Detalle del Skill
agency-status
Useful agency dashboard, though broader than marketing agencies.
Revisar antes de usar
La revisión automática comprueba relevancia, no seguridad ni respaldo. Lee las instrucciones de la fuente antes de usar este Skill.
SKILL.md
Este extracto es una copia guardada durante la revisión. La fuente externa contiene la versión completa y actual.
--- name: agency-status description: Agency dashboard — shows agency-wide status, pipeline metrics, installed tools, and recent activity --- # Agency Status Dashboard You are the Agency Status Dashboard for the AI Agency Command Center. When the user runs `/agency status`, you produce a quick, comprehensive terminal dashboard showing the health of the entire agency operation: prospect counts, proposal metrics, revenue pipeline, tool suite availability, recent activity, and items needing follow-up. ## Trigger This skill activates when the user runs: ``` /agency status ``` No arguments required. This command always operates on the current working directory. ## Step 1 — Scan the Current Directory for All Output Files Use `Glob` to find all output files in the current working directory. Categorize every file found into these buckets: ### File Discovery Patterns **Agency-level files:** ``` AGENCY-ONBOARD-*.md → Full onboard reports (count as "audited prospects") AGENCY-PROPOSAL-*.md → Service proposals (count as "proposals sent") AGENCY-PIPELINE.md → Pipeline file AGENCY-REPORT*.pdf → PDF reports generated ``` **Marketing Suite files:** ``` MARKETING-AUDIT*.md → Marketing audits MARKETING-REPORT*.md → Marketing reports MARKETING-REPORT*.pdf → Marketing PDF reports MARKETING-PROPOSAL*.md → Marketing-specific proposals MARKETING-SEO*.md → SEO audits MARKETING-FUNNEL*.md → Funnel analyses MARKETING-COMPETITORS*.md → Competitive analyses ``` **Sales Team files:** ``` PROSPECT-ANALYSIS*.md → Prospect analyses SALES-REPORT*.md → Sales reports SALES-REPORT*.pdf → Sales PDF reports SALES-PROPOSAL*.md → Sales proposals SALES-RESEARCH*.md → Company research SALES-CONTACTS*.md → Decision maker intel SALES-OUTREACH*.md → Outreach sequences ``` **Reputation Manager files:** ``` REPUTATION-AUDIT-*.md → Reputation audits REPUTATION-REPORT*.md → Reputation reports REPUTATION-REPORT*.pdf → Reputation PDF reports REPUTATION-REVIEWS*.md → Review analyses REPUTATION-SENTIMENT*.md → Sentiment reports REPUTATION-COMPETITORS*.md → Competitor benchmarking REPUTATION-CRISIS*.md → Crisis playbooks ``` **GEO/SEO Tool files:** ``` GEO-AUDIT-*.md → GEO audits GEO-REPORT*.md → GEO reports GEO-REPORT*.pdf → GEO PDF reports GEO-CITABILITY*.md → Citability reports GEO-SCHEMA*.md → Schema reports GEO-CRAWLERS*.md → Crawler reports GEO-PLATFORM*.md → Platform reports ``` **Legal Assistant files:** ``` LEGAL-COMPLIANCE-*.md → Compliance audits LEGAL-REPORT*.md → Legal reports LEGAL-REPORT*.pdf → Legal PDF reports LEGAL-REVIEW*.md → Contract reviews LEGAL-PRIVACY*.md → Privacy analyses LEGAL-TERMS*.md → Terms analyses ``` ## Step 2 — Calculate Metrics ### Prospect Metrics 1. **Total prospects audited** — Count unique business names from AGENCY-ONBOARD-*, REPUTATION-AUDIT-*, GEO-AUDIT-*, MARKETING-AUDIT*, PROSPECT-ANALYSIS*, and LEGAL-COMPLIANCE-* files. Extract the business name from each filename (the part after the prefix). Deduplicate across tool suites. 2. **Proposals sent** — Count unique AGENCY-PROPOSAL-* and SALES-PROPOSAL-* files. 3. **Active clients** — Businesses with files across multiple dates (indicating ongoing work), or businesses with 3+ different report types. 4. **Conversion rate** — (Proposals sent / Total prospects audited) x 100. If there are active clients: (Active clients / Proposals sent) x 100 for close rate. ### Revenue Metrics Scan proposal files to extract pricing data: 1. **Total pipeline value** — Sum of all proposed monthly fees across all open proposals x 12 for annual. If no pricing is extractable, estimate based on proposal tier mentions: - Tier 1 / Essentials mentions: estimate $1,000/month - Tier 2 / Growth mentions: estimate $2,500/month - Tier 3 / Full Agency mentiLeer la fuente completa en GitHub (abre una página externa)