figure-evaluation
Evaluates scientific figures for publication quality using VLM-as-a-judge.
Skill by zc6600
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/zc6600-figure-evaluation
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/figure-evaluation
What's inside
- Skill name
figure-evaluation- Description
- Evaluates scientific figures for publication quality using VLM-as-a-judge. Use when user uploads a figure and asks for "critique", "review", "scoring against academic standards", or asks "is this figure publication-ready?".
- License
- unknown
- Instructions
- 40 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from zc6600/aura
- 0.519score
research-topic-selector
zc6600
Mines recent literature for a genuinely open research problem within a target subfield and vets it against strict admissibility gates (open, programmatically…
SkillBFreshness: BClaude Code +9 - 0.516score
stanford-town
zc6600
Replicates the Stanford Smallville Generative Agents simulation using the Host-Agent and Subagent architecture without prompt leakage.
SkillBFreshness: BClaude Code +9 - 0.469score
multi-agent-simulation
zc6600
Orchestrates multi-agent collaboration workflows (e.g., Debate, Refine, Swarm).
SkillCFreshness: CClaude Code +9 - 0.469score
paper2skill
zc6600
Converts academic papers (especially on agents/multi-agent systems) into executable Aura skills.
SkillCFreshness: CClaude Code +9 - 0.469score
auto-figure
zc6600
Generates publication-ready scientific illustrations (AutoFigure mode).
SkillCFreshness: CClaude Code +9 - 0.445score
find-skills
zc6600
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
SkillCFreshness: CClaude Code +9 - 0.445score
brand-guidelines
zc6600
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel.
SkillCFreshness: CClaude Code +9 - 0.443score
skill-creator
zc6600
Guide for creating effective skills.
SkillCFreshness: CClaude Code +9 - 0.430score
example-skill
zc6600
An example skill demonstrating the standard structure and best practices from the Anthropic Skill Guide.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 4, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/zc6600/aura
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from zc6600
- 0.546score
development-workflow
zc6600
Git development workflows, pull requests, and CI feedback.
SkillAFreshness: AClaude Code +9 - 0.519score
research-topic-selector
zc6600
Mines recent literature for a genuinely open research problem within a target subfield and vets it against strict admissibility gates (open, programmatically…
SkillBFreshness: BClaude Code +9 - 0.516score
stanford-town
zc6600
Replicates the Stanford Smallville Generative Agents simulation using the Host-Agent and Subagent architecture without prompt leakage.
SkillBFreshness: BClaude Code +9 - 0.469score
multi-agent-simulation
zc6600
Orchestrates multi-agent collaboration workflows (e.g., Debate, Refine, Swarm).
SkillCFreshness: CClaude Code +9 - 0.469score
paper2skill
zc6600
Converts academic papers (especially on agents/multi-agent systems) into executable Aura skills.
SkillCFreshness: CClaude Code +9 - 0.469score
auto-figure
zc6600
Generates publication-ready scientific illustrations (AutoFigure mode).
SkillCFreshness: CClaude Code +9
Cite this page
figure-evaluation skill. Agent Mart. https://agentmart.dev/skills/zc6600-figure-evaluation (last updated 2026-10-24)