Install
$ agentstack add skill-siddiqss-semantic-seo-suite-seo-performance-tracker ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
seo-performance-tracker
The measured feedback loop. It replaces guesswork (and the fabricated "Pillar Page Rank" that wrapper tools invent) with real Search Console data joined to the topical map. Every figure is measured (GSC) or derived (rollups) — never estimated.
Read first: ../../framework/topical-map-theory.md (pillars/priority), ../../framework/query-semantics.md (query networks → new nodes).
Preconditions
topical-map.jsonwithurls on published nodes (the auditor sets these).- GSC configured:
grounding.sources.gsc: true+credentials.gsc_credentials_path.
If not configured, say so and do NOT invent metrics — spot-checking positions via web_search is unreliable; be explicit about that limitation.
Workflow
- Pull GSC data:
`` python ../../scripts/gsc_client.py --site "" --creds \ --start --end --dims query,page \ --out brands//data/gsc/pull.json # optional prior period for decay: python ../../scripts/gsc_client.py ... --start --end \ --out brands//data/gsc/prev.json ``
- Analyse against the map:
`` python ../../scripts/gsc_analyze.py --gsc brands//data/gsc/pull.json \ [--gsc-prev brands//data/gsc/prev.json] \ --map brands//topical-map.json --brand "" \ --out brands//audits/-performance.md `` Produces:
- Pillar rollups — impressions/clicks/avg-position per pillar (
derived). The
honest Pillar Page Rank.
- Striking-distance — queries at position 5–15 → quick-win update targets.
- Measured cannibalization — one query landing on multiple pages (the strongest
cannibalization signal; confirms/ː refutes the auditor's embedding guess).
- Decaying pages — >30% click loss vs the prior period.
- Uncovered queries — GSC queries not in any node's query network → candidate new
map nodes.
- Feed the loop:
- Add uncovered-query candidates to the map via topical-map-builder (as new nodes
or as query-network additions to existing nodes).
- Mark striking-distance and decaying nodes
needs-update; push them upcalendar.md. - Send confirmed measured-cannibalization pairs to semantic-site-auditor /
linking-and-schema for consolidation/redirect.
Definition of done
- Performance report produced with all five sections, every figure provenance-tagged.
- Actionable next steps flowed back into map + calendar.
- If GSC isn't configured: an honest "not available" with the setup pointer, no invented
numbers.
Grounding ladder
- T1 (GSC): the whole skill — this is a T1 capability (GSC is free).
- Without GSC: the skill explains it can't measure performance reliably and points to
README GSC setup. It does not fabricate a substitute.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: siddiqss
- Source: siddiqss/semantic-seo-suite
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.