tikz-figure-review

tikz-figure-review is a skill for Claude Code from shubham0704/claude-skills. It costs 177 tokens per session (5,103 once invoked), scanned A, original, MIT.

A review workflow for TikZ and pgfplots figures, which are diagrams and charts made inside LaTeX documents. It checks rendered figures for common visual problems and guides fixes.

In plain words
What is it for?
Use it to extract figures from a LaTeX document, compile them separately, inspect PNG previews, and fix alignment, labels, clipping, overlaps, and layout.
Why use it?
It helps catch misplaced labels, cut-off content, overlapping elements, and legends covering data before a paper, tutorial, lecture note, or thesis is submitted.

Skill for Claude Code

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

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cd figures_check && ln -s ../phase-data phase-data.

Part of the tikz-figure-review plugin — 1 skill shipped together

Good fit Use it to extract figures from a LaTeX document, compile them separately, inspect PNG previews, and fix alignment, labels, clipping, overlaps, and layout.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/shubham0704/claude-skills
agentmods
npx agentmods add skills/shubham0704/claude-skills/tikz-figure-review

Made for: Claude Code.

Or install tikz-figure-review, the plugin that ships this one along with the rest of its 1 skill.

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 tikz-figure-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/shubham0704/claude-skills/tikz-figure-review/github.svg)](https://agentmods.dev/skills/shubham0704/claude-skills/tikz-figure-review)
Your own site
<a href="https://agentmods.dev/skills/shubham0704/claude-skills/tikz-figure-review"><img src="https://agentmods.dev/badge/skills/shubham0704/claude-skills/tikz-figure-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 tikz-figure-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/shubham0704/claude-skills/tikz-figure-review"><img src="https://agentmods.dev/badge/skills/shubham0704/claude-skills/tikz-figure-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 177 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,103 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00177 $0.05103
Opus 5 $0.00088 $0.02551
Sonnet 5 $0.00035 $0.01021
Haiku 4.5 $0.00018 $0.00510

Measured 12d ago against content hash a5736db076af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tikz-figure-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 12d 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.

tikz-figure-review/SKILL.md · 460 lines

How it starts

The opening of the file, as written. The whole thing — 460 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TikZ / pgfplots Figure Review

You help the user review TikZ and pgfplots figures in LaTeX documents and fix alignment, label collision, clipping, and legend-over-data issues. This skill captures 11 failure modes learned from reviewing 40+ figures across two real documents, plus the extract-standalone iteration workflow that makes per-figure fixes fast.

1. Workflow

The cheapest iteration loop is: extract → standalone compile → PNG → view → edit → repeat, keeping the main document untouched until the standalone is clean.

1.1 One-time setup (per project)

Create a working directory (e.g. figures_check/) with:

  • _preamble.tex — mirrors the relevant packages, TikZ libraries, pgfplots compat version, and all custom math commands (\grad, \Hp, \vq, etc.) from the main document. Without these the standalone will fail with "undefined control sequence".
  • One figN_<name>.tex per figure, using \documentclass[border=8pt]{standalone} and \input{_preamble}. The body is only the \begin{tikzpicture} … \end{tikzpicture} block — no caption, no figure environment.

Known pitfall: pgfplots compat mismatch. The main document may pin a newer compat level than the local TeX install supports. Set the preamble to the lowest compat that works on the local install (e.g. 1.17) and do not sync that one line back to the main document.

1.2 Per-figure compile / render

cd figures_check
pdflatex -interaction=nonstopmode figN_name.tex > figN_name.log 2>&1
pdftoppm -r 200 -png figN_name.pdf figN_name
# produces figN_name-1.png

200 dpi is enough to read labels; go to 300 dpi only for fine alignment checks.

1.3 Parallel review

Once every standalone compiles and has a fresh PNG, dispatch review subagents. Each subagent gets:

  • The PNG path (to view via the Read tool).
  • The standalone .tex path (for fast iteration).
  • The line range in the main .tex (for syncing the fix back).
  • Explicit instructions to edit both files and keep the tikzpicture body identical.
  • A re-render command and a "max 3 iterations" cap.
  • A pointer to this SKILL file as reference.

Read the full file on GitHub · 460 lines

Files

What ships with it

3 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.

  1. 12d ago First seen · 460 lines · 177 tokens per session scan A a5736db076af

Subscribe to this mod's changes

tikz-figure-review is a skill published in the GitHub repository shubham0704/claude-skills (1 stars, last pushed 7d ago), licensed MIT. It adds 177 tokens to every session and 5,103 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

ieee-latex

Compile, diagnose, and fix IEEEtran LaTeX manuscripts for JSAC, TWC, TCOM, WCL, CL, and related IEEE journals: documentclass options, BibTeX/IEEEtran bibliography, undefined citations/refs, overfull hboxes, figure/table placement, algorithm/equation numbering, Index Terms, EDICS, biographies, and final PDF checks. Use…

TenWalk/ieee-skills · 161 tokens

autoreport

Use when generating a physics or engineering experiment report from measured data and reference materials — orchestrates Theory, Data Analysis, Plotting, and Report sub-agents to produce a compiled LaTeX PDF. Also use for any sub-task in that pipeline: deriving formulas, analyzing lab data, plotting measurements with…

xjsongphy/skills · 74 tokens

pydicom

Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.

K-Dense-AI/scientific-agent-skills · 56 tokens

pptx-posters

Create and audit editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Use when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required.

K-Dense-AI/scientific-agent-skills · 59 tokens

pdf-design

Designs PDF reports and proposals from HTML with previews and branding. Use to create, export, or securely upload a PDF.

jamditis/claude-skills-journalism · 28 tokens

document-design

Creates print-ready HTML that exports to PDF. Use to make a proposal, report, one-pager, newsletter, slides, or flyer.

jamditis/claude-skills-journalism · 31 tokens