Hoo export
Run an always-on SEO/AEO growth loop on your own site with Claude: pulls GA4 and Search Console signals, proposes fixes with the reasoning attached, applies approved changes to WordPress, verifies they landed, and learns from outcomes. Every write is human-approved. MIT, no telemetry, no scraping.
npx -y skills add shalintripathi/organic-os --skill hoo-exportAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 18 days oldThe repository was created 18 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use to flatten the brain to CSV for BI tools - "export the data", "CSV for Sheets or Looker Studio", /organic-os:export. Read-only over the brain; writes only the dated export folder.
SKILL.md
1.9 KB, as published. Nobody here has run it
CSV export (your data, no tier gate)
Resolve the brain: use registry.get_active() when running interactively; scheduled runs receive the brain path from the routine configuration.
- Run
core.contracts.check_schema(brain_path)first. If not compatible, relay the action string and stop. - Run the export via the canonical invocation:
PYTHONPATH="$CLAUDE_PLUGIN_ROOT/lib" python3 -csnippet callingcore.export.export_all(brain_path). It writesruns/<UTCdate>-export/inside the brain (see docs/site-repo-contract.md) and returns the dir, the file list, and a skipped-line count. - Present the result: each file with its path, plus the skipped-line count when it is non-zero ("N signal lines carried a metric token that did not parse and were skipped, never guessed at"). A source the brain does not have yet (no keyword history, no outcome records) is simply absent from the list - say so in one line, no error.
- One line on usage: import the CSVs into Sheets or Looker Studio directly - your data is files in your own repo, so there is no locked tier and no gate (ROADMAP, v0.4: commercial tools gate export behind top tiers; export here is a right, not an upsell).
- If the configured approval channel supports documents, offer to send
the CSVs there (telegram:
core.telegram.send_documentper file; in-session: the paths from step 2 are already the delivery; a channel that cannot carry a file reports the paths instead - ADR-0009). - Commit "export: YYYY-MM-DD" if the brain mode is git.
This skill never mutates signals, items, the skillbook, or the site -
the CSV files under runs/ are its only writes.