An external-style review of someone else’s manuscript, paper, thesis chapter, proposal, or preprint. It evaluates the work as submitted, including its claims, evidence, methods, structure, and contribution.

Use it to assess research novelty, significance, evidence, writing, and readiness, then produce a reviewer-style recommendation and revision list.

It helps reveal unsupported claims, unclear contributions, overstatement, weak methods, and revisions a reviewer may request before submission.

peer-review — Skill for Claude Code by yha9806

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add yha9806/academic-writing-toolkit --skill peer-review

Clone the repo

git clone --depth 1 https://github.com/yha9806/academic-writing-toolkit

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yha9806/academic-writing-toolkit/peer-review/github.svg)](https://agentmods.dev/skills/yha9806/academic-writing-toolkit/peer-review)

Your own site

<a href="https://agentmods.dev/skills/yha9806/academic-writing-toolkit/peer-review"><img src="https://agentmods.dev/badge/skills/yha9806/academic-writing-toolkit/peer-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yha9806/academic-writing-toolkit/peer-review"><img src="https://agentmods.dev/badge/skills/yha9806/academic-writing-toolkit/peer-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,059 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00070	$0.01059
Opus 5.5	$0.00028	$0.00424
Sonnet 5.5	$0.00014	$0.00212
Haiku 4.5	$0.00007	$0.00106

Measured 2mo ago against content hash 446f326610c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

peer-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

archive/skills/peer-review/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/peer-review - External Manuscript Review

Purpose

Produce a reviewer-style assessment of another author's work. This skill judges the manuscript as submitted, not as the author wishes it to be.

Use /argument-governance first when the review needs a formal gap-contribution or claim-evidence map.

Codex-Only Baseline

Complete the review with Codex using the supplied manuscript, supplements, rubric, and source anchors. Do not require Gemini, gemini-agent, a second model, or a subagent. If another reviewer tool is available, record its output as optional advisory context only.

If /argument-governance is unavailable in the user's environment, manually extract the same spine in the review report: problem, gap, contribution, main claims, evidence, boundary language, and reviewer risks.

Enhanced Advisory Mode

If the user explicitly provides or enables an API-key-backed model review, use it only after Codex has made a first-pass review from the supplied materials.

Rules:

keep API keys in environment variables, never in review files
send only user-approved manuscript or supplement excerpts
label the external result as advisory_external_review
compare it against Codex's local findings
include only grounded, source-checkable points in the final review
do not treat the external model as a reviewer consensus, venue decision, or factual verifier

Core Rules

Review only the manuscript and explicitly supplied supplementary materials.
Do not use private project memory, prior chats, unstated author intent, or unpublished context as evidence.
Separate reviewer judgment from factual verification.
Do not rewrite the manuscript unless the user explicitly asks for revision suggestions.
Attribute concerns to manuscript locations, sections, figures, tables, claims, or missing evidence.
Be fair: identify strengths before high-level weaknesses, but do not soften required revisions.
Do not infer venue-specific acceptance thresholds unless the venue or rubric is supplied.
Do not treat an unavailable external review tool as a blocker.

Read the full file on GitHub · 155 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 155 lines · 70 tokens per session scan A 446f326610c9

Subscribe to this mod's changes

peer-review is a skill published in the GitHub repository yha9806/academic-writing-toolkit (54 stars, last pushed 10d ago), licensed MIT. It adds 70 tokens to every session and 1,059 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Research academic-writing agent-skills ai-tools codex-cli cursor

peer-review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
peer-reviewyha9806/academic-writing-toolkit	Skill	54	10d ago	MIT	A	70	Claude Code
academic-cvmuhammad1438/academic-writer-skills	Skill	7	7mo ago	MIT	A	0	Claude Code
argumentation-enginemuhammad1438/academic-writer-skills	Skill	7	7mo ago	MIT	A	0	Claude Code
conference-presentationmuhammad1438/academic-writer-skills	Skill	7	7mo ago	MIT	A	0	Claude Code
latex-writermuhammad1438/academic-writer-skills	Skill	7	7mo ago	MIT	A	0	Claude Code
preregistration-guidemuhammad1438/academic-writer-skills	Skill	7	7mo ago	MIT	A	0	Claude Code
cover-letter-writermuhammad1438/academic-writer-skills	Skill	7	7mo ago	MIT	A	0	Claude Code