tonyflo79
@tonyflo79
Public Skills
order-bump-writer
by tonyflo79
Generate 50-150 word checkbox copy for order bumps displayed on checkout pages. Use when writing order bump copy that appears as a checkbox add-on during purchase. Produces 5-7 variants optimized for split testing, each following the 3-element structure (WHAT + WHY NOW + PRICE) with different emphasis angles. Brevity is the primary constraint — every word must earn its place. If the copy reads like a shortened sales page, it has failed. Trigger when users mention order bumps, checkout page copy, add-on offers, bump copy, or checkbox upsells. Requires U0 Upsell Strategist output or standalone brief.
upsell-editorial
by tonyflo79
Systematic quality review and revision of the complete assembled upsell sequence. Use as the final quality gate after U4 has assembled the full post-purchase funnel. Scores every piece (order bump, upsell page, downsell page) against upsell-specific editorial criteria, identifies structural and tone issues, applies revisions (Arena for critical/major P1/P2 issues, direct fix for minor P3/P4), rescores to verify improvement, and packages the final polished sequence. Every piece must score 7.5+ to pass. Trigger when users mention upsell review, editorial pass on upsell pages, quality check, or finalizing the upsell sequence. Requires U4 assembled output.
email-campaign-strategist
by tonyflo79
Design complete email campaign strategy — campaign type, email-by-email sequence blueprint, body type assignments, emotional arc, and urgency escalation. Use when launching a new email campaign, planning an email sequence, or determining the strategic architecture of a promotional email series. This skill is the architect of the email campaign — it decides WHAT gets written; E1-E4 decide HOW. Operates in two modes: Mode A (downstream from Skills 01-09 with full strategic context) or Mode B (standalone from user brief). Produces campaign-blueprint.yaml for handoff to E1 (writer). Trigger when users mention email strategy, campaign planning, sequence design, email architecture, or starting an email promotion.
email-editorial
by tonyflo79
Systematic quality review and revision of the complete assembled email campaign. Use as the final quality gate after E3 has assembled the full sequence. Scores every email against the EMAIL-QUALITY-RUBRIC, identifies structural and voice issues, applies revisions (full Arena for critical/major issues, direct fix for minor/cosmetic), rescores to verify improvement, and packages the final revised campaign. Every email must score 7.5+ to pass. Trigger when users mention email review, editorial pass, quality check, email polish, campaign revision, or finalizing an email campaign. Requires E3 assembled-sequence.yaml output.
email-sequence-assembler
by tonyflo79
Assemble individually generated emails and selected subject lines into a complete, sequenced email campaign with timing, cross-email callbacks, P.S. strategy, and campaign-level validation. Use after E1 has written all emails and E2 has generated subject lines. Takes discrete pieces and builds the cohesive whole — placing emails in blueprint-specified order, matching subject lines, setting send timing, verifying body type variety, and adding cross-email narrative threading. Trigger when users mention assembling emails, building the sequence, campaign assembly, email sequencing, or compiling the campaign. Requires E0 blueprint, E1 drafts, and E2 subject lines.
email-writer
by tonyflo79
Generate individual promotional emails following the campaign blueprint from E0. Use when writing email body copy for a planned email campaign sequence. Each email is written to a specific body type (one of 7: CT, QO, TM, QA, LB, ST, NR) using structural specimens and voice specimens from the 6-persona Arena. Generates ONE email at a time per the blueprint position. Produces individual email drafts with 70-80% content / 20-30% pitch ratio, natural bridge transitions, and attention- grabbing opening hooks. Trigger when users mention writing emails, email copy, email body, drafting an email, or generating email content. Requires E0 campaign-blueprint.yaml.
upsell-page-writer
by tonyflo79
Write 500-2000 word 1-click upsell pages — the first post-purchase offer buyers encounter after completing their front-end purchase. This is NOT a sales page; the buyer already said yes. Extends the logic of that yes into a congruent post- purchase offer using the CAIRO structure (Congratulate, Amplify, Intrigue, Reason, Offer). Supports video script mode for complex products (up to 4000 words). All drafts run through the Arena in generative_full_draft mode. Trigger when users mention upsell pages, post-purchase offers, 1-click upsells, OTO pages, or writing the page that appears after checkout. Requires U0 strategy and Skill 04 Mechanism output.
ad-script-architecture
by tonyflo79
Modular script structure design for paid ad creative across 8 frameworks (PAS, AIDA, BAB, Hook-Body-CTA, Story, Edutainment, UGC-DR, Viral). Use after format strategy (A03) is complete and you need structural blueprints for ad scripts. Designs modular scripts with swap-points (hook + setup + mechanism + proof + CTA) with exact word counts derived from speech rate physics (6s=15w, 15s=40w, 30s=75w, 60s=160w). Modules are independently swappable but each script maintains coherent flow. Produces SCRIPT-PACKAGE.md with structural blueprints for A07 to fill with copy. Trigger when users mention ad scripts, script structure, ad frameworks, modular scripts, or script architecture. Requires A03 FORMAT-STRATEGY.md.
ad-pre-launch-scoring
by tonyflo79
Probabilistic evaluation and variant prioritization for ad testing sequences. Use after the variant matrix (A09) is assembled and you need to determine which variants to test first. Scores variants with probability ranges (not false precision) and assigns Tier 1/2/3 priority for testing sequence. Every score traces to evidence from A01 intelligence, A06 Arena results, benchmarks, or historical data. The goal is prioritization, not perfection — tier assignment matters, decimal precision does not. Trigger when users mention ad scoring, variant prioritization, which ads to test first, pre-launch evaluation, or predicting ad performance. Requires A09 variant matrix.
ad-arena
by tonyflo79
Multi-persona adversarial evaluation of complete ad concepts using 7 ad-specific personas across 3 competitive rounds. Use after visual direction (A05) is complete and you need to stress-test ad concepts before production. Evaluates the COMPLETE concept (hook + script + visual as an atomic unit) — never isolated elements. Seven personas provide adversarial critique, and quality peaks in Round 3. Human selects the winners; the Arena recommends with transparent scoring. Produces AD-ARENA- RESULTS.md with scored candidates and synthesis. Trigger when users mention ad testing, concept evaluation, Arena for ads, ad review, or stress-testing ad creative. Requires A04 scripts and A05 visual direction as complete concepts.
ad-visual-direction
by tonyflo79
Shot-by-shot visual direction and creative production specs for paid ad assets. Use after script architecture (A04) is complete and you need visual briefs for each script. Specifies every shot (type, subject, action, duration, framing, text overlays, transitions) across 5 treatment types: Talking Head, B-Roll+VO, Text-on- Screen, Screen Recording, and Mixed. The visual sells before the audio does — 85% of social video is watched on mute initially. Produces VISUAL-DIRECTION-PACKAGE.md with actionable production briefs. Trigger when users mention ad visuals, video direction, shot lists, visual briefs, creative direction for ads, or production specs. Requires A04 SCRIPT-PACKAGE.md.
ad-visual-video-production
by tonyflo79
Production asset generation and quality control for paid ad creative using external tools (Gemini Nano Banana 2, Veo 3.1, Imagen 4, ElevenLabs for voice/music/SFX). Use after copy production (A07) is complete and you need to generate the actual visual and audio assets. Executes visual briefs from A05 using tool-agnostic orchestration — tools are swappable but production quality is binary (production- ready or rejected). Produces the AD-ASSETS directory with all generated media files. Trigger when users mention ad production, generating ad visuals, video production, creating ad assets, or producing ad creative. Requires A05 visual briefs and A07 final copy.
ad-launch-package
by tonyflo79
Platform-compliant packaging and delivery preparation for ad campaign launch. Use after pre-launch scoring (A10) is complete and you need to package everything for the media buyer to go live. Launch-ready means COMPLETE — the media buyer can launch without asking a single question. Includes correct platform specs, file naming conventions, folder structure, campaign structure recommendations, and budget allocation suggestions. Trigger when users mention launch package, ad delivery, campaign packaging, preparing ads for launch, media buyer handoff, or getting ads ready to go live. Requires A10 scoring report and all upstream production assets.
ad-format-strategy
by tonyflo79
Strategic platform-native format mapping and creative volume planning for paid ads. Use after hook and angle discovery (A02) is complete and you need to map each hook to its optimal platform, format, and creative treatment. Determines whether each hook works best as video, static, or carousel — and on which platform (Meta, TikTok, YouTube, Google). Format follows function based on hook needs, platform rewards, and intelligence data from A01. Produces FORMAT-STRATEGY.md with complete distribution plan. Trigger when users mention ad formats, platform mapping, creative formats, video vs static decisions, or platform-specific ad strategy. Requires A02 HOOK-ANGLE-MATRIX.md and A01 intelligence.
ad-intelligence
by tonyflo79
Build comprehensive competitive intelligence on what ads are running and winning in a target vertical. Use when launching a new ad campaign, entering a new market, or refreshing competitive intelligence. Scrapes 500+ competitor ads across 2+ platforms (Meta Ad Library, TikTok Creative Center), classifies every ad by hook type (32-type taxonomy), format, visual style, and estimated run duration. Extracts top 20 winning ad specimens with full verbatim copy transcription and identifies opportunity gaps (underused hook types, format gaps, messaging whitespace). Three modes: Initial Scan (new projects), Continuous Monitor (active campaigns), and Tool-Assisted Scan (pre-scraped data import). Trigger when users mention ad research, competitor ads, ad intelligence, what ads are running, or competitive ad analysis. First skill in the Ad Engine pipeline.
ad-performance-learning
by tonyflo79
Post-launch performance analysis and intelligence feedback loop for paid ad campaigns. Use after ads are live and performance data is available. Analyzes real performance data, extracts actionable learnings, and propagates them back into engine files (A01 intelligence, A02 hook taxonomy, A06 Arena calibration, A10 scoring models). When data conflicts with predictions, data wins. Learnings must be actionable (WHAT + WHY + HOW to apply) and the loop must close by updating engine files, not just producing reports. Trigger when users mention ad performance, campaign results, ad analytics, what worked, learning from ads, or updating the engine with results. Requires live campaign performance data.
ad-hook-angle-discovery
by tonyflo79
Strategic derivation and creative generation of advertising hooks and angles for paid ad campaigns. Use after ad intelligence (A01) is complete and you need hook and angle candidates for ad creative. Generates 50+ hooks across 8+ hook types and 10+ angles using the 32-type hook taxonomy. Angles are strategic (the frame through which the audience sees the message); hooks are creative expressions of those angles. Volume is the game — more hooks mean more testable creative. Produces the HOOK-ANGLE-MATRIX.md with all candidates scored and categorized. Trigger when users mention ad hooks, advertising angles, hook generation, creative angles, or brainstorming ad openers. Requires A01 AD-INTELLIGENCE-HANDOFF.md.
ad-assembly-variant-matrix
by tonyflo79
Assemble copy and visual/audio assets into coherent ad variants and generate an exhaustive testable variant matrix. Use after visual/video production (A08) is complete and all creative elements need to be combined. Validates coherence of every variant (copy + visual + audio must work as a complete ad unit) and generates the full combinatorial matrix of all testable combinations. Every variant must map to concrete files with platform and format specs. The matrix is the product — exhaustive, validated, and deployable. Trigger when users mention ad assembly, variant matrix, combining ad elements, ad variants, or building the testing matrix. Requires A07 copy and A08 production assets.
project-brief
by tonyflo79
Initial project brief capture for new copywriting campaigns. Produces TWO documents: (1) Soul.md — the voice/identity document for all downstream copy skills, and (2) Research Brief — the input document for Skill 01 Deep Research. Use when starting any new project, onboarding a new client, or initializing a campaign. Trigger when users mention starting a new project, creating a brief, kicking off research, or initializing a campaign. This is the entry point for the entire pipeline.
ad-copy-production
by tonyflo79
Volume-oriented copy production filling approved script architectures with 30+ testable ad variants per concept. Use after the Ad Arena (A06) has selected winning concepts and you need to produce final ad copy. Copy fills blueprints — A04 designed the structure, A06 approved it, A07 writes the words. Generates variants through modular swapping: 5-10 hook swaps per winning body, producing an exhaustive variant library for testing. Word count limits from speech rate physics are enforced as hard constraints. Trigger when users mention writing ad copy, ad copywriting, filling scripts, variant generation, or producing final ad text. Requires A04 scripts and A06 Arena results.