agentmods.dev

figure.make_professional

figure.make_professional is a skill for Claude Code from gpsaggese/helpers. It costs 18 tokens per session (857 once invoked), scanned A, original, Apache-2.0.

A workflow for polishing an existing TikZ, SVG, Graphviz, or Mermaid diagram and comparing it with the original. These are text-based formats for drawing diagrams and figures.

In plain words
What is it for?
It helps review a figure's format, apply the matching project conventions, render a before image, and produce a more publication-ready result.
Why use it?
A figure may be hard to read or inconsistent with a project's visual rules. Rendering the original and the edited version makes the improvement visible while keeping the correct rules for each file type.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

not rated 158repo +1 today A scan 18 tokens original Apache-2.0

Good fit It helps review a figure's format, apply the matching project conventions, render a before image, and produce a more publication-ready result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gpsaggese/helpers/figure.make_professional
View source ↗ gpsaggese/helpers
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 gpsaggese/helpers --skill figure.make_professional
Clone the repo
git clone --depth 1 https://github.com/gpsaggese/helpers

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.

agentmods badge for figure.make_professional

README.md
[![agentmods](https://agentmods.dev/badge/skills/gpsaggese/helpers/figure.make_professional/github.svg)](https://agentmods.dev/skills/gpsaggese/helpers/figure.make_professional)
Your own site
<a href="https://agentmods.dev/skills/gpsaggese/helpers/figure.make_professional"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/figure.make_professional/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 figure.make_professional

Your own site · 80×15
<a href="https://agentmods.dev/skills/gpsaggese/helpers/figure.make_professional"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/figure.make_professional.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 857 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 $0.00018 $0.00857
Opus 5.5 $0.00007 $0.00343
Sonnet 5.5 $0.00004 $0.00171
Haiku 4.5 $0.00002 $0.00086

Measured yesterday against content hash 1d5ca8401599, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

figure.make_professional 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 yesterday.

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.

.claude/skills/figure.make_professional/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal

  • Take an existing figure (<FILE>.tex/TikZ, <FILE>.svg, <FILE>.dot/Graphviz, or <FILE>.mmd/Mermaid) and polish it into a publication-quality figure using the project's figure conventions
  • Prove the improvement with a before/after image

Workflow

Identify the Figure Type

  • .tex (TikZ/LaTeX source): apply .claude/skills/tikz.rules.md
  • .svg (SVG source): apply .claude/skills/svg.rules.md
  • .dot/.gv (Graphviz source): apply .claude/skills/graphviz.rules.md
  • .mmd/.mermaid (Mermaid source): apply the ## Mermaid Graph section of .claude/skills/figure.rules.md
  • All four types share the cross-diagram ## Color Palette in .claude/skills/figure.rules.md
  • If unsure which rules apply, inspect the extension and content first. Never mix rule sets on one figure

Render the Original (Before)

  • Render the figure as given, with no edits, to before.png
    • TikZ: 
      > dev_scripts_helpers/dockerize/dockerized_tikz_to_bitmap.py \
    -i <FILE>.tex -o before.png
    • SVG: 
      > inkscape <FILE>.svg --export-type=png --export-filename=before.png
    • Graphviz: 
      > dot -Tpng <FILE>.dot -o before.png
    • Mermaid: 
      > mmdc -i <FILE>.mmd -o before.png
  • Keep this file untouched. It is the baseline for the final comparison

Apply the Rules

  • Read the relevant rules file in full. Edit the source to follow every section, especially:
    • Layout & spacing (grid alignment, no cramped or overlapping elements; for Graphviz: rank/cluster alignment)
    • Color system (restrained, semantic palette; no raw saturated colors; use the shared palette in figure.rules.md unless the rules file gives a more specific one, e.g., Graphviz's flat/architecture color tables)
    • Typography (label-size hierarchy, sentence case, consistent font)
    • Strokes & geometry (consistent line weights and arrowheads/corners; for Graphviz: edge style semantics; for Mermaid: the required %%{init: ...}%% theme directive)
    • The "What NOT to Do" anti-pattern list at the end of the rules file (Graphviz/Mermaid have none: follow every section above instead)
  • Do not change the figure's meaning or content. Change only its visual execution

Read the full file on GitHub · 81 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. yesterday First seen · 81 lines · 18 tokens per session scan A 1d5ca8401599

Subscribe to this mod's changes

figure.make_professional is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 857 once invoked, about $0.0001 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 2026-11-06.

Creative and mediaDesign and UX
Related

figure.make_professional compared with skills from other repositories

figure.make_professional next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
figure.make_professionalgpsaggese/helpersSkill158todayApache-2.0A18Claude Code
webgl-holographic-foilnexu-io/open-designSkill106ktodayApache-2.0A41Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-designSkill106ktodayApache-2.0A53Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-designSkill106ktodayApache-2.0A78Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codexSkill34ktodayMITA52Codex
glance-canonical-layoutsandroid/skillsSkill10kyesterdayApache-2.0A56Claude Code
accessibilitymicrosoft/hve-coreSkill1.6ktodayMITA47Claude Code