review

review is a skill for Claude Code from wenhaochai/claude-plugins. It costs 127 tokens per session (4,297 once invoked), scanned A, original, MIT.

A self-review process for an unfinished machine-learning research paper written in Overleaf, an online LaTeX editor. It reads the project and produces a reviewer-style critique without changing the paper.

In plain words
What is it for?
Checking an ML paper’s clarity, structure, evidence, and likely reviewer concerns before submitting it to a research venue.
Why use it?
It exposes weaknesses before submission and separates feedback from the author’s decisions about what to change.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the writing plugin — 3 skills, 1 agent shipped together

Good fit Checking an ML paper’s clarity, structure, evidence, and likely reviewer concerns before submitting it to a research venue.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wenhaochai/claude-plugins/review
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 wenhaochai/claude-plugins --skill review
Clone the repo
git clone --depth 1 https://github.com/wenhaochai/claude-plugins

Made for: Claude Code.

Or install writing, the plugin that ships this one along with the rest of its 3 skills, 1 agent.

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.

agentmods badge for review

README.md
[![agentmods](https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/review/github.svg)](https://agentmods.dev/skills/wenhaochai/claude-plugins/review)
Your own site
<a href="https://agentmods.dev/skills/wenhaochai/claude-plugins/review"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/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.

agentmods 80×15 button for review

Your own site · 80×15
<a href="https://agentmods.dev/skills/wenhaochai/claude-plugins/review"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,297 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00127 $0.04297
Opus 5 $0.00063 $0.02148
Sonnet 5 $0.00025 $0.00859
Haiku 4.5 $0.00013 $0.00430

Measured 9d ago against content hash 44a42ee12ae1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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 9d 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.

writing/skills/review/SKILL.md · 314 lines

How it starts

The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.

writing:review — Pre-submission paper self-review

You are a senior reviewer for a top-tier ML venue (NeurIPS / ICML / ICLR / CVPR / COLM / ARR). Your job is to produce a reviewer-style critique of the user's own pre-submission Overleaf draft.

Hard scope rules:

  • Output is a diagnostic report only. Do NOT modify the paper source. The user reads the report and decides what to act on.
  • Naming and structural decisions are the user's. Flag candidates; never auto-rename or restructure.
  • Paragraph-level red-highlight / \textcolor{red} / review_state.md workflow is a separate skill — not this one.

Self-check (one line at start)

Print exactly once when activated:

writing:review v0.1.0 active: 6-phase pipeline (preflight → ingest → best-interpretation summary → section interrogation → weakness assembly + filter → report). style auto-loaded for clarity-rule citations.

Step 0 — Load style (mandatory)

Before reading the paper, invoke Skill(writing:style). The 15 canonical + 11 page-capped + 2 audit RULE numbers will be cited by RULE-XX in clarity weaknesses (e.g., "RULE-P1 violation: §3 opens with overview paragraph"). Without this, clarity weaknesses become subjective.

Step 1 — Resolve project name from user input

If the user did not specify a project, ask which project before continuing. Let <name> be the project name the user provided.

Resolution sequence (stop at first hit):

  1. Exact: ~/Documents/docs/project/<name>/
  2. Glob fuzzy: ~/Documents/docs/project/*<name>*/ (handles "user says short name, repo has venue prefix")
  3. Multiple match → list and ask user to pick
  4. No match → error: "no project under ~/Documents/docs/project/ matches <name>"

Confirm the resolved repo path to the user before proceeding.

Step 2 — Pre-submission auto-pull (cooperative project)

Per global CLAUDE.md "合作项目开工先自动 pull": if repo has any git remote and is behind upstream, run git fetch && git pull. If working tree is dirty, surface the state to the user and stop — do not auto-stash.

Read the full file on GitHub · 314 lines

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.

  1. 9d ago First seen · 314 lines · 127 tokens per session scan A 44a42ee12ae1

Subscribe to this mod's changes

review is a skill published in the GitHub repository wenhaochai/claude-plugins (16 stars, last pushed 9d ago), licensed MIT. It adds 127 tokens to every session and 4,297 once invoked, about $0.0006 per session on Opus 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.

Related

Other skills, from other repositories

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens