Look up official company data from European public registries across 11 countries/regions (CZ, SK, PL, DE, UK, NL, RO, HR, SE + EU-level + ESG). Covers company registration, ownership, financial filings, VAT status, ESG data. Use when the user asks to "look up a company", "check registry", "find company info", "look up IČO/KRS/LEI/CRN", "company due diligence", "check VAT status", "find ownership structure", or needs official data from European registries. Reads tracked companies from data/companies.json. Some lookups use Python scripts (stdlib), some fall back to Apify actors for scraping-based registries.
npx skills add https://github.com/apify/awesome-skills --skill apify-public-registries
Look up official company data from European public registries via Python scripts (direct REST API)
or Apify actor fallback (scraping when no API exists).
apify CLI (npm install -g apify-cli && apify login); fallback: Apify MCP connector (call-actor tool). CLI is faster and preferred when both are available.KVK_API_KEY env var (register at developers.kvk.nl — see REGISTRATION/NL.md)GUS_API_KEY env var (email [email protected])${CLAUDE_PLUGIN_ROOT} is the plugin's root directory (where .claude-plugin/ lives). It is resolved automatically by Claude Code when the plugin is installed, or set to the --plugin-dir path during development.
Copy this and tick boxes as you progress:
Task Progress:
- [ ] Step 0: Verify prerequisites — run `python3 --version` (required); for Apify-dependent registries: try `apify --version && apify info`, or check for `call-actor` MCP tool; if neither, tell user to install apify CLI or Apify MCP connector
- [ ] Step 1: Identify country + identifier type (IČO/KRS/CUI/LEI/company name)
- [ ] Step 2: Run the lookup command per country table
- [ ] Step 3: Interpret results (key fields vary by source)
- [ ] Optional: Apify fallback for scraping-based registries
- [ ] Optional: Cross-reference with EU-level sources (GLEIF LEI, ESMA bonds, EBA)
All paths relative to ${CLAUDE_PLUGIN_ROOT}/skills/apify-public-registries/.
| Country | Command | Identifier | Access |
|---|---|---|---|
| CZ | python3 reference/scripts/CZ/fetch_all.py lookup <IČO> | IČO (8-digit) | Free (ARES API) |
| SK | python3 reference/scripts/SK/fetch_all.py lookup <IČO> | IČO | Free (ORSR scraping) |
| PL | python3 reference/scripts/PL/fetch_all.py lookup <KRS> | KRS (10-digit, zero-padded) | Free (KRS API) |
| PL | python3 reference/scripts/PL/fetch_all.py lookup_nip <NIP> | NIP (10-digit) | Free (Biała Lista, 100/day) |
| PL GUS | (included in batch fetch_all.py) | NIP | GUS_API_KEY REQUIRED — without it, returns fake test data silently (see gotchas) |
| DE | python3 reference/scripts/DE/fetch_all.py keyword <name> | Company name | Apify (mcpc CLI) |
| UK | python3 reference/scripts/UK/fetch_all.py search <name> | Company name | Apify (mcpc CLI) |
| NL | python3 reference/scripts/NL/fetch_all.py | KVK number (configured) | API key (KVK_API_KEY) |
| RO | python3 reference/scripts/RO/fetch_all.py lookup <CUI> | CUI number | Free (ANAF — offline since 2026-03) |
| HR | Manual — see REGISTRATION/HR.md | OIB / MBS | OAuth registration |
| SE | Manual — see REGISTRATION/SE.md | Org.nr | Bolagsverket registration |
| EU | python3 reference/scripts/EU/fetch_all.py lookup <name> | Company name | Free (GLEIF + ESMA + TED) |
| EU | python3 reference/scripts/EU/fetch_all.py lookup_lei <LEI> | LEI (20-char) | Free (GLEIF) |
| ESG | python3 reference/scripts/ESG/fetch_all.py lookup <country> | Country name/ISO code | Free |
| Need | Best source | Command |
|---|---|---|
| Basic profile (name, address, legal form) | CZ: ARES, SK: ORSR, PL: KRS, DE: Handelsregister, UK: Companies House | See country table above |
| Ownership / corporate tree | EU GLEIF | EU/fetch_all.py lookup_lei <LEI> |
| Financial filings (CZ) | Justice.cz sbírka listin (Apify fallback) | CZ/fetch_all.py justice |
| Financial filings (SK) | FinStat.sk | SK/fetch_all.py finstat |
| Financial filings (PL) | eKRS via Apify | PL/fetch_all.py financials |
| Bonds & instruments | ESMA FIRDS | EU/fetch_all.py lookup <name> |
| VAT / due diligence (CZ) | DPH register | Included in CZ/fetch_all.py lookup |
| VAT / due diligence (PL) | Biała Lista | PL/fetch_all.py lookup_nip <NIP> |
| Bank regulatory data | EBA Transparency CSVs (100MB+) | EU/fetch_all.py eba |
| ESG / emissions | Climate TRACE + EU ETS | ESG/fetch_all.py lookup <country> |
| Regulated entities (CZ) | ČNB bank list + OAM | CZ/fetch_all.py cnb_banks / cnb_oam |
| Public procurement | TED | EU/fetch_all.py lookup <name> |
${CLAUDE_PLUGIN_ROOT}/data/companies.json -> identifiers.registry_ids for existing IDs.Identifier types by country:
Execute the command from the country table. Scripts are at:
${CLAUDE_PLUGIN_ROOT}/skills/apify-public-registries/reference/scripts/<CC>/fetch_all.py
Example — look up a company in Czech ARES:
python3 ${CLAUDE_PLUGIN_ROOT}/skills/apify-public-registries/reference/scripts/CZ/fetch_all.py lookup 25099345
Example — find ownership chain via GLEIF:
python3 ${CLAUDE_PLUGIN_ROOT}/skills/apify-public-registries/reference/scripts/EU/fetch_all.py lookup_lei 31570048XH84U51GGT05
Example — look up InPost in KRS:
python3 ${CLAUDE_PLUGIN_ROOT}/skills/apify-public-registries/reference/scripts/PL/fetch_all.py lookup 0000536554
Batch fetch (all companies in a country):
python3 reference/scripts/CZ/fetch_all.py # all CZ sources (ares, dph, cnb_banks, cnb_oam, justice)
python3 reference/scripts/PL/fetch_all.py # all PL sources (krs, biala_lista, gus, financials)
python3 reference/scripts/EU/fetch_all.py # all EU sources except EBA (gleif, ted, esma, eurostat)
Key fields vary by source:
| Source | Key fields |
|---|---|
| ARES (CZ) | obchodniJmeno, dic, sidlo.textovaAdresa, czNace, datumVzniku, pravniForma |
| DPH (CZ) | nespolehlivyPlatce (unreliable payer flag), bank accounts |
| GLEIF (EU) | lei, legalName, jurisdiction, status, registeredAs, parent LEI + name |
| KRS (PL) | nazwa, nip, regon, kapital (share capital) |
| Biała Lista (PL) | statusVat, krs, regon, accountNumbers |
| ORSR (SK) | name, address, legal_form, share_capital, registration_date |
| FinStat (SK) | revenue, profit, employees, assets |
| Handelsregister (DE) | name, legal form, share capital, management, HRB number |
| Companies House (UK) | company number, SIC codes, directors, incorporation date |
| ESMA FIRDS (EU) | isin, lei, instrument name, cfi_code, status |
| TED (EU) | buyer-name, winner-name, total-value, procedure-type |
| ANAF (RO) | denumire, adresa, scpTVA (VAT payer flag), active status |
When no direct API exists, use Apify CLI with a specific actor or apify/website-content-crawler:
apify call apify/website-content-crawler \
--input '{"startUrls":[{"url":"https://or.justice.cz/ias/ui/rejstrik-$firma?ico=25099345"}],"maxCrawlPages":1}' \
--user-agent apify-awesome-skills/apify-public-registries
Apify-dependent registries:
| Country | Registry | Actor | Trigger |
|---|---|---|---|
| DE | Handelsregister | radeance/handelsregister-api | DE/fetch_all.py keyword <name> |
| UK | Companies House | dhrumil/company-house-scraper | UK/fetch_all.py search <name> |
| PL | eKRS Financials | minute_contest/poland-krs-financial-scraper | PL/fetch_all.py financials |
| CZ | Justice.cz filings | apify/website-content-crawler | Direct via apify CLI |
| RO | ListaFirme.ro | apify/website-content-crawler | RO/fetch_all.py listafirme |
| SE | Allabolag.se | apify/website-content-crawler | Manual (residential proxy needed) |
Note: DE, UK, and RO scripts use mcpc CLI internally (not apify CLI).
CZ (ares, dph, cnb_banks, cnb_oam, justice), SK (orsr, finstat), PL (krs, biala_lista, gus),
EU (gleif, esma, ted, eurostat), ESG (ets, climate_trace), RO (anaf)
DE (handelsregister), UK (companies_house), PL (financials via eKRS),
CZ (justice.cz sbírka listin via scraping), RO (listafirme.ro)
KVK_API_KEY — register at developers.kvk.nl (REGISTRATION/NL.md)GUS_API_KEY — email [email protected] (test key abcde12345abcde12345 exists but has no real data)GUS_API_KEY is unset — test server returns plausible-looking records (ul. Test-Krucza, Kraków-Podgórze) for any valid NIP. Production key required: email [email protected]. Always inspect first GUS record to confirm prod vs test.@apify session.EU/fetch_all.py eba separately, not as part of normal batch.fetch_all.py without arguments) reads lookup_targets.json from the script's directory — these are per-country ID→name mappings, NOT copies of data/companies.json. For single-company lookups, pass the identifier directly.Get Firecrawl credentials and SDK setup into a project. Use when an application needs `FIRECRAWL_API_KEY`, when an agent should add Firecrawl to `.env`, when the user wants to authenticate Firecrawl for app code, or when choosing the first SDK and docs for a new Firecrawl integration. This skill includes its own browser auth flow, so it does not depend on the website onboarding skill.
Searches Meta Ad Library (Facebook/Instagram/WhatsApp ads) by keyword or Facebook page ID and extracts ad details including creatives, copy, CTA, publisher platforms, spend, impressions, reach estimates, and page transparency info. Use when user mentions Meta Ad Library, Facebook ads scraper, Instagram ads data, FB ad library, search Facebook ads, get ads from a Facebook page, scrape Meta ads, Facebook advertising data, ad creative extraction, competitor ads analysis, brand ads monitoring, Meta advertising transparency, political ads Facebook, housing ads Facebook, view all ads from a page, facebook ads search, fb ads library api, facebook ad archive, instagram ad data, get ad creatives.
> Scrapes LinkedIn job postings using the JobSpy library (python-jobspy). Use this skill whenever the user wants to find jobs on LinkedIn, search for open roles, pull job listings, build a job pipeline, source job targets for GTM research, or monitor hiring signals. Even if the user just says "find me some jobs" or "what roles is [company] hiring for", use this skill. It runs a local Python script that outputs a CSV of job postings with title, company, location, salary, job type, description, and direct URLs.
When the user wants to fix indexing issues from Search Console, use noindex, or implement Google Indexing API. Also use when the user mentions "fix indexing," "not indexed," "Crawled - currently not indexed," "discovered - currently not indexed," "index coverage," "noindex," "noindex tag," "pages not indexed," "why not indexed," "request indexing," or "Google Indexing API." For sitemap, use xml-sitemap.
| Discover and list all URLs on a website without extracting content, via the Tavily CLI. Use this skill when the user wants to find a specific page on a large site, list all URLs, see the site structure, find where something is on a domain, or says "map the site", "find the URL for", "what pages are on", "list all pages", or "site structure". Faster than crawling — returns URLs only. Essential when you know the site but not the exact page. Combine with extract for targeted content retrieval.
Use when the user needs X (Twitter) data or confirmation-gated X actions through Xquik: tweet search, user lookup, follower extraction, media download, monitoring, webhooks, MCP, SDKs, posting, likes, DMs, and profile updates. Requires a Xquik API key. Never ask for X login material.
Use Xquik for X data workflows: tweet search, user lookup, follower export, media downloads, monitors, webhooks, REST API, MCP, SDK setup, and approval-gated account actions.
Use Xquik for X/Twitter REST, MCP, SDKs, search, filtered exports, monitoring & approved publishing. Not affiliated with X Corp. Trigger for X API alternatives, pricing comparisons, tweet search, user lookup, timelines, follower exports, media, webhooks, bulk extraction, giveaways, or MCP setup. Read-only by default. Require explicit approval for writes, private reads, monitors, webhooks & metered bulk jobs.
Take apify/apify-public-registries from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference npm.
Without those the skill loads but fails at the first command.