By hanhuark
Iterative reviewer-author manuscript revision workflow with verification and human-pause conditions.
An iterative manuscript improvement skill for virtual peer review, author revision, verification, and re-review.
The workflow treats manuscript improvement as a closed loop:
The pause condition is central: the skill should stop and ask the researcher when progress requires new data, experiments, simulations, images, datasets, theory, modeling, confidential decisions, or author judgment.
By default, the skill should not stop after the first review report. Unless the user asks for review-only output, it should complete at least one full cycle: review, revise, verify, and re-review.
flowchart TD
A["Manuscript + target journal"] --> B["Reviewer Agent<br/>Critique + recommendation"]
B --> C["Author Agent<br/>Revise manuscript + response log"]
C --> D["Verifier Agent<br/>Check claims, citations, figures, and build"]
D --> E["Reviewer Agent<br/>Re-review revised manuscript"]
E --> F{"Acceptable?"}
F -- "Yes" --> G["Stop<br/>Ready or near-ready"]
F -- "No, revision possible" --> C
F -- "No, missing information" --> H["Pause<br/>Ask human for data, decisions, or theory"]
H --> C
Install directly from GitHub:
codex skills install github:hanhuark/reviewer-author-loop-skill
Or copy the skill folder into your Codex skills directory:
mkdir -p ~/.codex/skills
cp -R skills/reviewer-author-loop ~/.codex/skills/
skills/reviewer-author-loop/: reviewer-author-verifier workflow for manuscript revision./reviewer-author-loop:reviewer-author-loopExample prompt:
Use the reviewer-author-loop skill on this manuscript. Act first as a reviewer, then revise as the author, verify the changes, and continue until the manuscript is acceptable or human input is needed.
This skill is designed as a process scaffold. It can cite or coordinate with other skills when available:
academic-paper-reviewer for independent peer-review style critique.academic-paper for manuscript structure and prose revision.deep-research for targeted literature checks.mechanical-engineering-research or another domain skill for field-specific judgment.documents:documents for DOCX editing and rendering.spreadsheets:Spreadsheets for data tables and analysis.zotero:Zotero for reference management.Private manuscripts, reviewer reports, unpublished data, grant proposals, and confidential comments should only be used for the current task. Do not copy private text into reusable examples, public repositories, or skill files. Convert lessons from private materials into abstract process rules with no identifiable titles, names, manuscript IDs, wording, or facts.
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub hanhuark/reviewer-author-loop-skillThermal-fluid mechanical engineering research workflow for CFD review, correlation checks, experiment planning, literature review, technical writing, data analysis, presentations, proposals, research coding, and AI/ML-assisted workflows.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows