跳到主要内容
知仓学习社ZHICANG

submit

Submission pipeline — journal targeting, replication package, audit, and final gate. Replaces /submit, /target-journal, /audit-replication, /data-de…

不碰外部(只输出文字)无严重或高危命中brycewang-stanford/Auto-Empirical-Research-Skills

它会碰到什么

扫了多少1 个文本文件,2 KB
它会碰到什么不碰外部(只输出文字)
命中总数0 处
命中统计严重 0 · 高 0 · 中 0 · 低 0

这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。

技能内容

Submit

Submission pipeline with four modes covering journal selection through final verification.

Input: $ARGUMENTS — mode keyword, optionally followed by journal name.


Modes

/submit target — Journal Targeting

Get ranked journal recommendations.

Agent: Orchestrator (journal selection function)

Considers: contribution fit, methodology fit, audience fit, recent publications, desk rejection risk. Consults .claude/references/domain-profile.md for journal tiers.

Output: Ranked list of 3 target journals with rationale.

Save to quality_reports/journal_recommendations_[date].md

/submit package — Build Replication Package

Assemble AEA-compliant replication package.

Agents: Coder + Verifier

Produces:

  • Master script that runs all analyses end-to-end
  • README with data sources, computational requirements, instructions
  • Data documentation and codebook
  • Organized file structure per AEA standards

Save to paper/replication/

/submit audit — Audit Replication Package

Verify replication package completeness.

Agent: Verifier (submission mode — 10 checks)

Checks:

  1. Master script exists and runs
  2. All tables reproduce
  3. All figures reproduce
  4. README complete
  5. Data documentation present
  6. Numbered script order
  7. Dependencies listed
  8. Runtime documented
  9. Output paths match paper references
  10. No hardcoded paths

/submit final [journal] — Final Submission Gate

Full verification + score enforcement + submission checklist.

Workflow:

  1. Run comprehensive review if not done recently
  2. Run replication audit
  3. Check score gate: aggregate >= 95, all components >= 80
  4. If PASS: generate cover letter draft + submission checklist
  5. If FAIL: list blocking issues and stop

Principles

  • Score >= 95 + all components >= 80. No exceptions.
  • Don't skip verification. Even if reports exist, check they're recent.
  • If it fails, stop. Don't generate materials for a failing paper.
  • Cover letter is a draft. User must review before sending.

想直接用这个技能?

本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。

同名技能的其他版本

有 2 个不同仓库或目录里都有叫 submit 的技能。它们内容并不相同,别混用: