Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseOpenClawOpenClaw+21 more

    dosen pt indonesia data agent

    3

    Standardize and merge PDDIKTI, SINTA, and HR data for Indonesian university accreditation and Tridharma reporting.

    $15

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    0 installsSecurity scanned
    dosen pt indonesia data agent

    dosen pt indonesia data agent

    Example session with this skill installed

    I have a CSV of faculty NIDNs and a JSON export from SINTA. I need to generate a summary for BAN-PT Kriteria 5 showing total publications and Sinta 1-2 counts grouped by Program Studi.

    • Read your context and instructions
    • Compiled the dosen pt indonesia
    • Generated the data export

    I have processed the request to merge your PDDIKTI faculty data with SINTA research records. The logic ensures NIDN strings are preserved and publications are categorized by their impact levels as required for Kriteria 5.

    BAN-PT Kriteria 5: Research Summary Pipeline

    import pandas as pd
import json

def generate_kriteria_5_summary(faculty_csv, sinta_json):
    # Load faculty data (PDDIKTI export)
    df_faculty = pd.read_csv(faculty_csv, dtype={'NIDN': str})
    
    # Load SINTA publication data
    with open(sinta_json, 'r') as f:
        sinta_data = json.load(f)
    df_sinta = pd.DataFrame(sinta_data)
    df_sinta['author_nidn'] = df_sinta['author_nidn'].astype(str)

    # Calculate metrics
    sinta_1_2 = df_sinta[df_sinta['sinta_level'].isin([1, 2])]
    
    total_pubs = df_sinta.groupby('author_nidn').size().reset_index(name='total')
    top_tier_pubs = sinta_1_2.groupby('author_nidn').size().reset_index(name='sinta_1_2')

    # Merge with faculty list
    df_merged = pd.merge(df_faculty, total_pubs, left_on='NIDN', right_on='author_nidn', how='left')
    df_merged = pd.merge(df_merged, top_tier_pubs, on='author_nidn', how='left').fillna(0)

    # Group by Program Studi for Accreditation Matrix
    summary = df_merged.groupby('program_studi').agg({
        'NIDN': 'nunique',
        'total': 'sum',
        'sinta_1_2': 'sum'
    }).rename(columns={
        'NIDN': 'Jumlah Dosen',
        'total': 'Total Publikasi',
        'sinta_1_2': 'Publikasi Sinta 1-2'
    })

    return summary.to_markdown()

# Usage: 
# print(generate_kriteria_5_summary('dosen_list.csv', 'sinta_export.json'))
    Program StudiJumlah DosenTotal PublikasiPublikasi Sinta 1-2
    Informatika2414238
    Sistem Informasi188612
    Teknik Elektro159422
    Manajemen3011015

    Next steps

    1. Ensure your dosen_list.csv contains a program_studi column matching BAN-PT nomenclature.
    2. Verify that the sinta_level field in your JSON export is an integer (1-6).
    3. Run the script locally to generate the final Markdown table for your accreditation document.

    dosen-pt-indonesia-data-agent.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.

    What you get

    Standardize NIDN identifiers across fragmented institutional datasets.Generate BAN-PT 9 Kriteria tables for Program Studi accreditation.Categorize faculty research outputs by SINTA levels and Scopus indexing.Mask sensitive student data to comply with UU PDP privacy regulations.Calculate faculty-to-student ratios and MBKM metrics for PDDIKTI feeds.

    About this skill

    The problem

    Indonesian university data is often trapped in fragmented silos across PDDIKTI, SINTA, and internal HR systems. Manually merging these for BAN-PT 9 Kriteria accreditation or BKD reporting leads to NIDN formatting errors, incorrect SINTA tier mapping, and UU PDP privacy risks.

    What it does

    • Standardizes NIDN and NIDK identifiers to prevent data corruption during CSV/JSON processing.
    • Maps publication data strictly to SINTA 1-6 levels and Scopus/WoS indexing for Hibah Dikti eligibility.
    • Calculates student-to-faculty ratios and faculty functional ranks (Jabatan Fungsional) per Program Studi.
    • Automates the aggregation of Tridharma pillars (Pendidikan, Penelitian, Pengabdian) into accreditation-ready matrices.
    • Enforces UU PDP compliance by masking sensitive student identifiers like NIK and KK before reporting.

    Frameworks & tools

    Python, Pandas, JSON, and CSV. Specific focus on Kemendikbudristek reporting standards including BAN-PT, LAM, PDDIKTI, and SINTA.

    Why this beats prompting it yourself

    Generic AI agents struggle with specific Indonesian academic taxonomies like NIDN string handling or the nuances of SINTA vs. WoS mapping for local accreditation. This skill provides pre-built logic for the 9 Kriteria framework, ensuring your data pipelines adhere to actual Kemendikbudristek regulations without manual prompt engineering for every schema.

    Use cases

    • Generating Kriteria 4 (SDM) and Kriteria 5 (Penelitian) matrices for BAN-PT accreditation.
    • Building BKD (Beban Kerja Dosen) validation pipelines from institutional HR exports.
    • Calculating MBKM metrics and student-to-faculty ratios for university dashboards.
    • Merging SINTA publication exports with faculty lists for internal research grant audits.

    Known limitations

    Requires local CSV/JSON exports from university systems; does not make direct network calls to live government APIs. Focused exclusively on the Indonesian higher education ecosystem.

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    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

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean 6 days ago

    • Passed all security checks, Safe to install

    Listed6 days ago

    What's inside

    Frequently Asked Questions