Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Voltpeer assemble

    1

    Assemble and align multi-panel battery research figures with millimetre precision and full data provenance.

    Free

    1 useSecurity scanned

    Voltpeer assemble

    Example session with this skill installed

    I have three PNG plots (cycling, rate, and SEM) in /data/exp1. Assemble them into a single-column manuscript figure with standard battery labels. Check for axis alignment.

    • Read your context and instructions
    • Compiled the voltpeer assemble
    • Generated the image

    I have inventoried the three panels provided in /data/exp1. The cycling and rate capability plots share a common X-axis scale (Cycle Number), while the SEM image requires a hero-slot placement due to its aspect ratio. I have generated the figure manifest and a diagnostic preview.

    Manuscript Figure Assembly: Experiment 1

    PanelSource FileEvidence RoleStatus
    acycling_1C.pngLead ResultAligned
    brate_cap.pngDirect SupportAligned
    csem_surface.pngCondition BoundaryScale Bar Verified
    {
      "figure_id": "fig_exp1_assemble",
      "layout": "single_column",
      "width_mm": 89,
      "panels": [
        {"slot": "a", "source": "cycling_1C.png", "crop": "none"},
        {"slot": "b", "source": "rate_cap.png", "crop": "none"},
        {"slot": "c", "source": "sem_surface.png", "crop": "fixed_aspect"}
      ],
      "qa_check": {
        "axis_alignment": "pass",
        "label_consistency": "pass",
        "effective_dpi": 300
      }
    }
    

    The assembled figure has been placed in results/fig_exp1_final.pdf. I have applied the 1.5 pt coordinate-ruler gate to ensure the Y-axes of panels

    a and

    b are perfectly flush. Redundant titles were removed from the individual PNGs to maintain a clean manuscript look.

    Next steps

    1. Review the results/index.html contact sheet to verify the SEM scale bar visibility.
    2. Confirm if a specific journal width (e.g., 120mm or 180mm) is required for the final export.
    3. Provide copyright/provenance notes if this figure is intended for a Review article.

    cycling_1C.png

    PNG · 1536×1024

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Manually arranging battery research panels in generic design tools leads to misaligned axes, inconsistent typography, and lost data provenance. voltpeer-assemble is a specialized agent skill for battery scientists and engineers that automates the construction of publication-ready manuscript figures while maintaining strict scientific integrity. It handles the physical layout of microscopy, cycling data, and spectra, ensuring every panel is traceable and dimensionally accurate for journal submission.

    What it does

    • Multi-format assembly combines PNG, TIFF, PDF, and SVG panels into a single aligned manuscript plate.
    • Scientific grid enforcement applies specific battery research layout recipes to ensure evidence hierarchy is clear.
    • Traceability mapping maintains a project-local manifest linking every panel to its original source file and rights status.
    • Automated QA runs a coordinate-ruler gate to detect axis misalignments, inconsistent margins, and low DPI.
    • Manuscript-first styling automatically manages uniform labeling (a, b, c) and strips redundant panel subtitles.

    How it works

    1. Inventory: The skill scans the source folder to generate contact sheets and verify panel dimensions.
    2. Evidence mapping: You define the role of each panel (lead result, support, or validation) to determine the layout hierarchy.
    3. Manifest generation: A JSON manifest is created to lock in grid occupancy, physical millimetre sizes, and crop instructions.
    4. Strict composition: The compose_figure.py tool generates the final PDF/PNG with a diagnostic ruler overlay for final inspection.

    Frameworks & tools

    This skill utilizes a custom Python-based composition engine requiring CairoSVG for vector handling. It integrates with .voltpeer project structures for metadata persistence.

    Why this beats prompting it yourself

    Generic LLMs cannot verify if two plots have aligned X-axes or if a scale bar has been accidentally cropped. This skill uses a physical-layout engine to ensure millimetre-perfect alignment and enforces battery-specific data encoding rules that LLMs otherwise ignore.

    Use cases

    • Assembling multi-panel cycling figures for peer-reviewed battery manuscripts.
    • Creating evidence-story layouts for internal technical review presentations.
    • Consolidating heterogeneous data (SEM images + XRD spectra) into a single plate.
    • Auditing existing figure drafts for axis alignment and typography consistency.

    Known limitations

    Does not perform native image vision without host-exposed tools. SVG composition requires a local Cairo installation. Cannot recolor rasterized microscopy or heatmaps.

    Requires Cairo for SVG support. No native image vision; depends on host tools for visual inspection. Cannot modify data inside flattened raster panels.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Requires

    Python

    Permissions

    Terminal / Shell
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill automates the precise alignment of battery research figures (like SEM images and cycling plots) using a physical-layout engine that enforces scientific grid hierarchy and maintains a JSON manifest for full data provenance.

    The skill supports PNG, TIFF, PDF, and SVG formats, allowing you to combine heterogeneous data like vector-based spectra and rasterized microscopy into a single, high-resolution manuscript plate.

    This skill is designed for AI agents with Python execution capabilities and requires a local installation of CairoSVG for vector handling, specifically integrating with .voltpeer project metadata structures.

    You receive the specialized layout engine, pre-defined battery research layout recipes, the `compose_figure.py` tool, and a diagnostic ruler system for automated quality assurance.

    The skill includes an automated QA gate that detects axis misalignments, inconsistent margins, and low DPI, ensuring your figures meet strict journal submission standards before you export.

    New in Agents & Orchestration