Academic Figure Maker
Generate and audit publication-ready plots for computer science and machine learning papers.
Installation
- Make sure Claude is on your device and in your terminal.
Skills load from
~/.claude/skills/when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then runclaudein any terminal to verify.One-time setupnpm i -g @anthropic-ai/claude-codeAlready have it? Skip ahead.
- Paste into Claude Code or into your terminal.
This copies the whole skill folder into
~/.claude/skills/academic-figure-joshua-zyy/— the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.Faster alternative (instruction-only skills)
Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.
Quick install (SKILL.md only)Sign up to copy - Restart Claude Code.
Quit and reopen Claude Code (or any other agent that loads from
~/.claude/skills/). New skills are picked up on startup. - Just ask Claude.
Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.
Prefer to read the source first? Open on GitHub.
When Claude uses it
Use when creating, revising, or auditing data and result figures for CS/AI/ML papers — benchmarks, ablations, training curves, confusion matrices, robustness and efficiency plots — generated as editable Python SVG that follows publication design rules. Architecture and framework diagrams are out of scope.
What this skill does
This skill routes academic figure requests for computer science, AI, and machine learning papers. It generates publication-ready plots as editable Python/matplotlib SVG files while enforcing rigorous design standards. The skill handles data-driven figures—benchmarks, ablations, training curves, confusion matrices, and efficiency plots—but explicitly excludes model framework diagrams, architecture overviews, and complex mechanism illustrations.
What it does
- Routes figure requests into one of four modes: creating plots from data, auditing existing figures, revising figures, or planning figures for paper sections
- Generates editable Python/SVG plots from numeric data or experimental results with built-in CS/AI/ML chart design validation
- Enforces publication standards through binding design rules defined in internal constraint files (stance, red-lines, anti-patterns)
- Audits figures for publication readiness with pass/fail QA checks and concrete remediation steps
- Produces figure blueprints for architecture diagrams and mechanism illustrations by creating manual-drawing requirements, evidence checklists, and caption drafts instead of rendering images
- Traces evidence to ensure revised figures maintain connection to underlying data and claims
How to use it
Provide your request with either raw numeric data, existing figure files, or a paper section needing figure planning. The skill will ask one clarifying question if the data source or intended use is unclear, then echo the selected mode (chart-from-data, figure-audit, figure-revision, or figure-blueprint) before executing. For data-driven plots, you'll receive a Python script, source data reference, editable SVG, and QA report. For audits, every item gets a pass/fail status and fix instructions.
Related skills
Claude API Helper
anthropics
Build, debug, and optimize Claude API applications with caching and model migration support.
Customer Health Scorer
alirezarezvani
Analyze customer accounts to predict churn risk and identify expansion opportunities.
Adaptyv Protein Lab
foryourhealth111-pixel
Submit protein sequences for automated lab testing and validation experiments.
CLAUDE.md Optimizer
daymade
Optimize your CLAUDE.md file for clarity, efficiency, and maintainability.