Overview
Preserve meaning before optimizing looks. This workflow makes figures that don't lie: bars and areas start at zero, axis breaks are declared, error bars state which uncertainty and how much data behind them, missing/zero/excluded points are visibly distinguished rather than quietly connected, and dual axes get avoided where possible. Raw data, filters, normalizations and seeds stay filed beside the figure, and the delivered file is reopened and inspected instead of trusting defaults.
Plotting runs in the task's compute environment with publication style presets, color-blind-safe palettes and text-contrast checks — color always paired with a second cue like shape or label — exporting PNG, PDF and SVG at controlled sizes and fonts. Journal requirements are never guessed: identify journal, article type and stage, verify against current official guidance, then a human eye closes the loop.
Static publication figures are this release's deliverable; automated checks assist, but compliance calls remain human.
Where it helps
- Produce manuscript figures with clearly named error bars and sample sizes, data notes archived alongside
- Audit existing figures for contrast and grayscale legibility
- Plan exports against the target journal's live requirements with size checks
- Rebuild color-blind-hostile figures with redundant visual encoding
#charts#matplotlib#png#PDF
Examples
Examples describe the request and the shape of the expected deliverable; they are not completed run results.
01Example prompt
Make a journal single-column figure from these three-timepoint means: 95% bootstrap CIs, raw points overlaid, color-blind-safe palette with marker redundancy, export 600-dpi PNG plus vector PDF with data provenance.
Expected output
Two reopened-and-verified exports with their data-provenance notes (sources, processing, seed, missing-data handling) and contrast-check results.
02Example prompt
This dual-axis chart looks like it's inflating a correlation — rebuild it per the guardrails: justify dropping dual axes, show the alternative encoding, and list which caption claims must change.
Expected output
An honestly re-encoded replacement figure with caption corrections itemized, originals kept.
Requirements and limits
- Install platforms
- iOS: iOS · Android: Android
- Script runtime
- Runs scripts in the task environment
- Minimum app version
- 1.7.60
Reviewed permission scope
iOS · Android
- Capabilities
- Remote executionRead workspace filesWrite workspace files
- Reviewed tools
- Shell commands
- Reviewed dependencies
- matplotlib==3.10.1 · numpy==2.2.4 · pillow==11.1.0 · pypdf==5.4.0
- Review decision
- Approved
- Review stage
- Guest execution qualification
- Reviewed on
- 2026-10-27
Implementation and runtime details
- Adaptation stage
- frozen
iOS
- Tools
- Shell commands
- Capabilities
- Remote executionRead workspace filesWrite workspace files
- Runtime environment
- linux / riscv64 · guest-verified
Android
- Tools
- Shell commands
- Capabilities
- Remote executionRead workspace filesWrite workspace files
- Runtime environment
- linux / riscv64 · guest-verified
License and source
Source and trace details
License
MIT
MIT (root LICENSE.md)
MIT at the pinned upstream revision; full license and per-file adaptation/asset audit are preserved in references/licenses/. Floe additions and synthetic fixtures are identified separately.
- Source
- https://github.com/K-Dense-AI/scientific-agent-skills
- Upstream path
- skills/scientific-visualization
- Source checked
- 2026-10-26
- Publisher
- JiangNanGenius
- Publication commit (retrieval)
- 25e07dbeeb6cc93c2fe83ddc72a34302cc40832a
- Audited source commit
- 84c524b6fb483e4cad94db076e7d9c9962966c19
- Signed catalog digest
- iOS 46196ba57ed7ea7f22085e74b113207f31193e820ab8983cf7a60eee953f2340 · Android 16de89d019e2057804a40f215485ccb09d5495a25864b34d681168eeaf8f9697
- Publication snapshot (UTC)
- 2026-10-31
Publication commit 25e07dbeeb, audited source 84c524b6fb; catalog digest iOS 46196ba57ed7… · Android 16de89d019e2….
Versions and status
Version records ship with the signed catalog; the target and released versions are shown below.
- Adaptation
- Ready
- Publication state
- Curated skills are available
- Deep adaptation
- Yes
- Released version
- 1.1.0