# llms-full.txt for informedclearly.com
site: https://informedclearly.com
owner: Informed Clearly
contact: https://informedclearly.com/contact
last-updated: 2026-06-07
version: 1.5

# Purpose
purpose:
  - Provide a complete machine-readable map of public pages, feeds, sitemaps, and APIs.
  - Describe canonical URL rules, language variants, and crawling etiquette.
  - Enable LLMs/agents to cite and summarize content safely and consistently.

# Languages (URL prefix)
languages:
  - en
  - nl
  - fr
  - de
  - es
  - pt

language-notes:
  - Public pages are language-prefixed: /{lang}/...
  - Prefer canonical URLs and the user's requested language where possible.
  - When uncertain, default to /en/.

# Curated entrypoints (start here)
entrypoints:
  - /en/
  - /en/news/1/
  - /en/summary
  - /en/finance
  - /en/finance/bitcoin
  - /en/similar/bitcoin
  - /en/search?q=bitcoin
  - /feed/rss/en
  - /sitemap.xml
  - /.well-known/ai-plugin.json
  - /.well-known/security.txt
  - /openapi.yaml
  - /api/articles
  - /api/languages

# Content types
content:
  html_pages:
    - /{lang}/
    - /{lang}/news/{page}/
    - /{lang}/articles/{page}/
    - /{lang}/{category}/
    - /{lang}/{category}/{page}/
    - /{lang}/{category}/{id}/{slug}
    - /{lang}/summary
    - /{lang}/summary/{date}
    - /{lang}/authors/{author-slug}
    - /{lang}/finance
    - /{lang}/finance/{slug}
    - /{lang}/similar/{keyword}
    - /{lang}/search?q={keyword}
  json_endpoints:
    - /{lang}/search_live?q={keyword}
    - /{lang}/finance/{slug}/chart?range={range}
  feeds:
    - /feed/rss
    - /feed/rss/{lang}
    - /feed/atom
    - /feed/atom/{lang}
  sitemaps:
    - /sitemap.xml
    - /sitemaps/static.xml
    - /sitemaps/news.xml
    - /sitemaps/categories.xml
    - /sitemaps/summaries.xml
    - /sitemaps/archive/{yyyy-mm}.xml
  api_json:
    - /openapi.yaml
    - /openapi.json
    - /.well-known/ai-plugin.json
    - /.well-known/llms.txt
    - /.well-known/llms-full.txt
    - /.well-known/security.txt
    - /.well-known/host-meta
    - /.well-known/host-meta.json
    - /.well-known/webfinger?resource={uri}
    - /api/languages
    - /api/articles
    - /api/articles/{id}
    - /api/articles/latest
    - /api/articles/by-url
  images_static:
    - /static/news_image/{key}.webp
    - /static/generated/finance/{symbol}_{range}.png

# Category discovery
categories:
  discovery:
    - Enumerate category slugs from: https://informedclearly.com/sitemaps/categories.xml
  notes:
    - Prefer categories sitemap rather than guessing category slugs.

# Finance specifics
finance:
  overview:
    - /{lang}/finance
  detail:
    - /{lang}/finance/{slug}
  slugs:
    - bitcoin
    - ethereum
    - solana
  charts:
    image_files:
      - /static/generated/finance/{symbol}_{range}.png
    json_endpoint:
      - /{lang}/finance/{slug}/chart?range={range}
    ranges:
      - 1d
      - 7d
      - 14d
      - 30d
      - ytd

# Search specifics
search:
  page:
    - /{lang}/search?q={keyword}
  live:
    - /{lang}/search_live?q={keyword}
  notes:
    - Intended for keyword discovery.
    - Keep the "q" parameter; drop tracking parameters (utm_*).

# Similar specifics
similar:
  page:
    - /{lang}/similar/{keyword}
  notes:
    - Intended for discovery of related content by concept/keyword.
    - Prefer strong nouns/phrases (e.g., bitcoin, inflation, election, AI).

# Canonical & duplicates
canonicals:
  - category_detail: /{lang}/{category}/{id}/{slug}
  - finance_detail: /{lang}/finance/{slug}
  - Prefer canonical URLs for citation.
  - Drop non-canonical query parameters (utm_*, ref, etc.).

hreflang:
  - Pages may provide alternate language variants via hreflang.
  - Prefer requested language variant where available.

# Allowed public paths (explicit)
allow:
  - /
  - /{lang}/
  - /{lang}/news/{page}/
  - /{lang}/articles/{page}/
  - /{lang}/{category}/
  - /{lang}/{category}/{page}/
  - /{lang}/{category}/{id}/{slug}
  - /authors
  - /{lang}/authors/{author-slug}
  - /{lang}/summary
  - /{lang}/summary/{date}
  - /{lang}/finance
  - /{lang}/finance/{slug}
  - /{lang}/finance/{slug}/chart
  - /{lang}/similar/{keyword}
  - /{lang}/search
  - /{lang}/search_live
  - /feed/rss
  - /feed/rss/{lang}
  - /feed/atom
  - /feed/atom/{lang}
  - /sitemap.xml
  - /sitemaps/static.xml
  - /sitemaps/news.xml
  - /sitemaps/categories.xml
  - /sitemaps/summaries.xml
  - /sitemaps/archive/{yyyy-mm}.xml
  - /robots.txt
  - /openapi.yaml
  - /openapi.json
  - /.well-known/ai-plugin.json
  - /.well-known/llms.txt
  - /.well-known/llms-full.txt
  - /.well-known/security.txt
  - /.well-known/host-meta
  - /.well-known/host-meta.json
  - /.well-known/webfinger?resource={uri}
  - /api/languages
  - /api/articles
  - /api/articles/{id}
  - /api/articles/latest
  - /api/articles/by-url
  - /static/news_image/
  - /static/generated/finance/

# Do NOT crawl
disallow:
  - /admin/
  - /login/
  - /logout/
  - /submit-url
  - /submit-url-status
  - /track-page
  - /like/
  - /dislike/
  - /image_upload
  - /api/private/

# Crawl etiquette (advisory; enforce via robots.txt)
crawl:
  crawl-delay: 5s
  rate-limit: 1 rps
  max-parallel: 2
  guidance:
    - Prefer sitemaps and feeds for discovery.
    - Avoid aggressive crawling of paginated lists.
    - Respect cache headers and avoid refetching unchanged resources.

# API notes (public, read-only)
api:
  base: https://informedclearly.com/api
  auth: none
  content-type: application/json
  openapi:
    - https://informedclearly.com/openapi.yaml
    - https://informedclearly.com/openapi.json
  endpoints:
    - /api/languages
    - /api/articles
    - /api/articles/{id}
    - /api/articles/latest
    - /api/articles/by-url
  examples:
    - https://informedclearly.com/api/languages
    - https://informedclearly.com/api/articles?lang=en&per_page=10
    - https://informedclearly.com/api/articles?q=bitcoin&lang=en&per_page=10
    - https://informedclearly.com/api/articles?lang=en&date_from=2026-06-01&per_page=10
    - https://informedclearly.com/api/articles/latest?lang=en
    - https://informedclearly.com/api/articles/by-url?url={urlencoded-canonical-url}
  query-parameters:
    articles:
      q: optional full-text query over title, summary, body, and related text
      lang: optional language code, one of en,nl,fr,de,es,pt
      category: optional category slug
      author: optional exact author name
      date_from: optional YYYY-MM-DD lower bound
      date_to: optional YYYY-MM-DD upper bound
      page: optional 1-based page number
      per_page: optional page size, max 50
    article-detail:
      lang: optional language hint for /api/articles/{id}
    by-url:
      url: required canonical informedclearly.com article URL
  guidance:
    - Prefer this unauthenticated informedclearly.com API for structured access.
    - Use /api/languages before crawling if language-specific behavior matters.
    - Use /api/articles for discovery and filtering.
    - Use /api/articles/{id} or /api/articles/by-url for canonical article detail.
    - Cite canonical informedclearly.com article URLs from the "url" or "citation.url" field.
    - Do not attempt to call private/admin endpoints.

  response-shapes:
    article-summary:
      - id
      - lang
      - title
      - published_at
      - url
      - content: optional; present when returned by the active API backend
      - keywords: optional
      - source_name: optional
      - source_url: optional
      - citation
      - provenance
      - meta
    article-detail:
      - id
      - lang
      - title
      - content
      - url
      - citation
      - provenance
      - meta

# Query parameters
query-params:
  keep:
    - q
    - page
    - range
  drop:
    - utm_*
    - ref
    - fbclid
    - gclid

# Freshness / refresh hints
refresh:
  home: 6h
  listing_pages: 12h
  detail_pages: 24h
  summaries: 24h
  finance_overview: 4h
  finance_detail: 4h
  finance_charts: 4h
  similar_pages: 12h
  search_pages: 12h
  feeds: 2h
  sitemaps: 12h

# Sitemap inventory
sitemaps:
  index:
    - https://informedclearly.com/sitemap.xml
  core:
    - https://informedclearly.com/sitemaps/static.xml
    - https://informedclearly.com/sitemaps/categories.xml
    - https://informedclearly.com/sitemaps/news.xml
    - https://informedclearly.com/sitemaps/summaries.xml
  current-archive-examples:
    - https://informedclearly.com/sitemaps/archive/2026-06.xml
    - https://informedclearly.com/sitemaps/archive/2026-05.xml
  archive-pattern:
    - /sitemaps/archive/{yyyy-mm}.xml
  guidance:
    - Enumerate all current archive months from the sitemap index instead of relying on a fixed list.
    - News sitemap is for recent Google News discovery; monthly archive sitemaps cover historical articles.

# Usage policy (advisory)
usage-policy:
  attribution:
    - 'Source: Informed Clearly - {title} ({url})'
  text:
    - Summarize and quote short passages with attribution.
    - Do not reproduce full articles.
  images:
    - Allowed to download, store, or rehost images from /static/news_image/.
    - Prefer alt text or link to the page.
  training: Allowed

# Smoke fixtures (examples to validate crawling)
smoke-fixtures:
  category:
    - en: ai
    - nl: ai
  similar:
    - en: bitcoin
    - nl: bitcoin
  finance:
    - en: bitcoin
    - nl: bitcoin
  search:
    - en: bitcoin
    - nl: bitcoin