More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    Sourcerow: Real data, every row sourced and dated

    1

    Pulls facts from search, APIs, scrapers or client files, checks each claim at its source, strips personal data and duplicates, then seeds local first with a source link and verified date per row.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Sourcerow: Real data, every row sourced and dated

    Sourcerow: Real data, every row sourced and dated

    Example session with this skill installed

    Sourcerow: build a dataset of public libraries in Riverton for our app demo. Name, address, opening hours, phone. Official sources only, seed to my local DB.

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

    Sourcerow report: Riverton public libraries (example data)

    Scope: entity library, fields name, address, opening_hours, phone, plus source_url, verified_at, licence. Consumer: local Postgres libraries table.

    Sources audited

    SourceTypeLicenceChecked
    Riverton open-data portal (libraries.csv)clean fetchopen licence, attribution required2026-10-19
    Riverton City Library site (branch pages)clean fetchfacts only, no text copied2026-10-19

    Pull and clean: 31 rows pulled, 4 duplicates removed on branch_code, 27 unique.

    Verification (27 rows)

    StatusCount
    CONFIRMED22
    NOT_SUPPORTED3
    DEAD_LINK2

    Only the 22 CONFIRMED rows are kept. Branch phone numbers are public listings; no personal contacts stored.

    Seed (dry run, then write)
    New 22 · Existing 0 · Skipped 0 · Error 0. Written to local only. Second run: New 0 · Existing 22 · Error 0.

    Not found

    • Opening hours for Eastgate Mobile Library (no official page)
    • Phone for Millbrook Reading Room (portal field empty)
    • Mill Lane branch: portal lists it, branch page returns 404 (DEAD_LINK)

    Next steps

    • Confirm the two missing values with the library office, or keep them marked Provisional.
    • Re-verify opening hours right before the demo deploy.
    • Approve a hosted write if the demo needs the data online.

    libraries.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

    A demo, deck or directory full of placeholder facts looks fine until someone asks where a number came from. Stale prices, closed businesses still listed and figures nobody can trace undermine the whole product. Sourcerow replaces invented data with real data where every row carries its source and the date it was checked.

    What it does

    • Source audit classifies each source (clean fetch, bot-protected, login-gated, client-rendered) and records licence, attribution rule and rate limit before any pull.
    • Claim verification opens the source behind each fact and tags it CONFIRMED, NOT_SUPPORTED, PII or DEAD_LINK; only CONFIRMED rows are kept.
    • PII guard keeps raw files local and gitignored and verifies with aggregates (counts, coverage), never by echoing rows.
    • Clean and dedupe normalizes phones, names and localities and dedupes on a stable natural key.
    • Idempotent seed defaults to a dry run that prints New, Existing, Skipped and Error, then upserts to a local database first.

    How it works

    1. Scope the entity, fields, area, time window and freshness, adding source_url, verified_at and licence to the field list.
    2. Pull by the cheapest reliable path: web search or fetch, a hosted scraper actor (balance checked first), then self-hosted fallbacks.
    3. Verify and clean every claim, filter noise and re-express outside content in your own words.
    4. Seed and report counts per status, sources with dates and an explicit not-found list.

    Frameworks & tools

    Uses REST APIs, CSV, RSS, WordPress REST API and open-data portals for clean sources, with Scrapling (StealthyFetcher), Playwright with a saved storageState, Telethon for chat channels, OCR, openpyxl in read-only mode and OSM Overpass as fallbacks or for specific variants.

    Why this beats prompting it yourself

    A plain prompt will happily fill a gap with a plausible number. Sourcerow never invents a value: unverified rows are marked Provisional or left out, and a second seed run must report 0 new and 0 errors.

    Use cases

    • Demo catalogs built from open data instead of made-up entries.
    • Outreach directories collected, deduped and exported to CSV.
    • Client spreadsheets imported read-only into a database with a preview.
    • Research for decks and posters delivered as a source table.

    Known limitations

    Not for synthetic test fixtures or production schema changes. Hosted database writes happen only on an explicit decision. If a source's licence forbids scraping, it asks for an export or official API instead.

    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

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scanned

    Verified clean 1 day ago

    • Passed all security checks, Safe to install

    Requires

    Scrapling
    Playwright
    Telethon
    OCR
    openpyxl
    OSM Overpass

    Listed1 day ago

    What's inside

    Frequently Asked Questions