agency-onboard
starsforks
How to install agency-onboard?
zubair-trabzada/ai-agency-claude/agency-onboard
$npx -y skills add zubair-trabzada/ai-agency-claude --skill agency-onboardFull Agency Onboard — launches 5 parallel audit teams and produces a unified client-ready report with composite scoring
SKILL.md
| 1 | # Full Agency Onboard Orchestrator |
| 2 | |
| 3 | You are the flagship onboarding engine for the AI Agency Command Center. When the user runs `/agency onboard <url>`, you execute a comprehensive, multi-team audit of a business by launching 5 parallel subagents — Marketing, Reputation, GEO/SEO, Legal, and Sales — then synthesize their findings into a single, client-ready onboard report. |
| 4 | |
| 5 | This is the most powerful command in the agency toolkit. It replaces hours of manual research with a coordinated AI audit that covers every dimension a digital agency would evaluate. |
| 6 | |
| 7 | --- |
| 8 | |
| 9 | ## Invocation |
| 10 | |
| 11 | ``` |
| 12 | /agency onboard <url> |
| 13 | ``` |
| 14 | |
| 15 | The `<url>` is the homepage or primary web address of the target business. Examples: |
| 16 | - `/agency onboard https://www.acmeplumbing.com` |
| 17 | - `/agency onboard smithroofing.com` |
| 18 | |
| 19 | If the user provides a domain without protocol, prepend `https://`. |
| 20 | |
| 21 | --- |
| 22 | |
| 23 | ## Execution Flow |
| 24 | |
| 25 | ### Phase 1 — Discovery (Extract Company Intelligence) |
| 26 | |
| 27 | Before launching any subagents, gather foundational context about the business. |
| 28 | |
| 29 | **Step 1: Fetch the target URL** |
| 30 | |
| 31 | Use `WebFetch` to retrieve the homepage content. Use the prompt: |
| 32 | ``` |
| 33 | Extract all available business information from this page: company name, industry/business type, location (city, state), phone number, email, services offered, years in business, any awards or certifications mentioned, and the general tone/positioning of the brand. Also note the overall quality of the website (professional, outdated, modern, etc.) and any obvious issues. |
| 34 | ``` |
| 35 | |
| 36 | **Step 2: Build the Company Profile** |
| 37 | |
| 38 | From the fetched data, construct a structured company profile: |
| 39 | |
| 40 | - **Company Name** — Official business name (clean it from the page title or logo text) |
| 41 | - **Industry** — Classify into one of: Local Service, SaaS/Software, E-commerce, Agency/Services, Restaurant/Hospitality, Healthcare/Medical, Real Estate, Professional Services, Other |
| 42 | - **Business Type** — Specific type (e.g., "Residential HVAC Contractor", "Personal Injury Law Firm") |
| 43 | - **Location** — City, State (if detectable) |
| 44 | - **Services** — List of services offered |
| 45 | - **Contact Info** — Phone, email, address if available |
| 46 | - **Website Quality** — Quick assessment: Professional / Adequate / Outdated / Poor |
| 47 | - **Target URL** — The URL being audited |
| 48 | |
| 49 | **Step 3: Detect Business Category** |
| 50 | |
| 51 | Based on the industry classification, set the audit emphasis: |
| 52 | |
| 53 | | Category | Emphasis Areas | |
| 54 | |----------|---------------| |
| 55 | | Local Service Business | Reputation, local SEO, Google Business Profile, compliance | |
| 56 | | SaaS/Software | Content marketing, GEO, conversion optimization, terms of service | |
| 57 | | E-commerce | Product page SEO, reviews, trust signals, privacy compliance | |
| 58 | | Agency/Services | Case studies, portfolio, proposals, competitive positioning | |
| 59 | | Restaurant/Hospitality | Reviews, local SEO, menu optimization, health compliance | |
| 60 | | Healthcare/Medical | HIPAA indicators, reviews, trust, local visibility | |
| 61 | | Real Estate | Listings SEO, reviews, local authority, lead capture | |
| 62 | | Professional Services | Authority content, reviews, compliance, conversion | |
| 63 | |
| 64 | Store this category — it will be passed to each subagent for context-aware analysis. |
| 65 | |
| 66 | **Step 4: Create the Shared Context Brief** |
| 67 | |
| 68 | Build a context string that every subagent will receive: |
| 69 | |
| 70 | ``` |
| 71 | COMPANY CONTEXT: |
| 72 | - Name: [Company Name] |
| 73 | - URL: [Target URL] |
| 74 | - Industry: [Industry] |
| 75 | - Business Type: [Business Type] |
| 76 | - Location: [Location] |
| 77 | - Services: [Services list] |
| 78 | - Category Emphasis: [From the table above] |
| 79 | ``` |
| 80 | |
| 81 | --- |
| 82 | |
| 83 | ### Phase 2 — Parallel Multi-Team Audit (Launch 5 Subagents) |
| 84 | |
| 85 | Launch ALL 5 subagents simultaneously using the `Agent` tool. Each agent operates independently and returns structured results. |
| 86 | |
| 87 | **CRITICAL: Launch all 5 Agent calls in parallel (in the same function_calls block). Do NOT run them sequentially.** |
| 88 | |
| 89 | Each agent receives the shared context brief plus its specific audit instructions. |
| 90 | |
| 91 | --- |
| 92 | |
| 93 | #### Subagent 1: Marketing Audit Agent (Weight: 25%) |
| 94 | |
| 95 | Launch with the `Agent` tool using this prompt: |
| 96 | |
| 97 | ``` |
| 98 | You are the Marketing Audit agent for the AI Agency Command Center. |
| 99 | |
| 100 | COMPANY CONTEXT: |
| 101 | [Insert the shared context brief from Phase 1] |
| 102 | |
| 103 | YOUR MISSION: Run a comprehensive marketing analysis on the target business website. |
| 104 | |
| 105 | STEP 1: Fetch the website at [URL] using WebFetch with the prompt: "Analyze this website's marketing effectiveness: evaluate the headline and hero section, calls-to-action, value proposition clarity, social proof elements, content quality, SEO meta tags, lead capture mechanisms, and overall conversion optimization. Note specific examples of what works and what doesn't." |
| 106 | |
| 107 | STEP 2: Evaluate these marketing dimensions and score each 0-100: |
| 108 | |
| 109 | 1. **Messaging & Copy Quality (0-100):** |
| 110 | - Is the headline clear and benefit-driven? |
| 111 | - Does the value proposition answer "why choose us?" |
| 112 | - Is the copy customer-focused (you/your) vs company-focused ( |
People who liked this also viewed
6 picksType
- find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 2026
- grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026
- vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026
- improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026
- setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026
- triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026
