mcpField
G
gsc-portfolio-audit

gsc-portfolio-audit

github.com/openclaudiaMarketing & growth722101 installsUpdated 1w ago
Repository

About gsc-portfolio-audit

GSC Portfolio Audit is a script and workflow for reviewing Search Console performance across multiple properties in one account. It ranks properties and highlights query changes, click-through gaps, and trends for marketers or site owners.

Key features

  1. 01Portfolio-wide property ranking
  2. 02New, rising, dropping, and lost queries
  3. 03CTR gap identification
  4. 04Selectable date windows and properties
  5. 05Parallel data retrieval

Use cases

  1. 01Reviewing performance across many sites
  2. 02Finding queries with significant click changes
  3. 03Prioritizing title and description updates
  4. 04Comparing search periods across a quarter

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/openclaudia/openclaudia-skills --skill gsc-portfolio-audit

After installing, type/gsc-portfolio-auditin Claude Code to confirm it loaded.

Bundled filesscripts/audit_gsc.py

Details

From the project README

GSC Portfolio Audit

Answers "how is everything doing?" across every property on a Search Console account, which is the question the per-site tooling can't answer without dozens of manual exports.

Setup

Requires an OAuth refresh token with https://www.googleapis.com/auth/webmasters.readonly:

export GOOGLE_GSC_CLIENT_ID=...      # or GOOGLE_CLIENT_ID
export GOOGLE_GSC_CLIENT_SECRET=...  # or GOOGLE_CLIENT_SECRET
export GOOGLE_REFRESH_TOKEN=...
export GSC_EXCLUDE="olddomain.com"   # optional, comma-separated
pip install requests

The most common setup failure is unauthorized_client on token refresh. It means the refresh token was issued for a different OAuth client than the id/secret you paired with it. Accounts that have added Google integrations over time usually have several clients; match the pair that minted the token.

Run it

python3 scripts/audit_gsc.py            # full: ranking + keyword diff for the top 12
python3 scripts/audit_gsc.py portfolio  # just the ranked table
python3 scripts/audit_gsc.py queries --site sc-domain:example.com
python3 scripts/audit_gsc.py --days 90  # quarter over quarter

Flags: --days (window, compared against the window immediately before it), --site (repeatable), --top, --limit, --min-clicks.

Sections and what they mean

SectionRead it as
NEWqueries with zero clicks last period. Where growth is actually coming from.
RISINGup ≥50%. Check whether position moved too — if it didn't, demand rose, not your ranking.
DROPPINGdown ≥40% off a real base. Position tells you which kind: rank fell = ranking loss; rank held but clicks collapsed = something took the clicks above you (AI Overview, a new SERP feature, or the query changed shape).
LOSTranked before, no data now.
CTR GAP≥1,500 impressions, top 10, under 2% CTR. Title and description rewrites, the cheapest wins available.

Interpreting

  • Report clicks first, impressions second. One large property can swing portfolio impressions enough to mask that everything else grew.
  • Separate brand from non-brand. A site whose entire keyword set is its own name (or misspellings of a competitor's) has no acquisition engine, however good the click count looks. Say so plainly in the report.
  • A whole-site collapse on its own head term is usually not SEO. Check ownership before diagnosing rankings: whois <domain> | grep -i "registrar\|updated date" plus whether it still resolves. Expired, transferred, or disputed domains produce a textbook ranking cliff that no amount of SEO work will fix.
  • "new" in the portfolio table means zero clicks in the prior window, which for a recently launched site is a launch, not a data gap.
  • Don't skip queries in languages you can't read. On multi-market sites the growth is usually in non-English long tail; translate the interesting ones rather than filtering them out.
  • A property returning 403 is verified for listing but not for search analytics. The script reports it instead of hiding it.

Notes

  • GSC data lags about 3 days; the script offsets for this automatically.
  • Both periods are fetched per property in parallel, so a 40-property account takes seconds.
  • Query rows are capped at 25,000 per period, well above what any single site returns for a 28-day window.

Comments

Markdown supported