Academic Paper Reviewer
Simulate a full journal-style peer review with five personas before you submit or revise an academic manuscript.
Overview
Academic Paper Reviewer is an agent skill most often used in Ship (also Validate scope work and Build docs) that simulates a five-reviewer journal peer review and returns an editorial decision with a revision roadmap.
Install
npx skills add https://github.com/imbad0202/academic-research-skills --skill academic-paper-reviewerWhat is this skill?
- Runs five independent reviewer personas: Editor-in-Chief, three field-tuned peer reviewers, and a Devil’s Advocate
- Supports full review, re-review verification, quick assessment, methodology focus, Socratic guided, and reviewer calibra
- Auto-detects discipline and configures field-specific expertise for non-overlapping methodology, domain, and argument le
- Produces a structured Editorial Decision plus a Revision Roadmap after multi-perspective synthesis
- Triggers on simulate review, manuscript critique, editorial review, and measure reviewer accuracy workflows
- 5 independent reviewer personas including Editor-in-Chief and Devil’s Advocate
- 6 review modes including full, re-review, quick, methodology, Socratic, and calibration
- Skill version 1.9.x with verified-only data access level in metadata
Adoption & trust: 3.7k installs on skills.sh; 28.8k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have a draft manuscript but no timely, multi-angle peer feedback that matches how journals actually evaluate methods, novelty, and argument strength.
Who is it for?
Researchers and indie builders shipping papers who want committee-style critique, re-review checks, or reviewer calibration before submitting to a venue.
Skip if: Builders who only need grammar polish, non-academic blog posts, or verified human IRB/legal sign-off—the skill simulates review; it does not replace formal ethics or publisher systems.
When should I use this skill?
Review paper, peer review, manuscript review, referee report, critique paper, simulate review, editorial review, re-review, or reviewer calibration.
What do I get? / Deliverables
You receive consolidated referee reports, devil’s-advocate challenges, and an actionable revision roadmap—then use re-review mode to verify changes before resubmission.
- Structured referee-style reports per perspective
- Editorial decision summary
- Revision roadmap with prioritized changes
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Ship → review because the skill’s primary output is structured referee-style critique and an editorial decision roadmap, aligned with quality gates before publication. Subphase review matches peer review, referee reports, re-review verification, and calibration—not initial ideation or distribution.
Where it fits
Quick-assessment mode to decide if a preprint idea is worth a full simulation before committing weeks to experiments.
Methodology-focus mode to align methods and supplementary sections with what field reviewers typically attack.
Full five-reviewer simulation plus Devil’s Advocate before uploading to a journal portal.
Re-review mode to verify that revision responses actually address prior major comments.
Calibration mode to tune how harsh or constructive simulated reviewers feel against past real reports.
How it compares
Use instead of a single-pass “critique my PDF” chat when you need role-separated methodology, domain, and adversarial review like a real desk decision.
Common Questions / FAQ
Who is academic-paper-reviewer for?
Grad students, indie researchers, and small teams preparing journal or conference manuscripts who want structured peer-review simulation before external submission.
When should I use academic-paper-reviewer?
During Validate when scoping whether a draft is submission-ready; during Ship for full referee simulation, methodology-only passes, or re-review after revisions; and during Build docs when aligning supplementary methods sections with reviewer expectations.
Is academic-paper-reviewer safe to install?
Treat manuscript text as sensitive input; review the Security Audits panel on this Prism page and avoid pasting unpublished secrets or proprietary data you cannot share with your agent runtime.
Workflow Chain
Requires first: academic paper
Then invoke: academic pipeline
SKILL.md
READMESKILL.md - Academic Paper Reviewer
# Academic Paper Reviewer v1.9.0 — Multi-Perspective Academic Paper Review Agent Team Simulates a complete international journal peer review process: automatically identifies the paper's field, dynamically configures 5 reviewers (Editor-in-Chief + 3 peer reviewers + Devil's Advocate) who review from four non-overlapping perspectives — methodology, domain expertise, cross-disciplinary viewpoints, and core argument challenges — ultimately producing a structured Editorial Decision and Revision Roadmap. **v1.1 Improvements**: 1. Added Devil's Advocate Reviewer — specifically challenges core arguments, detects logical fallacies, and identifies the strongest counter-arguments 2. Added `re-review` mode — verification review, focused on checking whether revisions address the review comments 3. Expanded review team from 4 to 5 members > **Routing discipline (v3.9.2):** see `.claude/CLAUDE.md` "Routing Discipline (v3.9.2)" + `shared/references/intent_clarification_protocol.md` for cross-skill routing rules. This skill assumes routing has already settled — ambiguous cross-phase materials should have been clarified upstream. --- ## Quick Start **Simplest command:** ``` Review this paper: [paste paper or provide file] ``` **Output:** 1. Automatically identifies the paper's field and methodology type 2. Dynamically configures the specific identities and expertise of 5 reviewers 3. 5 independent review reports (each from a different perspective) 4. 1 Editorial Decision Letter + Revision Roadmap --- ## Trigger Conditions ### Trigger Keywords **English**: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review, calibrate reviewer, reviewer calibration, measure reviewer accuracy ### Non-Trigger Scenarios | Scenario | Skill to Use | |----------|-------------| | Need to write a paper (not review) | `academic-paper` | | Need in-depth investigation of a research topic | `deep-research` | | Need to revise a paper (already have review comments) | `academic-paper` (revision mode) | ### Quick Mode Selection Guide | Your Situation | Recommended Mode | Spectrum | |----------------|-----------------|----------| | Need comprehensive review (first submission) | full | balanced | | Checking if revisions addressed comments | re-review | fidelity | | Quick quality assessment (15 min) | quick | fidelity | | Focus only on methods/statistics | methodology-focus | fidelity | | Want to learn by doing (guided review) | guided | originality | | Want to know this reviewer's own error profile before trusting its scores | calibration | fidelity | **Spectrum** (v3.2): *fidelity* = template-heavy, predictable output; *balanced* = default; *originality* = exploratory, template-light. See `shared/mode_spectrum.md` for the full cross-skill spectrum table. Not sure? Use `full` for pre-submission review, `re-review` for post-revision verification. `calibration` is opt-in — run it once per domain when you want to know the reviewer's FNR/FPR before relying on its rubric scores. --- ## Agent Team (7 Agents) | # | Agent | Role | Phase | |---|-------|------|-------| | 1 | `field_analyst_agent` | Analyzes the paper's field, dynamically c