Voltpeer data

    1

    Standardize raw LAND and NEWARE battery cycler exports into validated, plot-ready datasets.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    Voltpeer data

    Example session with this skill installed

    I have a LAND export named 'cell_a_cycle.csv'. Inspect the file and help me map the columns so I can plot specific capacity later. The cell mass was 1.2mg.

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

    I have inspected cell_a_cycle.csv. The file contains 12,450 rows across 14 columns. No blank rows were detected, and all values in the voltage/current columns are parseable as floats.

    Inspection Results

    HeaderSample ValueData TypeStatus
    Index1IntegerSequential
    Cycle_ID1IntegerStep Basis
    Voltage(V)3.652FloatValid
    Current(mA)-0.501FloatNegative (Discharge)
    Capacity(mAh)0.042FloatCumulative
    Timestamp2023-10-01 10:00StringParseable

    I have prepared a mapping configuration. Please confirm the following:

    1. Current Sign: Negative values represent Discharge (Standard).
    2. Normalization: Capacity will be divided by 1.2 mg to yield mAh/g.
    3. Units: Voltage is in V, Current is in mA.

    Next steps

    1. Confirm the mapping and normalization units above.
    2. Run the prepare command to generate the .voltpeer/ project record and mapped CSV.
    3. Once confirmed, use voltpeer-plot to render the capacity vs. voltage curves.

    cell_a_cycle.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 test data is messy, inconsistent, and prone to unit errors. Raw exports from instruments like LAND or NEWARE often come with ambiguous column headers, hidden metadata layers, and varying sign conventions that break standard plotting scripts. This skill provides a structured ingestion pipeline to turn raw battery cycler files into analysis-ready datasets without losing data integrity.

    What it does

    • Multi-format ingestion processes LAND (.csv, .txt) and NEWARE (.ndax, .ndc-14) exports including multi-layer workbooks.
    • Structural inspection scans headers, row counts, and blanks to identify table layout before processing.
    • Canonical mapping creates a JSON-based schema to map instrument-specific columns to standardized fields.
    • Integrity preservation retains all original observations and cell values while adding labeled canonical fields.
    • Readiness validation tracks unit confirmation, normalization bases, and sign conventions to gate downstream plotting.
    • Exclusion logging records specific row exclusions with human-provided reasons and MD5 hashes for provenance.

    How it works

    1. Inventory raw files by reading sample rows to identify instrument types and data structures.
    2. Run inspection scripts to report headers and parseability without assigning scientific meaning prematurely.
    3. Define mapping contracts via JSON to specify units, cycle basis, and normalization denominators.
    4. Execute preparation to generate a standardized output directory containing mapped data and audit logs.

    Frameworks & tools

    This tool utilizes Python-based processing scripts (scripts/prepare_csv.py, scripts/instrument_import.py) and specialized handlers for Excel and battery cycler proprietary formats.

    Why this beats prompting it yourself

    Generic prompts often guess units based on magnitude or silently drop "bad" data points, leading to scientific inaccuracy. This skill enforces a strict execution contract that requires human confirmation of normalization and sign conventions before flagging data as ready for publication-grade plotting.

    Use cases

    • LAND/NEWARE import for cleaning raw cycler exports for electrochemical analysis.
    • Protocol standardization for mapping disparate lab formats to a single canonical schema.
    • Audit trail generation for tracking data exclusions and unit origins in research papers.
    • Normalization prep for calculating specific capacity using confirmed mass or area values.

    Known limitations

    Does not include plot rendering or scientific interpretation. Requires manual confirmation of units and normalization factors to achieve "ready_for_plot" status. Existing output directories are protected from overwriting.

    How to use

    Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scanned

    Verified clean 8 days ago

    • Free to download with an account

    Requires

    Python

    Listed8 days ago

    What's inside

    Frequently Asked Questions