Agent skill

Agent Figure Gallery

by Dsadd4 in Dsadd4/AgentFigureGallery

Lets a plotting agent query a gallery of scientific figure references, show candidates for you to pick from, and export the chosen ones before it writes plot code.

MITAuto-check passedData & Analytics

Install Agent Figure Gallery

skills CLI
$ npx skills add Dsadd4/AgentFigureGallery --skill agent-figure-gallery -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Dsadd4/AgentFigureGallery agent-figure-gallery --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Dsadd4/AgentFigureGallery.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-figure-gallery .claude/skills/agent-figure-gallery && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-figure-gallery
GitHub stars
163
Token cost
~643 tokens
SKILL.md length
188 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Lets a plotting agent query a gallery of scientific figure references, show candidates for you to pick from, and export the chosen ones before it writes plot code.

  • Works in 6 steps: Resolve the KB root → Query before reading individual references → Generate visible candidates → …
  • Choosing the visual style for a scientific figure from reference examples
  • SKILL.md covers Core Rule, Key Files, Minimal Workflow and Preference Semantics, plus 1 more section
  • Calls python

What it does

This skill acts as a light controller for an external AgentFigureGallery knowledge base, found through the AGENT_FIGURE_GALLERY_ROOT or DRAWING_KB_ROOT environment variable. The figure collection itself is not loaded into the skill. The agent queries the gallery for the task first, then generates visible candidates for a chosen plot type and serves them on localhost through the agentfiguregallery command line tool.

You mark candidates as like, reject or select, or use global like and global reject for preferences that apply across tasks. The selected references are exported as a bundle, optionally with their scripts, and the agent consults that bundle before writing or revising plotting code. Local preferences keep their plot type, global rejects hide a figure from later sessions, and the file closes with a short check to run after changes to the tool, the gallery or the bundle export.

When your agent uses it

  • Choosing the visual style for a scientific figure from reference examples
  • Letting a person pick preferred example plots before the agent codes the figure
  • Revising plot code so it matches figures you selected earlier
  • Hiding reference figures you never want shown again

Example prompts

  • “Find reference figures for an embedding plot of my single-cell data and show me the candidates.”
  • “I picked three of the candidates; export them as a bundle and write the matplotlib code from them.”
  • “Reject that heatmap style for good so it stops showing up in future sessions.”

Requirements

  • A local copy of the AgentFigureGallery knowledge base, pointed to by AGENT_FIGURE_GALLERY_ROOT
  • The agentfiguregallery command line tool, which runs on Python

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Resolve the KB root
  2. Query before reading individual references
  3. Generate visible candidates
  4. Record human preferences
  5. Export a selected bundle
  6. Use the bundle before writing or revising plotting code.

What it can do on your machine

Read from SKILL.md and the folder at commit 0b55f26. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Figure Gallery loads about 643 tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 188 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~643

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Dsadd4/AgentFigureGallery at commit 0b55f26, republished under its MIT licence (© Dsadd4). 188 words, ~643 tokens.

Download SKILL.mdSave it as .claude/skills/agent-figure-gallery/SKILL.md (or your agent's skills folder).
name
agent-figure-gallery
description
Query visual scientific figure references, show candidates for human preference selection, export selected reference bundles, and guide plotting agents from human-selected visual examples to code action.

Core Rule

Treat this skill as a lightweight controller. Do not load the full visual corpus into the skill. Use AGENT_FIGURE_GALLERY_ROOT or DRAWING_KB_ROOT to point at the external AgentFigureGallery knowledge base.

Key Files

  • KB root: AGENT_FIGURE_GALLERY_ROOT=/path/to/AgentFigureGallery
  • CLI: agentfiguregallery or python -m agentfiguregallery.cli
  • Gallery server: backend command that serves the reference gallery on localhost
  • Candidate index: data/reference_candidate_index.json
  • Global preferences: data/reference_global_preferences.json
  • Reference sessions: outputs/reference_sessions/

Minimal Workflow

  1. Resolve the KB root:
    bash
    export AGENT_FIGURE_GALLERY_ROOT=/path/to/AgentFigureGallery
  2. Query before reading individual references:
    bash
    agentfiguregallery query --task "<user task>"
  3. Generate visible candidates:
    bash
    agentfiguregallery gallery --plot-type <plot_type> --task "<user task>" --limit 50 --serve
  4. Record human preferences:
    bash
    agentfiguregallery prefer --session outputs/reference_sessions/<session_id> --like <ID> --reject <ID> --select <ID>
  5. Export a selected bundle:
    bash
    agentfiguregallery bundle --session outputs/reference_sessions/<session_id> --copy-scripts
  6. Use the bundle before writing or revising plotting code.

Preference Semantics

  • like: useful for this task or plot type.
  • reject: not useful for this task or plot type.
  • select: use this candidate for the current agent action.
  • global_like: generally useful across tasks.
  • global_reject: hide from future sessions.

Local preferences must preserve plot_type. Global preferences are cross-task.

Validation

After changing the CLI, gallery, preference logic, or bundle export:

bash
agentfiguregallery gallery --plot-type embedding_plot --limit 20 --serve
agentfiguregallery prefer --session outputs/reference_sessions/<session_id> --like E01 --select E02
agentfiguregallery bundle --session outputs/reference_sessions/<session_id>

Success means visible candidates render, stable IDs are shown, preferences persist, global rejects are hidden from later generated sessions, and the bundle contains selected references plus source code paths.

© Dsadd4, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/agent-figure-gallery of Dsadd4/AgentFigureGallery.

Open the folder on GitHubat commit 0b55f26

Compare with similar skills

Agent Figure Gallery next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Figure Gallery compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Figure Gallery this skillDsadd4/AgentFigureGallery163—~643Automated safety check: PassMIT
Scientific Figure MakingChenLiu-1996/figures4papers8.3k—~557Automated safety check: PassCustom licence
FigMirrorVILA-Lab/FigMirror521—~2.4kAutomated safety check: PassNone
Scientific Figure Generationlingzhi227/agent-research-skills390—~809Automated safety check: PassNone
MathModel Figure Templatesjihe520/MathModelAgent6.2k—~627Automated safety check: NotesNone
FigMirror Figure Style TransferVILA-Lab/FigMirror521—~2.1kAutomated safety check: PassNone

Similar skills

  • Scientific Figure Making

    ChenLiu-1996/figures4papers

    Covers publication-ready matplotlib figures for academic papers, slides, and reports—bars, trends, scatter, heatmaps, and multi-panel layouts—with this…

    8.3k GitHub stars~557 tokensUpdated today
    Data & AnalyticsAuto-check passed
  • FigMirror

    VILA-Lab/FigMirror

    Mirrors the visual style of a top-conference paper figure onto your own data, producing a camera-ready PDF and a self-contained matplotlib script.

    521 GitHub stars~2.4k tokensUpdated 9 days ago
    Data & AnalyticsAuto-check passed
  • Scientific Figure Generation

    lingzhi227/agent-research-skills

    Generates publication-quality scientific figures with matplotlib or seaborn through query expansion, a run-and-retry coding loop and a visual check of the rendered PNG.

    390 GitHub stars~809 tokensUpdated 7 mo ago
    Data & AnalyticsAuto-check passed
  • MathModel Figure Templates

    jihe520/MathModelAgent

    Renders ready-made scientific figure templates, such as raincloud plots, Taylor diagrams and chord diagrams, from bundled Python scripts in the MathModel sandbox.

    6.2k GitHub stars~627 tokensUpdated 7 days ago
    Data & AnalyticsAuto-check: notes
  • Redraws your data as a matplotlib figure in the visual style of a reference paper figure, using a drawer and reviewer loop.

    521 GitHub stars~2.1k tokensUpdated 9 days ago
    Data & AnalyticsAuto-check passed
  • Fin Arch Diagram

    csmar432/finai-research

    生成研究/项目架构图、流程图、层次图(swimlane / processflow / hierarchytree)。适合 PPT 汇报、技术文档、综述插图。输出风格接近 draw.io,可选 graphviz(高质量)/ matplotlib(零依赖)双后端。

    109 GitHub stars~1.5k tokensUpdated 4 days ago
    Data & AnalyticsAuto-check passed

Questions about Agent Figure Gallery

What does Agent Figure Gallery do?

Lets a plotting agent query a gallery of scientific figure references, show candidates for you to pick from, and export the chosen ones before it writes plot code. This skill acts as a light controller for an external AgentFigureGallery knowledge base, found through the AGENT_FIGURE_GALLERY_ROOT or DRAWING_KB_ROOT environment variable. The figure collection itself is not loaded into the skill.

When should I use Agent Figure Gallery?

Agent Figure Gallery fits situations like: choosing the visual style for a scientific figure from reference examples; letting a person pick preferred example plots before the agent codes the figure; revising plot code so it matches figures you selected earlier; hiding reference figures you never want shown again.

How do I install Agent Figure Gallery in Claude Code?

Run `npx skills add Dsadd4/AgentFigureGallery --skill agent-figure-gallery -a claude-code`. Or copy the skill folder (skills/agent-figure-gallery in Dsadd4/AgentFigureGallery) into .claude/skills/agent-figure-gallery in your project. Claude Code loads it when a task matches its description.

How do I install Agent Figure Gallery in Codex?

Run `npx skills add Dsadd4/AgentFigureGallery --skill agent-figure-gallery -a codex`. Or copy the skill folder (skills/agent-figure-gallery in Dsadd4/AgentFigureGallery) into .agents/skills/agent-figure-gallery in your project. Codex loads it when a task matches its description.

Can I use Agent Figure Gallery in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Dsadd4/AgentFigureGallery --skill agent-figure-gallery -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-figure-gallery, .gemini/skills/agent-figure-gallery, .github/skills/agent-figure-gallery and .opencode/skills/agent-figure-gallery in your project.

What does Agent Figure Gallery need to run?

Going by SKILL.md and its folder, Agent Figure Gallery needs the command-line tools its instructions call (python). Our summary lists: A local copy of the AgentFigureGallery knowledge base, pointed to by AGENT_FIGURE_GALLERY_ROOT; The agentfiguregallery command line tool, which runs on Python.

Does Agent Figure Gallery access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agent Figure Gallery safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent Figure Gallery use?

Agent Figure Gallery is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Figure Gallery use?

About 643 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Figure Gallery?

Skills that share tags, products or a category with Agent Figure Gallery: Scientific Figure Making (ChenLiu-1996/figures4papers, 8.3k stars), FigMirror (VILA-Lab/FigMirror, 521 stars), Scientific Figure Generation (lingzhi227/agent-research-skills, 390 stars) and MathModel Figure Templates (jihe520/MathModelAgent, 6.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Figure Gallery?

Dsadd4 (a GitHub user) maintains it in Dsadd4/AgentFigureGallery, which has 163 GitHub stars. The repository was last updated on September 5, 2026.

Source: Dsadd4/AgentFigureGallery on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.