A read-only review that detects a file's format and sends it to the appropriate review checks. It supports LaTeX, Quarto, Typst, Python, and Markdown files.

Use it to review documents, slide decks, Python scripts, and Markdown files for format-specific writing, code, teaching, and layout problems.

It removes the need to choose separate review steps for each supported file type. It checks the file for issues without changing it.

review — Skill for Claude Code by clearsmog

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 clearsmog/claude-skills --skill review

Clone the repo

git clone --depth 1 https://github.com/clearsmog/claude-skills

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/clearsmog/claude-skills/review/github.svg)](https://agentmods.dev/skills/clearsmog/claude-skills/review)

Your own site

<a href="https://agentmods.dev/skills/clearsmog/claude-skills/review"><img src="https://agentmods.dev/badge/skills/clearsmog/claude-skills/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/clearsmog/claude-skills/review"><img src="https://agentmods.dev/badge/skills/clearsmog/claude-skills/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 692 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.

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	$0.00044	$0.00692
Opus 5	$0.00022	$0.00346
Sonnet 5	$0.00009	$0.00138
Haiku 4.5	$0.00004	$0.00069

Measured 11d ago against content hash 55796cbe036e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 11d 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.

review/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Universal Review

Auto-detect file format and launch the right review agents in parallel. Read-only — no fixes applied.

Format Detection

Determine file type from extension:

.tex → Beamer LaTeX slides
.qmd → Quarto RevealJS slides
.typ → Typst document (slides, docs, guides, CVs)
.py → Python script
.md → Markdown

For .typ files, also detect document type from content:

Contains #import "@preview/polylux" or #import "@preview/touying" → Typst slides
Contains #import "@local/qk" → Uses qk component library
Contains #set page(width: 16cm, height: 9cm) or similar → Presentation
Otherwise → Typst document (guide, essay, CV, etc.)

Routing Table

Extension	Agents (parallel)	Condition
`.tex`	proofreader + document-auditor + pedagogy-reviewer	Always
`.tex`	+ diagram-reviewer	If TikZ found (`\begin{tikzpicture}`)
`.qmd`	proofreader + document-auditor	Always
`.qmd`	+ quality-critic	If `.tex` sibling exists
`.typ`	typst-reviewer + proofreader	Always
`.typ`	+ pedagogy-reviewer	If slide format detected
`.py`	python-pro (subagent)	Always
`.md`	proofreader	Always

Steps

Parse $ARGUMENTS — resolve file path
Detect format from extension
For .typ files, read file to detect document subtype
Launch agents in parallel per routing table
Collect all reports from quality_reports/
Synthesize a consolidated summary table

Output

# Review Summary: [Filename]

| Dimension | Agent | Critical | Major | Minor | Verdict |
|-----------|-------|----------|-------|-------|---------|
| [varies] | [agent name] | N | N | N | [status] |

## Overall: [EXCELLENT / GOOD / NEEDS WORK / POOR]

## Critical Issues (if any)
[List top issues requiring immediate attention]

## Reports Generated
- quality_reports/[file]_report.md
- quality_reports/[file]_typst_review.md
- ...

Quality Score Rubric

Read the full file on GitHub · 79 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.

11d ago First seen · 79 lines · 44 tokens per session scan A 55796cbe036e

Subscribe to this mod's changes

review is a skill published in the GitHub repository clearsmog/claude-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 44 tokens to every session and 692 once invoked, about $0.0002 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 2026-08-31.

Claude Code Code review ai-skills automation claude image-generation notebooklm

replicate-runner

Use when run AI models on Replicate cloud API. Deploy image generation, video creation, audio processing, and custom models without managing infrastructure. Use when working with replicate runner.

oyi77/1ai-skills · 40 tokens

review-agent

Use when reading code changes with adversarial intent to find bugs, security holes, logic errors, and performance traps.

oyi77/1ai-skills · 26 tokens

karpathy-coding-principles

Use when andrej Karpathy's 4 coding principles — think before coding, simplicity first, surgical changes, goal-driven execution. Use when coding, reviewing code quality, reducing overengineering,.

oyi77/1ai-skills · 46 tokens

vicious-mockery

The bard's cantrip that deals psychic damage through insults. In practice this is adversarial review — the art of finding and articulating exactly what is wrong with something in a way that is impossible to ignore. Unlike polite feedback that gets filed and forgotten, vicious mockery lands. It is the red-team report…

Hmbown/Wizards-of-the-Ghosts · 101 tokens

perception

In D&D, Perception is the raw ability to notice things: the hidden door, the faint sound, the detail that does not belong. Unlike Investigation (which follows evidence methodically) or Insight (which reads subtext), Perception is about the initial act of noticing. The real-world version is detail-catching: spotting…

Hmbown/Wizards-of-the-Ghosts · 103 tokens

responding-to-feedback

Use when replying to feedback on your work (review comments, manuscript revisions, design critique, criticism).

redhuntlabs/wizard · 25 tokens