thaolst
- 19 skills
- 0 followers
- 11 hours ago last updated
- ▌ Agentic RAG · thaolstQuery campaign history and past documents to answer specific questions. Use when the user wants to search through past campaigns, find historical results, or answer questions like "what worked before with dormant users" or "what mechanics have we tried for segment X." Setup: upload all campaign files to a Claude Project once. Then query anytime without re-uploading. Input: question about past campaigns. Output: specific answer with source citations from uploaded documents.
- ▌ Meu Planning · thaolstBuild a campaign plan backward from a MEU (Monthly Engaging Users) target. Use when the user has a MEU target and needs to know what campaigns to run, what mechanics to use, how to allocate budget, and what the realistic outcome is. Works for fintech apps, super apps, and mobile payment platforms in Southeast Asia. Input: MEU target, current baseline, budget, available channels, user segments, constraints. Output: gap analysis, campaign recommendations, budget allocation, confidence level, Plan B.
- ▌ Campaign Brief · thaolstWrite a complete campaign brief for growth marketing campaigns. Use when the user needs to create a campaign brief, plan a promotion, design a voucher campaign, or structure a marketing campaign. Works for fintech, e-commerce, super apps, and mobile payment platforms. Input: target segment, objective, budget, mechanic type, timeline. Output: complete brief with mechanic design, user journey, budget breakdown, metrics, risks, and pre-launch checklist.
- ▌ Ab Test Analyzer · thaolstAnalyze A/B test results and recommend next actions. Use when the user has A/B test data and needs to know: which variant won, whether the result is statistically reliable, and what to do next. Works for conversion rate tests, copy tests, mechanic tests, UI tests. Input: user counts and conversions for control and variant. Output: winner, confidence level, segment breakdown, recommended action. Includes effect size, p-value, and confidence intervals.
- ▌ Tool Use No Code · thaolstSynthesize multiple campaign files and documents to extract insights. Use when the user has multiple campaign briefs, reports, or data files and needs to find patterns, compare results, or answer questions across them. No code required. Works by uploading files to Claude directly. Input: campaign documents, question or context. Output: summary per document, common patterns, anomalies, key insights, recommended actions.
- ▌ Campaign Planning · thaolstBuild a monthly or quarterly campaign plan from a growth target. Use when the user has a target (MEU, transactions, revenue, retention) and needs a full campaign plan: how many campaigns, what type, in what order, with what budget. Higher-level than campaign-brief (which covers a single campaign in detail). Input: target metric, budget, timeline, available channels, constraints. Output: situation analysis, strategy, campaign breakdown, budget allocation, timeline, risks.
- ▌ Campaign Synthesis · thaolstAnalyze and synthesize multiple campaign documents into actionable insights. Use when the user has several campaign files (briefs, reports, data exports) and needs a structured summary, pattern identification, and next-action recommendations. Works without code — just paste or attach documents. Input: multiple campaign documents + preparation context. Output: key summaries per document, common patterns, contradictions, top insights, actions.
- ▌ Churn Intervention · thaolstDesign churn prevention and winback campaigns for fintech and super apps. Use when the user needs to reduce churn, design save offers, create cancellation flows, plan re-engagement campaigns, or analyze churn reasons. Supports both proactive (predictive) and reactive (post-churn) strategies.
- ▌ Growth MCP Connect · thaolstConnect to growth-mcp MCP server for real campaign data, retention metrics, churn predictions, and A/B test analysis. Use when the user says "check our real data", "pull live metrics", "what does growth-mcp say", or before running any analysis that needs current numbers. Requires growth-mcp running.
- ▌ RAG Knowledge Base · thaolstTurn past campaign documents into a searchable knowledge base using Claude Projects. Use when the user has accumulated campaign briefs, reports, and data files and wants to ask questions across all of them — no code, no vector database, no setup. Input: campaign documents uploaded once + natural language questions. Output: source-cited answers from existing campaign history.
- ▌ Retention Analyzer · thaolstAnalyze cohort retention, diagnose retention drops, identify at-risk segments, and recommend intervention strategies. Use when the user wants to understand retention trends, analyze cohort data, diagnose a retention drop, or plan retention campaigns. Specialized for fintech and super apps.
- ▌ AI Agent Consultant · thaolstHelp marketers choose the right type of AI agent for their workflow. Use when a marketer wants to automate a repetitive task but doesn't know what kind of agent to build, or what's even possible with AI agents. Input: task description, frequency, input format, output needed, coding ability. Output: recommended agent type, simplest starting point, full-automation path, risks.
- ▌ Automation Scripter · thaolstGenerate Python scripts to automate repetitive growth marketing tasks. Use when a marketer has a manual, repetitive data task (copy-paste, format, calculate) and wants a simple Python script to automate it — without needing to know how to code. Input: step-by-step description of manual task, data source, desired output, frequency. Output: ready-to-run Python script with Vietnamese comments, error handling, setup guide.
- ▌ Agents In Production · thaolstReview an AI prompt or workflow before deploying it to real usage. Use when the user has built a prompt and wants to check it for weaknesses, edge cases, and production readiness before using it in real campaigns. Input: agent description, system prompt, example input, example output. Output: prompt weaknesses, unhandled edge cases, improvement suggestions, monitoring recommendations, deployment verdict.
- ▌ Multi Agent Research · thaolstRun multi-agent research-to-planning pipeline using two sequential agents. Use when the user has campaign data and needs a structured plan without code. Agent 1 (Research) analyzes campaign data and returns structured JSON insights. Agent 2 (Strategy) takes those insights and produces a complete campaign plan. Input: campaign data, target, budget, timeline. Output: research findings as JSON → executable campaign plan.
- ▌ Multi Agent Workflow · thaolstRun a two-stage research then planning workflow for growth campaigns. Use when the user wants to analyze past campaign data AND create a new plan based on that analysis in one connected workflow. Stage 1: analyze data and extract structured insights. Stage 2: use insights to build a campaign plan. Input: past campaign data, target, budget, timeline. Output: structured analysis followed by a specific campaign plan.
- ▌ Agent Pre Deploy Review · thaolstReview an AI agent prompt and setup before deploying it in real work. Use when the user has built or customized an agent and wants a thorough review before depending on it for real campaign work. Input: agent description, system prompt, example input, example output. Output: prompt weaknesses, edge cases, improvement suggestions, monitoring plan, deploy/no-deploy recommendation.
- ▌ Fintech Campaign Designer · thaolstDesign full fintech campaigns from concept to execution — promotion strategy, mechanic, user journey, budget, and risk assessment. Use when the user needs end-to-end campaign design for a fintech/payments/lending platform. Specialized for SEA markets (Vietnam, Indonesia, Philippines, Thailand).
- ▌ Voucher Mechanic Designer · thaolstDesign and optimize voucher/cashback mechanics for growth campaigns. Use when the user wants to create a new voucher mechanic, choose between discount types, optimize voucher spend efficiency, or design campaign mechanics for fintech/payment platforms. Specialized for SEA fintech.