Systems

Vapi · Retell · ElevenLabs · GHL. Production call flows + compliance layer.

Six Claude skills for Shopify, Amazon & multi-channel operators. Variant-aware, composable, agency-licensed.

25+ multi-agent patterns. Full code in Claude Agent SDK + LangGraph. Eval harnesses included.

Audit how AI engines see your business, then optimize.

Grade the opt-in page your lead magnet lives on. A runnable grader + workbook score it 0–100 on six levers (message match, single goal, value, friction, trust, honest promise) → GO LIVE / TIGHTEN / REWORK — with gates that block fake scarcity and a leaking conversion goal. Your marks, no baked-in benchmark.

Build an interactive assessment lead magnet that scores honestly and out-converts a PDF. A runnable scorer + design workbook turn a respondent's own answers into a 0–100 result band — with a no-manufactured-problems gate (PUBLISH / FIX / REWORK) that refuses to tell your best respondents they're failing. Your weights, no rigged gradient.

Grade your webinar as a lead engine, not just a talk. A runnable grader + workbook score it 0–100 on six funnel levers — registration, show-up, in-event qualification, follow-up, scoring, and measurement → RUN IT / TIGHTEN / REBUILD, with gates that catch a bait-and-switch or a webinar with no follow-up. Follow-up carries the most weight; your marks, no baked-in benchmark.

Stop nurturing every lead the same way. A runnable engine + workbook score each captured lead 0–100 on six weighted levers and return ADVANCE / KEEP NURTURING / RECYCLE / DROP — with a stale-engagement gate that holds a high-fit but cold lead in nurture, because fit isn't readiness. Routes the rest to the right track. It decides; you send.

Loom in → SOP + Claude skill + automation map out. The ABS Framework's doc method, productized.

All 9 Claude Skills Packs in one purchase — 55 installable skills across founder, ecommerce, trades, agency, studio operations, fractional exec, recruiting, support, real estate. 39% off the line.

Four tools for the whole retention lifecycle — onboarding sequences, support & success skills, churn autopsy kit, brand voice engine. One honest standard across every customer touch.

Four tools for the whole selling motion — battlecards, fractional-exec skills pack, brand voice engine, meeting intelligence. Honest selling, on-brand, call to close.

Six Claude skills that auto-load when you need them. Investor updates, board memos, runway, weekly cadence.

Production-readiness audit + 10-antipattern catalog + 6-layer checklist + monitoring template. For Blazr, Lovable, Bolt, v0, Replit.

A short, reassuring video course — plain English, no rush, a real safety module, and a printable companion guide. Yours forever, no subscription.

Six Claude skills for HVAC, plumbing, electrical, roofing, and landscaping shops. Lead intake, estimates, service reports, follow-ups, reviews, local SEO. Truck-friendly.

Diligence-grade SaaS metrics kit for founders raising in 2026. Burn Multiple, Rule of 40, LTV done right, AI gross margin defense. Sourced 2026 benchmarks.

Six Claude skills for digital, creative, marketing, PR, dev, and consulting agencies. Onboarding, status reports, scope creep, kickoff decks, invoice reconciliation, renewals.

Seven Claude skills that protect agency margin at the scope boundary: scope-creep detection, SOW generation, change orders, project retros, status updates, deliverable QA, the boundary email.

Seven Claude skills for the make-and-move surface — plus a runnable inventory auditor that reads your CSV and flags reorder, stockout, overstock, and dead stock. POs, three-way receiving match, scheduling, supplier scorecards, quality reports.

Six Codex skills + a runnable verifier for dev teams: framework upgrades (Next 15, React 19), dependency sweeps, monolith extraction, test backfill, dead-code removal. SHIP or HOLD with proof.

Six Codex skills + a runnable PR-hygiene gate: PR descriptions, security smells, breaking-change detection, conventional commits, review comments. PASS or BLOCK with proof.

Six Codex + Claude skills that document your codebase — README, API reference, ADRs, onboarding, changelogs (Diátaxis) — plus a runnable auditor that returns DOCUMENTED or GAPS.

The three Codex packs in one suite: Migration & Refactor, Code-Review & PR-Hygiene, and the Documentation Engine. 18 skills, 3 runnable CI gates. Fix it, guard it, document it.

The four-tool LLM dev-tools stack: RAG Retrieval Grader, Prompt Regression Lab, Prompt Injection Red Team Kit, and Agent Reliability Harness — one CI-ready tool for each way AI breaks, plus a pipeline playbook. Deterministic, offline, gate-your-build.

The audit-and-fix loop for AI visibility: the AEO Citation Audit & Optimizer Kit (diagnose where you stand) + the GEO / AI Visibility Playbook (fix it), with a 90-day loop playbook. Measure it, improve it, prove it. No guaranteed citations.

The honest back office: the AI Support Deflection Kit (escalate), the AI Document Extraction Kit (flag), and the Finance & Reporting Automation Kit (reconcile), with a connective playbook. One rule across inquiries, paperwork, and the books — don't guess, surface it. Humans stay in the loop.

Six Claude skills that run the full RFP response the Shipley way — shred, bid-decide, build the compliance matrix, theme, draft — plus a runnable verifier that catches the missed requirement before you submit.

Five Claude skills for margin defense + a runnable auditor that sweeps your deal book for realized (pocket) margin below floor — names the deals losing money behind your blended average. Discount guard, quote review, cost-change impact, leak diagnosis. Defends the price; doesn't set it.

Diligence-grade pricing intelligence for agencies adding AI services in 2026. 25+ service categories with sourced rates, pricing model decision tree, margin defense playbook.

Ten drop-in Claude Project blueprints — one per business function. Sales, founder, support, marketing, ops, finance, HR, product, legal, content. Custom instructions + KB map + starter prompts each.

One master prompt + five focused prompts that turn any meeting transcript into summary, decisions, action items, follow-up emails, and a standup-ready roll-up. Honest by design.

Master prompt + 8 focused prompts + 24-question bank across Sales/Marketing/Finance/Ops. Five-rule honesty layer keeps the output defensible. For any AI tool that runs code on uploads.

Catch the clean-looking invoice whose total doesn't tie. A deterministic engine + workbook check document fields against fixed rules — format, range, required, enum, cross-field math → PASS / REVIEW / REJECT, with a hard-fail gate that rejects any critical failure however high the score. No model, no guess; the validation layer after extraction.

Find the sensitive data before you share the file. A deterministic engine + workbook scan a document's text for PII — SSNs, cards, health markers, addresses — across three tiers → CLEAR / REDACT FIRST / DO NOT SHARE, with an exposure gate that blocks any unhandled high finding however high the coverage. It flags what to redact; it doesn't redact for you.

Catch the over-bill that's invisible on the invoice. A deterministic engine + workbook match every line against the PO and the goods receipt — seven checks → APPROVE / HOLD / BLOCK PAYMENT, with a payment-block gate that stops any line billing more than you received however clean the rest looks. The general-AP three-way match; it gates the pay decision, moves no money.

Sort every incoming document to the right queue — and flag the ones with no single right answer instead of guessing. A deterministic engine + workbook route on rules you control → ROUTE / QUARANTINE / UNMATCHED, with an ambiguity gate that quarantines any document two rules send two different places, so a signed contract never silently lands in AP.

“Did we get everything?” is where intake breaks. A deterministic engine + workbook score each intake packet against a checklist you define → COMPLETE / CHASE / HOLD INTAKE, with a blocker gate that holds any case missing a non-negotiable (a signed agreement, a consent, a valid ID) however complete the rest is. 83% with an expired ID is still HOLD INTAKE.

Catch the broken merge before it sends. A deterministic engine + workbook read your template and data list → READY / FIX / BLOCK per row and MERGE READY / FIX ROWS / HOLD per template, with a structural-dominant gate: one unmapped placeholder forces HOLD no matter how many rows are clean, because it breaks every row identically. It's the check, not the sender.

The front door to the document-ops line — run it first to learn which fix to buy. Score six stages (intake → classify → extract → reconcile → merge → govern) from your own marks; it takes the worst stage as the headline → AUTOMATED / MANUAL DRAG / STALLED, and routes your constraint to the exact drop that fixes it. A stall gate forces STALLED if any stage hits 40 or below.

Codify your voice into rules a machine can check. Voice Extractor + 8-section Voice Spec + On-Brand Writer + 100-point QA Checker + Voice Transfer. Worked example: 22 -> 92.

Six Claude skills for fractional CFO/CMO/COO/CRO/CPO/CHRO engagements. Diagnostic memos, engagement architect, retainer pricing, 90-day plans, board updates, executive briefs.

Six Claude skills for the full hiring lifecycle. Bias-checked JD writer, structured screener, interview kit with lawful-question flags, scorecard, candidate comms, offer drafter.

Six Claude skills spanning support and success. Triage, on-brand reply drafter (never invents), macros & KB, reply QA, churn-risk flagger, customer health check.

Six Claude skills across the deal lifecycle. Listing writer with Fair Housing check, CMA narrative builder, marketing kit, lead follow-up, buyer/seller comms, transaction update.

Five field-ready battlecards from your real intel — competitor, objection handling, discovery, talk track, persona. Accurate, honest, never invents competitor facts. Prompt, skill, or Project.

Grade your whole lead funnel across six stages and find the one choking it. A runnable engine + workbook report the constraint — your lowest stage, not the average — and route you to the exact fix → FLOWING / LEAKING / CLOGGED, with a broken-stage gate. The anchor of the lead-gen line: run it first to learn which drop to buy.

Score every inbound lead and work the right ones first. A runnable engine + workbook grade each lead PURSUE NOW / NURTURE / DISQUALIFY on fit, intent, and timeline from your own marks — with a hard gate that holds back a lead with no budget or no timeline. Priority, not permission.

Audit your lead-routing setup on the six rules that decide speed — instant acknowledgment, ownership, escalation, after-hours coverage, a measured SLA, and consent. A runnable linter + workbook score it 0–100 → PASS / FIX / BLOCK, with four hard gates that block any setup with a hole that drops leads. GHL build recipes included; your marks, no baked-in benchmark.

Six sequence types anchored to your real activation milestone — welcome, activation, adoption, stall-recovery, expansion, milestones. Activation-first, helpful, never oversells your product.

12 ICP personas + bias-check protocol. Pressure-test positioning in a weekend.

Exit interview + classifier + retention analyzer + 5 win-back sequences by churn reason. 48 hours to clarity.

Forecasting calculator + routing matrix + cache patterns + 15 production teardowns. Stop AI margin death.

Eval framework + dashboard + Notion war-room. Treat your prompts like code.

Diagnostic + 40+ patterns + AI rewriter + tier worksheet. New pricing page by 5pm.

Six editable policy templates for the moment an enterprise prospect, insurer, or auditor asks.

Publication-ready positioning in a guided 90-minute sprint. Four outputs you ship Monday.

The MCP-driven workflow that turns vidIQ search data into a recorded, point-of-view YouTube video in ~70 minutes. Four Claude Skills scout, interview you into an opinionated outline, and build an animated deck with a teleprompter. An authority gate refuses topics you can't speak to first-hand. Bring your own vidIQ Max plan.

The MCP-driven workflow that turns an email backlog into a finished morning in ~30 minutes. Four Claude Skills triage every thread via the Gmail MCP, draft the replies that need you, and hand you one ordered plan — with a delegate gate that routes off your pile what matters but isn't yours. It drafts; you send.

The MCP-driven workflow that revives a dormant HubSpot or GoHighLevel list. Four Claude Skills rank who's worth reviving, design an honest offer, and draft the re-engagement sequence in your voice — with a suppression gate that holds back anyone opted-out or unreachable. It ranks and drafts; you clear consent and send.

The MCP-driven workflow that clears every new client for takeoff. Four Claude Skills read the signed deal from HubSpot or GoHighLevel, score kickoff-readiness, and draft the onboarding packet into your own Google Drive — with a blocker gate that holds the kickoff until contract, deposit, and scope are locked. It drafts and stages; you share and send.

The MCP-driven workflow that grades a live sales pipeline so the forecast is honest. Four Claude Skills score whether each open deal is truly committed and draft the deal-review brief and rescue nudges — with a commit gate that refuses to count a deal with no next step, a dead close date, or gone silent, however large. It reads and drafts; you update the CRM and send.

The MCP-driven workflow that grades a published WordPress library so you refresh the right posts. Four Claude Skills score which posts are worth refreshing, draft the refresh in your voice, and stage a publish-ready draft — with a publish gate that refuses to fast-track inaccurate, unsalvageable, or worthless content, however well it ranks. It stages a draft; you publish.

The MCP-driven workflow that turns new inbound leads into drafted meeting invites. Four Claude Skills read new leads from your CRM and Gmail, score each (BOOK NOW / NURTURE / DECLINE), and draft a first-touch reply proposing real open times from your own Google Calendar — with a meeting-readiness gate that holds back a lead with no budget or no timeline. It reads and drafts; you send and book.

The flagship of the Executive Suite — your founder's chief-of-staff on a cadence. Four Claude Skills read your calendar, inbox, CRM, and metrics every Monday and deliver a one-page operating report to your own inbox: the three priorities, the at-risk flags, what slipped, and the one decision to make — with a floor gate that calls a crossed red line OFF PLAN. It reads and synthesizes; you act.

The Executive Suite advisor built to tell you no. Bring one hard decision and a five-member skeptical board each builds the strongest case against it and scores how well it survives — Go / Go with conditions / Not yet / No-go — with a veto gate where one fatal objection forces NO-GO however high the score. A stress-test, not a decision-maker; the call is yours.

Your AI VP of Sales — the Executive Suite's revenue inspector. Reads your CRM and grades every open deal on qualification, not stage or amount: Commit / Best case / At risk / Not real, with a Healthy / Thin / Exposed pipeline verdict against quota and the deal to work first. A disqualifier gate puts any deal missing an economic buyer or next step AT RISK, whatever its size. Read-only; you work the deals.

Your AI CFO — the Executive Suite's cash inspector. Grades your cash position on runway and trajectory, not the bank balance: reads your recent months, computes the real runway, and returns an honest verdict — HEALTHY / TIGHT / AT RISK / CRITICAL — with the concrete fix. Two gates make it honest: a hard runway floor (under three months is CRITICAL) and a trajectory gate (accelerating burn bumps the verdict one level worse). Read-only; you make the calls.

The capstone of the Executive Suite — the orchestration layer that ties your executive systems into one honest company status. It reads each system's verdict (operations, strategy, sales, finance), maps them to one severity scale, and reports the worst executive, not the average — with a compounding gate that escalates to CRITICAL when two domains are at risk at once. It names the binding constraint and Monday's top item. Orchestration only; you run the company.

The membership that runs your Executive Suite on a rhythm — a weekly board briefing, a monthly review, and a quarterly reset on a Command Deck that counts from the last time you actually ran each one. The keystone is the weekly: miss it once and you're DRIFTING, miss two cycles and it's OFF RHYTHM, no matter how current the rest is. Includes all five Executive Suite systems, the operating kit, and updates while subscribed. It schedules and reports; you run the company.