creative-strategist-skills

"Imports raw transcripts (Fathom, Telegram, WhatsApp, email, free-form text — any format) into the Notion 'Real Customers' database. Creates one entry per external speaker identified, fills the 'Client input' phase properties (Name, Client relation, Transcript, dates, demographics if available), and leaves the 'AI extracted' fields for the Notion AI agent to populate. Use when the user pastes/uploads a call transcript, conversation log, sales call recording, or any customer interaction artifact they want ingested for downstream Persona work. Trigger on: 'import this transcript', 'ingest this call', 'add this prospect to Real Customers', 'push this Fathom into Notion'. Requires Notion MCP authenticated. Does NOT extract insights (sentiment, pain points, objections, summary) — that's the Notion AI agent's job, triggered separately."

"Builds a 3-layer persona from existing data and research. Use after brand-guidelines to deepen audience understanding before brief writing. Trigger on: 'who is our audience', 'build a persona', 'deep dive audience', 'who are we really talking to'. Produces a complete persona document ready to feed creative-brief and hook-writing."

"Builds a complete creative brief from research outputs. The brief defines the angle, awareness stage, hook direction, creative mechanic, format, specs, and success criteria. Use after audience-research and customer-reality. Trigger on: 'build a brief', 'creative brief', 'we're preparing a campaign', 'I want to run ads'. This is the central strategic document — nothing goes to production without it."

Runs a full Meta Ads account analysis in 7 steps using Windsor.ai as MCP data bridge. Pulls live campaign/creative/audience data directly into Claude and produces an actionable audit report: account health, campaign audit, creative lifecycle, angle & format performance, audience analysis, and prioritized action plan. Trigger on: 'analyze my Meta account', 'Meta Ads audit', 'which ads to tune', 'creative analysis Meta', 'Windsor analysis'. Requires Windsor.ai MCP connection.

Pilots the actual LAUNCH of ads on Meta via the official Meta/Facebook MCP, with hard guardrails at every step: full plan validated before any API call, everything created PAUSED, strict URL/UTM/creative rules, and a post-publication diff against the validated plan to catch Meta's silent auto-mutations. Use when assets are final and the campaign structure exists (see campaign-setup). Trigger on: 'launch these ads', 'push to Meta', 'publie les ads', 'mise en ligne campagne', 'put the campaign live'. Requires Meta MCP. Launching ads without this skill's checklist is how expensive Meta mistakes happen.

"Generates a validation agent .md file for any workflow step. The agent scores outputs 1-100 across 5 dimensions, provides actionable rewrites, and enforces hard violations. Use when adding quality gates to new or existing skills. Trigger on: 'create a validation agent', 'build a QA agent', 'I need a quality gate for [step]'. Output is a standalone agent-[name].md file ready for Project Knowledge upload."

Daily Meta Ads account optimization routine using CMAS methodology (Cut/Maintain/Scale). Reads account state, identifies ads to cut/maintain/scale based on documented kill rules and scale rules, picks the next priority action (P1 Wow Idea / P2 Message Testing / P3 Audience Testing / P4 Scale), and logs every decision. Works for lead generation or ecommerce accounts, existing or new. Trigger on: 'daily media buyer routine', 'optimize the account today', 'apply kill rules', 'what do I cut/scale', 'media buyer check', 'routine media buyer'.

Aligns creative strategy with the brand's real business objectives, growth stage, and team constraints. Use before starting any sprint or client engagement. Trigger on: 'what should we focus on', 'real objectives', 'business context'. Requires conversation with founder or decision-maker.

"Runs a structured brand intake interview then researches the brand to build a complete brand context document. Use whenever starting work on a new brand or when no brand-context.md exists in the project. Trigger on: 'run brand intake', 'build brand context', 'I'm working on a new client', or any creative strategy workflow where brand context is missing. Must run BEFORE any downstream skill (creative-brief, hook-writing, review-audit). This is the prerequisite context layer for all creative strategy work."

Establishes a performance baseline from existing ad account data. Use when starting work on a brand that has been running ads. Trigger on: 'audit the account', 'what's our baseline', 'how are we performing'. Requires dashboard or account access.

"Maps the emotional reality of the target persona: dominant emotion, private vs social pain, acute vs chronic pain, and triggering micro-moments. Use after review-audit and audience-research to go deeper than demographics. Trigger on: 'emotional mapping', 'micro-moments', 'customer reality', 'what the audience really feels'. Produces an emotional map that directly informs hook direction and creative tone."

Maps the competitive landscape and market sophistication level for a product category. Use before building any creative strategy. Trigger on: 'research the market', 'what are competitors doing', 'sophistication level of this market'. Requires brand context from brand-guidelines.

Mines customer reviews to extract verbatims, pain points, triggers, objections, and ad-ready phrases. Use after brand-guidelines to build the raw material for hooks and copy. Trigger on: 'mine reviews', 'customer verbatims', 'what are customers really saying', 'language mining'. Produces a structured verbatim library organized by theme.

"Writes 10 psychologically-driven hooks calibrated to a specific awareness stage, persona, and creative mechanic. Use after creative-brief is validated. Trigger on: 'write hooks', 'generate hooks', 'first line of the ad', 'hook for [persona]'. Produces a scored hook bank ready for brief integration or direct testing."

"Plans a full-funnel message sequence: 4–5 touchpoints mapped to awareness stages, with angle, format, and CTA for each. Use after creative-brief when the campaign spans multiple awareness stages. Trigger on: 'sequence plan', 'creative funnel', 'ad journey', 'TOF MOF BOF', 'touchpoint sequence'. Produces a sequencing plan ready to brief the production team."

Turns a validated creative brief into scene-by-scene prompts for AI video generation tools (VEO3, Kling, Runway). Use when producing video with AI tools instead of human editors. Trigger on: 'VEO3 prompts', 'Kling prompt', 'generate AI video', 'AI video brief'. Produces a scene-by-scene prompt pack ready to execute in the chosen AI tool.

Turns a validated creative brief into a sequenced technical brief for a human video editor or creator. Use after creative-brief and hook-writing when the format is video. Trigger on: 'video brief', 'editor brief', 'video script', 'scene sequence'. Produces a scene-by-scene production brief ready to hand to the production team.

Reviews the full Meta ad account performance over a defined period to identify top performers, underperformers, creative patterns, and structural gaps. Use quarterly or when performance drops unexpectedly. Trigger on: 'account audit', 'performance overview', 'macro analysis', 'what's working in the account'. Produces a macro performance report with strategic recommendations.

Deconstructs an ad's performance data to identify why it worked or failed, extract learnings, and generate 3 test hypotheses. Use after a creative has accumulated significant spend. Trigger on: 'analyze this ad', 'why is it working', 'creative deconstruction', 'what do we learn from this result'. Produces a learning report and 3 actionable next test hypotheses.

Identifies missing angles, untested personas, uncovered awareness stages, and format gaps in the current creative strategy. Use after account-audit or when performance plateaus. Trigger on: 'what are we not testing', 'missing angles', 'strategic gap', 'going in circles'. Produces a prioritized gap report with sprint recommendations.

Turns a validated creative brief into a Nano Banana image generation prompt and a structured designer brief. Use after creative-brief is validated and the format is static. Trigger on: 'generate an image', 'designer brief', 'static ad', 'Nano Banana prompt', 'static creative'. Produces a ready-to-execute production package.

Structures paid social campaigns (Meta, TikTok, Google, Snapchat, Pinterest, LinkedIn): naming convention, campaign/ad set/ad architecture, audience setup, budget allocation, and kill rules. Use after creative production is complete and assets are ready to upload. Trigger on: 'structure the campaign', 'setup Meta / TikTok / Google', 'naming convention', 'how to organize campaigns', 'platform parameters'. Produces a ready-to-launch campaign structure.

Turns a winning static ad into a 3-4 second animation using start frame / end frame interpolation. Use when a static creative has proven performance and needs a motion variant for video placements. Trigger on: 'animate this static', 'make a GIF from this ad', 'static to video', 'interpolation', 'motion variant'. Supports manual (NB2 + Flow) and automated (fal.ai MCP) workflows.

Extracts complete brand intelligence via web search across 7 phases and outputs a structured brand-research-brief.json. Use after brand-guidelines when you need deep competitive, product, and founder data to fuel creative production. Trigger on: 'research the brand', 'build a research brief', 'brand deep dive', 'I need brand intelligence'. Requires brand URL and hero product. Output uploads to Project Knowledge and feeds brand-specs, audience-research, and creative-brief.

Generates two visual spec cards (Brand Spec Card + Visual Style Card) as HTML then PNG from the brand-research-brief.json. These cards are uploaded to Project Knowledge and used as reference images in every Nano Banana or AI image generation prompt. Trigger on: 'generate spec cards', 'build brand spec', 'brand spec card', 'visual style card'. Requires brand-research-brief.json. Output dramatically improves AI image generation accuracy (from ~60-70% to ~90-95% hit rate).