LLM Skills
~/catalog/keyword research//track
Keyword researchGitHub source

Track

/track

Track and remember over time: rankings, alerts, performance reports, and project memory. Not sure? Use /aaron:auto.

aaron-he-zhuaaron-he-zhu
113
June 5, 2026
Apache License 2.0
// skill content

--- name: track description: "Track and remember over time: rankings, alerts, performance reports, and project memory. Not sure? Use /aaron:auto." argument-hint: "<domain-campaign-or-memory-request> [--alert|--report|--remember] [--period <range>]" parameters: - name: target type: string required: true description: "Domain, keyword set, campaign, reporting scope, or memory request" - name: mode type: string required: false description: "alert, report, or remember (default: rank tracking)" - name: period type: string required: false description: "Reporting period (--report)" --- # Track Command Track and remember over time : ranking monitoring, alerts, performance reporting, and project memory. ## Route - rank-tracker - alert-manager - performance-reporter - memory-management - entity-optimizer ## Rules - Default: monitor rankings and SERP position changes via rank-tracker; store ranking history in project memory only when the user explicitly allows memory writes. - --alert: configure thresholds and notifications via alert-manager; require a metric source, threshold owner, and notification channel before setup; do not enable external alerts without explicit approval. - --report: require exactly one scope (domain, campaign, project, or period); report traffic, rankings, AI citations/readiness, authority, technical health, content progress, and open loops; keep source/date freshness visible and separate observed data from estimates. - --remember: memory management manages the HOT/WARM/COLD lifecycle:capture, promote, demote, archive, query, and restore from archive:plus cleanup, purge, and protocol aggregation; canonical entity profiles are routed to the entity optimizer. Restore looks up a matching memory/archive/YYYY-MM-DD-* file. Purge/GDPR/CCPA requests require scoped targets and delete or anonymize matching canonical and archived memory surfaces. Only the content-quality-auditor and domain-authority-auditor may append a single veto marker to memory/hot-cache.md without additional confirmation. ## Output Return inline artifacts by default. Files may be written only when the user explicitly requests it and the runtime is able to write.

// original public source
aaron-he-zhu/seo-geo-claude-skills
/commands/track.md
Independent project, not affiliated with Anthropic. This skill remains the property of its original author.
// install this skill
Paste this command in your terminal at the root of your project:
mkdir -p .claude/commands && curl -o ".claude/commands/track.md" "https://raw.githubusercontent.com/aaron-he-zhu/seo-geo-claude-skills/main/commands/track.md"
Then in Claude Code, type /track to activate it.
open_in_newOpen original source
// save
Save available after sign in.
loginSign in to save
// information
Stars 113
LicenseApache License 2.0
UpdatedJune 5, 2026
Format.md
AccessFree
// similar

Skills Keyword research

View allarrow_forward