claudecodex

paper-loop

Lean academic research workflow for economics and finance: idea formation, literature check, project planning, model derivation, drafting, four-reviewer multi-agent review (generalists + econometrics + theory specialists), scoring, and PDF compilation.

1 on GitHubby Chenghangv4.0.0updated 5 months agoproductivity
/

Plugin paper-loop from marketplace paper-loop-local in chenghang1989/Paper-Loop. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (11)

  • academic-writing

    Lean bilingual academic writing guide for economics and finance manuscripts. Use when drafting or revising English or Chinese paper sections and when the user needs clear contribution framing, evidence-driven paragraphing, and compact journal-style prose.

  • data-pipeline

    Build, extend, or debug reproducible empirical data pipelines for paper projects, including variable construction, merges, diagnostics, summary tables, and output artifacts tied to paper-spec.md.

  • full-loop

    Run multiple Paper Loop write rounds in Codex with early stopping, compact context discipline, score progression tracking, and remaining blocker synthesis.

  • idea-formation

    Turn a seed topic into 2-3 researchable economics or finance paper ideas, stress-test each through an adversarial finance-rubric critique, recommend the strongest one, update paper-spec.md when the user chooses, and save logs/idea-note.md plus logs/idea-critique.md.

  • init-paper

    Initialize a Codex-native economics or finance paper workspace. Use when the user asks to init paper, create a research project skeleton, set up paper-spec.md, AGENTS.md, reviews, logs, latex, code, data, output, references, or the standard Paper Loop project structure.

  • literature-novelty

    Targeted literature search and novelty assessment for economics and finance papers. Use when the user needs related papers, closest prior work, overlap assessment, or a fast novelty check without loading a full literature review into context.

  • novelty-check

    Check a paper idea against nearby economics and finance literature, identify the closest papers, judge overlap risk, and write logs/novelty-check.md.

  • referee-report

    Draft a structured referee report for an academic paper from a PDF, manuscript, or text file, with major concerns, minor concerns, actionable revision suggestions, and recommendation.

  • research-core

    Codex-native umbrella workflow for economics and finance paper projects. Use when the user needs workspace setup, idea formation, novelty checks, data pipelines, drafting rounds, full-loop academic automation, review synthesis, referee reports, or round-by-round scoring.

  • review-status

    Report the current Paper Loop review trajectory from reviews/scoreboard.md and the latest scorecard, including blockers, score trend, and next action.

  • write-round

    Run one Codex-native drafting or revision round for an economics or finance paper: plan, revise, create independent review passes, synthesize a scorecard, and update reviews/scoreboard.md.

Slash commands (8)

  • /paper-loop:data-pipeline

    Build or extend data processing pipeline for empirical analysis.

  • /paper-loop:full-loop

    Run several write-review rounds in sequence until the draft is stable.

  • /paper-loop:idea-formation

    Turn a seed topic into 2-3 researchable paper ideas, stress-test each through a Codex expert critique, and populate paper-spec.md once one is chosen.

  • /paper-loop:init-paper

    Initialize a lean paper workspace with the core files and folders.

  • /paper-loop:novelty-check

    Check the paper idea against the closest recent literature and record the overlap risk.

  • /paper-loop:referee-report

    Draft a structured referee report for a paper under review.

  • /paper-loop:review-status

    Show the current review trajectory, latest blockers, and next action from the scorecard files.

  • /paper-loop:write-round

    Execute one drafting or revision round with multi-model cross-review and a unified scorecard.

Subagents (4)

  • review-a

    Run Review A (research rigor and evidence quality) on the current manuscript. Uses the Codex CLI for independent assessment of question, identification, and evidence.

  • review-b

    Run Review B (writing quality and positioning) on the current manuscript. Uses Antigravity CLI (`agy`) for independent assessment of structure, flow, and interpretation. The underlying model is still Gemini; Antigravity CLI superseded the standalone `gemini` CLI in 2026.

  • review-c

    Run Review C (econometric rigor and code/data execution) on the current manuscript. Specialist reviewer that actually opens code/, output/, and the data registry to verify that the empirical claims survive code-level scrutiny. Authoritative on the "Evidence and code" dimension.

  • review-d

    Run Review D (theoretical model and derivation correctness) on the current manuscript. Specialist reviewer for asset-pricing and corporate-finance theory: SDF derivations, Euler equations, no-arbitrage / HJ-bound reasoning, contracting models, optimization first-order conditions, comparative statics

View source on GitHub

Similar plugins

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

pake

claudecodex

Package any website or local web build into a lightweight desktop app with Pake CLI.

1 skill

tw93/Pake 63,463

Maintain paper-loop?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted