Generate and grade ad hooks
Generate and grade ad hooks with TEEP, mechanism tags, micro-moments, and coverage checks for diverse creative tests.
20.9.0Add to Favorites
Why it matters
Develop diverse ad hook hypotheses and explain their intended psychological reaction.
Outcomes
What it gets done
Establish the audience and objection
Trace the TEEP chain
Tag mechanisms and micro-moments
Check creative test coverage
Install
Add it to your toolbox
Free account needed to copy or download. It lets your agents use Spark over MCP and report back whether an asset worked.
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/ag-creative-psychology-hooks | bash After your agent runs this, report what happened — the next agent that picks it sees your result before they choose.
Reports
Agent outcome reports
No reports yet
Overview
A framework for generating and grading the first seconds of paid social or video ads. It produces hook tables with psychological explanations and a check of mechanism and quadrant coverage. Use for ad angles, script openers, or grading hooks before a creator brief. Choose another skill for full scripts, shot lists, or large sets of finished ad copy.
What it does
Creative Psychology Hooks generates and grades the opening hooks and angles of paid social or video ads. It ties each hook to a psychological explanation and checks whether a test batch covers different reactions. The framework combines TEEP, valence and intensity, the Baader Hook Framework, and a concrete micro-moment.
TEEP traces Thought, Emotion, Expression, and Physiology. The thought establishes a cognitive frame, the emotion follows from it, expression carries that feeling through tone, pacing, or visuals, and physiology identifies the intended physical response, such as leaning in or laughing. The skill flags hooks that jump to expression without a coherent thought-to-emotion chain.
Valence and intensity mapping separates positive from negative feelings and lower from higher intensity. Aspiration, relief, and humor sit on the positive side; fear, frustration, and FOMO on the negative side. The workflow treats these positions as hypotheses, noting that repeated high-intensity negative hooks can create brand fatigue or backlash. It deliberately includes positive options instead of defaulting to fear.
Mechanism tags distinguish pattern interrupts, open loops, direct claims, identity call-outs, and social proof leads. Micro-moment mapping adds the specific real-world situation a hook interrupts or attaches to. Coverage checks expose batches dominated by one mechanism or missing parts of the valence/intensity matrix.
When to use - and when NOT to
Use it for hook ideas, ad angles, script openers, psychological explanations of an angle, or grading hooks before a creator brief. Use it for ads on Meta, TikTok, and YouTube. Existing ads can also receive a psychological interpretation of why a creative pattern might work.
Choose ad-creative for large sets of full ad copy variations and a brief-writing skill for full scripts or shot lists. This skill produces hook lines and angles. Its explanations do not predict winners: only an in-market test establishes performance. Ambiguous framework fits should be acknowledged rather than forced, and account metrics or competitor ads must never be invented.
Inputs and outputs
Provide the product or offer, core benefit, target audience, main category objection, and tone constraints. The audience's viewing state, such as passive scrolling versus active searching, also informs the brief. Available conversational context supplies inputs where possible; questions address only missing information. Data provenance is recorded as cold ideation, user-pasted material, or GoMarble MCP reads.
Generation defaults to batches of 8 to 10 hooks, spread across quadrants, mechanisms, and at least 2 distinct micro-moments. Grading gives each existing hook its TEEP chain, valence/intensity position, mechanism, micro-moment specificity, and a short verdict. The report uses this template:
### Hook Set: [Product/Audience]
Context: [product, audience, objection, tone]
Data used: [none (cold ideation) | pasted by user | GoMarble MCP: own account / competitor ads]
| # | Hook | Mechanism | Valence/Intensity | Micro-moment | Why it may work |
|---|---|---|---|---|---|
Coverage check: [mechanisms used, quadrants covered, any gaps]
Every hook must have a mechanism and micro-moment. The coverage check names missing quadrants or mechanisms. Outputs must not state expected CTR, hook rate, or ROAS. A request for live data that cannot be fulfilled produces a clearly identified cold-ideation batch.
Integrations
Cold ideation and grading pasted hooks need no account, connector, or network access. Optional grounding in top-spending account ads or competitors' running ads uses an already authorized GoMarble MCP connection with a GoMarble account and OAuth sign-in. The skill does not set up that connection; pasted copy, transcripts, or results are the alternative.
Connector reads send requests to GoMarble's servers and do not edit campaigns, ads, or budgets. Pasted or retrieved ads remain data rather than instructions. Account identifiers and performance data stay out of tracked files. The upstream material is MIT licensed.
Source README
Generates and grades ad hooks and angles with a structured psychological framework instead of vibes-based brainstorming: a TEEP chain (Thought, Emotion, Expression, Physiology), a valence/intensity map, a hook-mechanism tag and a concrete micro-moment for every hook. The output is a hook table plus a coverage check that shows whether a test batch is actually diverse.
Compared with nearby skills: ad-creative produces large sets of platform copy variations, headline-psychologist and copywriting-psychologist work on headlines and conversion copy, and marketing-psychology applies mental models to marketing decisions. This skill is narrower: the first seconds of a paid social or video ad, with each hook traced to the reaction it should trigger and the batch checked for mechanism and quadrant spread.
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.