More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Voltpeer plot

    1

    Automated battery data plotting and manuscript figure auditing with strict scientific visualization standards.

    Free

    2 uses1.0 (1 review)

    Voltpeer plot

    Example session with this skill installed

    I have a NEWARE export for my NMC811 cell. Inspect the headers in cell_data.csv and plot the capacity retention and Coulombic efficiency using the clear journal style.

    • Read your context and instructions
    • Compiled the voltpeer plot
    • Generated the data export

    I have inspected the NEWARE export and mapped the columns for NMC811 cycling. The data contains 150 cycles with stable discharge capacity. I have applied the journal_clear style preset, which uses open/filled markers for charge/discharge and consistent rectangular spines.

    Battery Performance Plot

    The figure has been generated with cycle-by-cycle Coulombic efficiency (CE) and discharge capacity panels.

    MetricStatusMapping
    Source Filecell_data.csvVerified
    Capacity BasismAh g⁻¹Active Mass Mapped
    Retention98.2%Ref: Cycle 1
    CE Average99.85%Verified
    Output Pathresults/NMC811_cycling.pdfRendered
    
    # Provenance metadata extract
    {
      "source_id": "NMC811-04",
      "style": "preset:journal_clear",
      "axes": ["capacity", "efficiency"],
      "units": {"capacity": "mAh/g", "voltage": "V"},
      "evidence_state": "verified"
    }
    

    Next steps

    1. Review the PDF export in the results/ folder for axis tick readability at final column width.
    2. Verify the active mass value used for normalization in the generated .voltpeer/mapping.json.
    3. Provide the electrolyte volume and N/P ratio if you wish to include these in the automated caption.

    cell_data.csv

    CSV · data export

    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

    Battery research is stalled by messy instrument exports and inconsistent figure standards. This skill automates the ingestion of raw battery test data and renders publication-ready figures that adhere to strict scientific visualization rules.

    What it does

    • Standardizes exports by mapping LAND, NEWARE, and other cycler formats into verified CSV schemas without manual column editing.
    • Renders performance plots including cycle-by-cycle Coulombic efficiency, discharge capacity, and capacity retention with precise marker and line rules.
    • Enforces scientific consistency by validating full-cell baselines, normalization units (e.g., mAh g⁻¹), and temperature/rate conditions.
    • Generates vector outputs in PDF, SVG, and high-resolution TIFF formats optimized for journal submission requirements.
    • Audits visual claims by checking panel labels, scale bars, and coordinate spines against a specialized battery figure grammar.

    How it works

    1. Inspect and map using the inspect command to identify headers and units from raw instrument files.
    2. Configure metadata to record author-confirmed experiment conditions, sample IDs, and evidence states.
    3. Execute plotting via the shipped plot_uploaded.py program using pre-defined style presets.
    4. Verify output through a check stage that audits the rendered image for scientific anomalies or clipping.

    Frameworks & tools

    This skill utilizes a fixed Python plotting library (batteryplot), specialized parsers for battery cycler exports, and JSON-based metadata mappings. It manages assets through a local .voltpeer/ directory and generates standards-compliant vector graphics.

    Why this beats prompting it yourself

    Generic LLMs often hallucinate trend lines or fail to distinguish between capacity and retention baselines. This skill uses a fixed, tested program to ensure every point reflects the raw data exactly while enforcing domain-specific rules like separate markers for cycle data and solid lines for voltage profiles.

    Use cases

    • Converting raw 蓝电 (LAND) or NEWARE spreadsheet exports into publication-ready cycling figures.
    • Planning multi-panel manuscript figures with consistent legends and shared coordinate axes.
    • Auditing existing battery figures for missing scientific metadata like N/P ratios or electrolyte loading.
    • Generating standardized electrochemical spectra or dQ/dV traces with verified axis labels.

    Known limitations

    Native binary files (CEX/NDA) require prior vendor export to text/Excel. The skill does not perform model fitting, impedance equivalent circuit modeling, or independent experiment authentication.

    Requires vendor-exported text/Excel files; no binary CEX/NDA support. Does not perform Rias/EIS fitting or independent experiment authentication. Final visual review requires host vision.

    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

    1.0
    1 review
    5
    0
    4
    0
    3
    0
    2
    0
    1
    1

    This skill has been used 2 times.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Requires

    Github
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Allowed Hosts

    arrizabalagags-png.github.io
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    The skill includes specialized parsers that map raw exports from LAND, NEWARE, and other major cyclers into verified CSV schemas, eliminating the need for manual column cleaning or header renaming.

    You will receive the `voltpeer plot` engine, the `batteryplot` Python library, a suite of publication-ready style presets, and the `inspect` utility for automated metadata mapping.

    This skill is designed to run in any Python-enabled environment or AI agent workspace that supports local directory management, utilizing the `.voltpeer/` structure to store metadata and assets.

    Unlike generic prompts that may hallucinate trends, this skill uses a fixed, deterministic plotting program to ensure every data point is mathematically accurate while enforcing strict scientific rules for units and markers.

    It generates high-resolution vector outputs in PDF, SVG, and 600+ DPI TIFF formats, all pre-configured to meet the strict resolution and font requirements of major scientific journals.

    The skill requires data to be exported to text-based formats (like .csv or .xlsx) first; it does not currently support direct ingestion of native binary files like .CEX or .NDA.

    New in Research & Analysis