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…
A skill your agent uses when asked to reproduce or refine a single scientific figure panel as editable Python/matplotlib code in NaturePanelForge.
Install Codex Panel Reproduce
$ npx skills add littlepeachs/NaturePanelForge --skill codex-panel-reproduce -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install littlepeachs/NaturePanelForge codex-panel-reproduce --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/littlepeachs/NaturePanelForge.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/codex-panel-reproduce .claude/skills/codex-panel-reproduce && rm -rf skills-srcUse ~/.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/
Install the "codex-panel-reproduce" agent skill from https://github.com/littlepeachs/NaturePanelForge/tree/main/skills/codex-panel-reproduce into .claude/skills/codex-panel-reproduce/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-panel-reproduce", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/littlepeachs/NaturePanelForge/tree/main/skills/codex-panel-reproduceType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add littlepeachs/NaturePanelForge --skill codex-panel-reproduce -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install littlepeachs/NaturePanelForge codex-panel-reproduce --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/littlepeachs/NaturePanelForge.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/codex-panel-reproduce .agents/skills/codex-panel-reproduce && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "codex-panel-reproduce" agent skill from https://github.com/littlepeachs/NaturePanelForge/tree/main/skills/codex-panel-reproduce into .agents/skills/codex-panel-reproduce/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-panel-reproduce", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add littlepeachs/NaturePanelForge --skill codex-panel-reproduce -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install littlepeachs/NaturePanelForge codex-panel-reproduce --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/littlepeachs/NaturePanelForge.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/codex-panel-reproduce .cursor/skills/codex-panel-reproduce && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "codex-panel-reproduce" agent skill from https://github.com/littlepeachs/NaturePanelForge/tree/main/skills/codex-panel-reproduce into .cursor/skills/codex-panel-reproduce/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-panel-reproduce", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/littlepeachs/NaturePanelForge.git --path skills/codex-panel-reproduce--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add littlepeachs/NaturePanelForge --skill codex-panel-reproduce -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install littlepeachs/NaturePanelForge codex-panel-reproduce --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/littlepeachs/NaturePanelForge.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/codex-panel-reproduce .gemini/skills/codex-panel-reproduce && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "codex-panel-reproduce" agent skill from https://github.com/littlepeachs/NaturePanelForge/tree/main/skills/codex-panel-reproduce into .gemini/skills/codex-panel-reproduce/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-panel-reproduce", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install littlepeachs/NaturePanelForge codex-panel-reproduceInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add littlepeachs/NaturePanelForge --skill codex-panel-reproduce -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/littlepeachs/NaturePanelForge.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/codex-panel-reproduce .github/skills/codex-panel-reproduce && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "codex-panel-reproduce" agent skill from https://github.com/littlepeachs/NaturePanelForge/tree/main/skills/codex-panel-reproduce into .github/skills/codex-panel-reproduce/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-panel-reproduce", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add littlepeachs/NaturePanelForge --skill codex-panel-reproduce -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install littlepeachs/NaturePanelForge codex-panel-reproduce --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/littlepeachs/NaturePanelForge.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/codex-panel-reproduce .opencode/skills/codex-panel-reproduce && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "codex-panel-reproduce" agent skill from https://github.com/littlepeachs/NaturePanelForge/tree/main/skills/codex-panel-reproduce into .opencode/skills/codex-panel-reproduce/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-panel-reproduce", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
codex-panel-reproduce- GitHub stars
- 223
- Token cost
- ~1.2k tokens
- SKILL.md length
- 381 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when asked to reproduce or refine a single scientific figure panel as editable Python/matplotlib code in NaturePanelForge.
- Asked to reproduce
- SKILL.md covers Trigger, Inputs, Reproduce One Panel and Dry Run, plus 4 more sections
- Calls python3 and python
- Refine a single scientific figure panel as editable Python/matplotlib code in NaturePanelForge
What it does
Codex Panel Reproduce is an agent skill from littlepeachs/NaturePanelForge. Use this skill when asked to reproduce or refine a single scientific figure panel as editable Python/matplotlib code in NaturePanelForge. It covers the local Codex panel-to-code workflow, dry-runs, review loops, expected artifacts, and validation.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Data & Analytics, covering Data visualization. It works with Python, Matplotlib and Qwen. The repository describes itself as: NaturePanelForge is a code-first workflow for turning scientific figure images and open-access Nature-family papers into panel-level, executable plotting-code reconstruction tasks. The licence is MIT.
When your agent uses it
- Asked to reproduce
- Refine a single scientific figure panel as editable Python/matplotlib code in NaturePanelForge
Example prompts
- “/codex-panel-reproduce”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 0ca0c91. 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:
python3python
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
Codex Panel Reproduce loads about 1.2k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 381 words of instructions outside code blocks.
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 littlepeachs/NaturePanelForge at commit 0ca0c91, republished under its MIT licence (© littlepeachs). 381 words, ~1,235 tokens.
Download SKILL.mdSave it as
.claude/skills/codex-panel-reproduce/SKILL.md (or your agent's skills folder).- name
- codex-panel-reproduce
- description
- Use this skill when asked to reproduce or refine a single scientific figure panel as editable Python/matplotlib code in NaturePanelForge. It covers the local Codex panel-to-code workflow, dry-runs, review loops, expected artifacts, and validation.
Codex Panel Reproduce
Trigger
Use this for code-only reproduction or refinement of one scientific figure panel in NaturePanelForge. The target is an editable Python script plus rendered PNG/PDF, not image editing or raster tracing.
For local user-supplied images, do not run Qwen scoring and do not require Qwen outputs. Qwen context is only optional metadata when the input already comes from an existing SciFigureHub/NaturePanelForge pipeline directory.
Inputs
- Single-image workflow: a target panel image path, optional caption, optional source PDF.
- Existing-panel workflow: a panel directory containing
target.png; optionalmetadata.json,qwen_score.json,qwen_prompt.md, andraw_response.txt. Missing Qwen files are acceptable for user-supplied images. - Refine workflow: an existing panel directory containing
target.png,reproduce_panel.py,reproduce_panel.png, andreproduce_panel.pdf.
Reproduce One Panel
Run from the NaturePanelForge repo root:
python3 forge.py single-panel-image \
--image path/to/target_panel.png \
--out-root UserRuns/single_panel \
--panel-id my_panel \
--caption "brief visual/caption context" \
--chart-type user_supplied \
--review-rounds 4 \
--skip-existingThis command prepares the local single-image bundle itself. It writes placeholder user-image metadata as needed; it does not classify the image with Qwen and does not need a local Qwen model.
For an existing panel directory:
python3 examples/prompt_codex_reproduce_fig02_g.py \
--panel-dir path/to/panel_dir \
--panel-root path/to/panel_root \
--reviews-dir path/to/reviews_root \
--specs-dir path/to/specs_root \
--jobs 1 \
--review-rounds 4 \
--skip-existingExpected panel outputs:
reproduce_panel.pyreproduce_panel.pngreproduce_panel.pdf
Expected mirrored review/spec outputs:
reproduce_panel_run_log.mdreproduce_panel_review_notes.mdreproduce_panel_review_summary.jsonreproduce_panel_prompt.mdreproduce_panel_raw_response.txt
Dry Run
Use --dry-run before a live run to create/check task context and print the nested Codex prompt without running it:
python3 -m nature_panel_forge.reproduce_image --image path/to/target_panel.png --out-root UserRuns/dry_run --dry-run --print-commandFor existing panel directories, add --dry-run to the batch reproduce or refine command.
Refine Existing Output
Use refinement only after a baseline reproduction exists:
python3 examples/prompt_codex_refine_reproduce.py \
--panel-dir path/to/panel_dir \
--panel-root path/to/panel_root \
--reviews-dir path/to/refine_reviews_root \
--specs-dir path/to/refine_specs_root \
--jobs 1 \
--review-rounds 4 \
--skip-existingRefine in place by editing reproduce_panel.py; do not create a competing script. Also write refine_complexity_assessment.json.
Show full SKILL.md (149 more words)Show less
Review Loop
Each live run should alternate code-writing and review passes until close enough or --review-rounds is reached. The review must compare the saved PNG against target.png and record concrete findings about chart type, data pattern, axes, ticks, labels, legends/colorbars, annotations, colors, font/readability, edge visibility, and layout collisions.
If a review finds a fixable issue, edit the Python code and rerender. Do not modify target.png, target.pdf, metadata, score files, prompts, or raw source context.
Validation
Before reporting success, verify:
python path/to/reproduce_panel.pyexits successfully.- The PNG and PDF outputs exist and are regenerated by the script.
- Review summary JSON has
review_passed: true. - Refine runs also have
font_audit_passed,layout_audit_passed, andedge_visibility_passedset to true. - The final response lists created files, final PNG size, iteration count, and the regeneration command.
Natural-Language Use
When the user asks in natural language, infer the CLI call and run the workflow. A good request looks like:
Use the codex-panel-reproduce skill to reproduce this scientific panel as editable Python/matplotlib code.
Target image: /path/to/target_panel.png
Optional PDF: /path/to/target_panel.pdf
Output root: UserRuns/my_panel
Panel id: my_panel
Chart type: bubble_plot
Caption: A short description of the visual structure, axes, legend, and data pattern.
Do not use Qwen scoring. Generate reproduce_panel.py, reproduce_panel.png, reproduce_panel.pdf, review notes, review summary, and a run log. Then report the output directory, review_passed, contract_passed, final PNG size, and rerender command.© littlepeachs, 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/codex-panel-reproduce of littlepeachs/NaturePanelForge.
Open the folder on GitHubat commit 0ca0c91
Compare with similar skills
Codex Panel Reproduce 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Codex Panel Reproduce this skilllittlepeachs/NaturePanelForge | 223 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Scientific Figure MakingChenLiu-1996/figures4papers | 8.3k | — | ~557 | Automated safety check: Pass | Custom licence | |
| Plot From ImageTrae1ounG/paper-plot-skills | 872 | 1 repos | ~868 | Automated safety check: Pass | None | |
| Python Executorcortega26/chile-hub | 113 | 2 repos | ~1.5k | Automated safety check: Pass | MIT | |
| FigMirror Figure Style TransferVILA-Lab/FigMirror | 521 | — | ~2.1k | Automated safety check: Pass | None | |
| Ieee Figure TableCloudWave818/ieee-skills | 359 | — | ~1k | Automated safety check: Pass | MIT |
Similar skills
Plot From Image
Trae1ounG/paper-plot-skills
Reproduce any academic paper figure from an uploaded image using accumulated style experience.
Python Executor
cortega26/chile-hub
Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh).
FigMirror Figure Style Transfer
VILA-Lab/FigMirror
Redraws your data as a matplotlib figure in the visual style of a reference paper figure, using a drawer and reviewer loop.
Ieee Figure Table
CloudWave818/ieee-skills
Audit, redesign, generate, and improve IEEE manuscript figures, tables, captions, result presentation, plotting scripts, visual polish, hybrid Python/R plus vector-editor workflows…
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.
Related
Works with
Categories
Questions about Codex Panel Reproduce
What does Codex Panel Reproduce do?
A skill your agent uses when asked to reproduce or refine a single scientific figure panel as editable Python/matplotlib code in NaturePanelForge. Codex Panel Reproduce is an agent skill from littlepeachs/NaturePanelForge. Use this skill when asked to reproduce or refine a single scientific figure panel as editable Python/matplotlib code in NaturePanelForge.
When should I use Codex Panel Reproduce?
Codex Panel Reproduce fits situations like: asked to reproduce; refine a single scientific figure panel as editable Python/matplotlib code in NaturePanelForge.
How do I install Codex Panel Reproduce in Claude Code?
Run `npx skills add littlepeachs/NaturePanelForge --skill codex-panel-reproduce -a claude-code`. Or copy the skill folder (skills/codex-panel-reproduce in littlepeachs/NaturePanelForge) into .claude/skills/codex-panel-reproduce in your project. Claude Code loads it when a task matches its description.
How do I install Codex Panel Reproduce in Codex?
Run `npx skills add littlepeachs/NaturePanelForge --skill codex-panel-reproduce -a codex`. Or copy the skill folder (skills/codex-panel-reproduce in littlepeachs/NaturePanelForge) into .agents/skills/codex-panel-reproduce in your project. Codex loads it when a task matches its description.
Can I use Codex Panel Reproduce 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 littlepeachs/NaturePanelForge --skill codex-panel-reproduce -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codex-panel-reproduce, .gemini/skills/codex-panel-reproduce, .github/skills/codex-panel-reproduce and .opencode/skills/codex-panel-reproduce in your project.
What does Codex Panel Reproduce need to run?
Going by SKILL.md and its folder, Codex Panel Reproduce needs the command-line tools its instructions call (python3 and python). Our summary lists: Python 3.
Does Codex Panel Reproduce 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 Codex Panel Reproduce 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 Codex Panel Reproduce use?
Codex Panel Reproduce 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 Codex Panel Reproduce use?
About 1.2k tokens (SKILL.md is roughly 4.9k 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 Codex Panel Reproduce?
Skills that share tags, products or a category with Codex Panel Reproduce: Scientific Figure Making (ChenLiu-1996/figures4papers, 8.3k stars), Plot From Image (Trae1ounG/paper-plot-skills, 872 stars), Python Executor (cortega26/chile-hub, 113 stars) and FigMirror Figure Style Transfer (VILA-Lab/FigMirror, 521 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Codex Panel Reproduce?
littlepeachs (a GitHub user) maintains it in littlepeachs/NaturePanelForge, which has 223 GitHub stars. The repository was last updated on July 16, 2026.
Source: littlepeachs/NaturePanelForge on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.