
manuscripts/**/*.texmanuscripts/**/*.qmdmanuscripts/**/*.mdIf multiple drafts are found, use request_user_input in Plan mode for a single-choice prompt when there are 2-3 clear candidates; otherwise ask conversationally. For the question UI:
Read the full manuscript and extract every quantitative claim:
Record location (section, paragraph, line number if available) for each claim.
Glob for all output files:
output/tables/**/*.tex — regression and summary tablesoutput/tables/**/*.html — HTML versionsoutput/figures/**/*.pdf, output/figures/**/*.png — figuresoutput/**/*.rds, output/**/*.pkl, output/**/*.parquet, output/**/*.csv — saved objectsBuild an inventory with file paths and sizes.
Read agents/verifier.md and use it as the base verification protocol.
By default, perform the verification inline. If the user explicitly requested delegated verification, you may run the verifier as a separate subagent. In either case, use:
Verifier prompt: "You are the verifier agent. Paper draft: [path].
Bibliography: [bib path].
CLAIMS TO VERIFY:
[paste the full claims list from Step 2]
OUTPUT FILE INVENTORY:
[paste the inventory from Step 3]
Verify each claim against the output files. Then do a reverse check —
find output files NOT referenced in the paper. Then check all citation
keys against the bibliography. Follow the verifier agent instructions
and return your full verification report."
After the verification pass completes, collect its results:
Create quality_reports/ if it is missing before saving.
Save to quality_reports/quality_gate_[YYYY-MM-DD]_[paper-name].md:
# Quality Gate Report: [Paper Name]
**Date:** [YYYY-MM-DD]
**Paper:** [file path]
## Verdict: PASS / CONDITIONAL PASS / FAIL
PASS = all claims matched, no missing citations, no unexplained unreferenced outputs
CONDITIONAL PASS = minor unverified claims or informational unreferenced outputs
FAIL = unverified critical claims or missing citations
---
## Claim Verification
| Claim | Location | Found in Output? | Source File | Status |
|-------|----------|-----------------|-------------|--------|
| β = 0.23 (SE = 0.04) | Section 4, para 2 | Yes | output/tables/main_regs.tex | MATCHED |
| N = 4,521 | Table 2 note | Yes | output/tables/main_regs.tex | MATCHED |
| 42% of firms | Intro, para 1 | No | — | UNVERIFIED |
---
## Unreferenced Outputs
Files in output/ not referenced in the paper:
| File | Size | Recommended Action |
|------|------|-------------------|
| output/tables/robustness_het.tex | 4.2 KB | Reference in Section 7 or explain exclusion |
---
## Missing Citations
| Key | Used At | Status |
|-----|---------|--------|
| SmithJones2021 | Section 3, para 1 | NOT IN BIBLIOGRAPHY — CRITICAL |
---
## Summary
- Claims verified: N / M total
- Claims unverified: K (see table above)
- Unreferenced outputs: J
- Missing citations: L
## Recommended Actions (Priority Order)
1. [BLOCKING] ...
2. [RECOMMENDED] ...