Skip to content

fsbtactic-code/marketing-brain-skill / skills/marketing-brain

marketing-brain

Flagged

Create, improve, research, or audit marketing strategy and execution using a bundled marketing library, verified live primary sources for volatile facts, and clearly labeled agent judgment. Use for full marketing systems, audits, landing pages and CRO, competitor intelligence, brand voice, audience and JTBD research, email sequences, SMM and social content systems, paid ads, headlines, copywriting, positioning, offers, launches, GTM, growth, funnels, retention, pricing, SEO, analytics, attribution, experiments, and consumer or buyer psychology. Trigger for English and Russian requests, including requests for ready-to-use assets.

FileKindSize
SKILL.mdskill md10.6 KB
agents/openai.yamlconfig325 B
assets/BUILD-MANIFEST.jsonconfig1.2 KB
assets/cards.jsonlother21.1 KB
assets/edges.jsonlother33.0 KB
assets/knowledge.sqlitebinary136.0 KB
assets/legacy-library.mbpack.parts/manifest.jsonconfig857 B
assets/legacy-library.mbpack.parts/part-0000.binbinary48.0 MB
assets/legacy-library.mbpack.parts/part-0001.binbinary48.0 MB
assets/legacy-library.mbpack.parts/part-0002.binbinary7.7 MB
assets/research-catalog.jsonlother280.4 KB
assets/source-channels.jsonlother52.1 KB
assets/sources.jsonlother10.2 KB
assets/templates/content-calendar.mdmarkdown1.3 KB
assets/templates/evidence-ledger.mdmarkdown1.3 KB
assets/templates/experiment-backlog.mdmarkdown1.2 KB
assets/templates/issue-registry.mdmarkdown1.2 KB
assets/templates/marketing-brief.mdmarkdown1.6 KB
assets/templates/marketing-system-manifest.jsonconfig1.1 KB
assets/wiki/cards/card_ad_effects_heterogeneous_by_firm.mdmarkdown1.3 KB
assets/wiki/cards/card_ad_roi_measurement_noise.mdmarkdown1.4 KB
assets/wiki/cards/card_choice_overload_context_dependent.mdmarkdown1.4 KB
assets/wiki/cards/card_cost_transparency_context.mdmarkdown1.2 KB
assets/wiki/cards/card_ftc_material_connection_disclosure.mdmarkdown1.4 KB
assets/wiki/cards/card_google_ads_experiment_hygiene.mdmarkdown1.3 KB
assets/wiki/cards/card_google_no_word_count_freshness_trick.mdmarkdown1.2 KB
assets/wiki/cards/card_google_people_first.mdmarkdown1.2 KB
assets/wiki/cards/card_google_who_how_why.mdmarkdown1.1 KB
assets/wiki/cards/card_incrementality_control_group.mdmarkdown1.2 KB
assets/wiki/cards/card_incrementality_precision_stratification.mdmarkdown1.3 KB
assets/wiki/cards/card_short_video_ad_spillover.mdmarkdown1.3 KB
assets/wiki/cards/card_telegram_ad_format.mdmarkdown1.0 KB
assets/wiki/cards/card_telegram_destination_quality.mdmarkdown1.1 KB
assets/wiki/cards/card_telegram_no_unsupported_absolutes.mdmarkdown1.0 KB
assets/wiki/cards/card_viral_content_arousal.mdmarkdown1.3 KB
assets/wiki/cards/card_youtube_audience_signals.mdmarkdown1.2 KB
assets/wiki/cards/card_youtube_publish_time.mdmarkdown1.4 KB
assets/wiki/cards/card_youtube_quality_over_frequency.mdmarkdown1.3 KB
assets/wiki/cards/card_youtube_search_ranking.mdmarkdown1.1 KB
assets/wiki/cards/card_youtube_tags_low_priority.mdmarkdown1019 B
assets/wiki/domains/consumer-behavior.mdmarkdown2.2 KB
assets/wiki/domains/content-editorial.mdmarkdown5.1 KB
assets/wiki/domains/creator-community.mdmarkdown1009 B
assets/wiki/domains/cro-funnels.mdmarkdown2.3 KB
assets/wiki/domains/law-policy-ethics.mdmarkdown2.8 KB
assets/wiki/domains/measurement-analytics.mdmarkdown4.5 KB
assets/wiki/domains/offer-messaging-copy.mdmarkdown2.7 KB
assets/wiki/domains/organic-smm.mdmarkdown4.9 KB
assets/wiki/domains/paid-acquisition.mdmarkdown6.2 KB
assets/wiki/domains/pricing-promotions.mdmarkdown850 B
assets/wiki/domains/seo-geo-ai-search.mdmarkdown2.8 KB
assets/wiki/domains/strategy-research.mdmarkdown932 B
assets/wiki/index.mdmarkdown935 B
assets/wiki/open-questions.mdmarkdown159 B
assets/wiki/pages.jsonlother18.3 KB
references/research-catalog-policy.mdmarkdown1.3 KB
references/retrieval-policy.mdmarkdown1.0 KB
references/task-playbooks.mdmarkdown5.1 KB
references/taxonomy.mdmarkdown1005 B
references/third-party-notices.mdmarkdown1.6 KB
references/workflow-audience.mdmarkdown8.4 KB
references/workflow-audit.mdmarkdown7.0 KB
references/workflow-brand-voice.mdmarkdown8.0 KB
references/workflow-competitors.mdmarkdown7.2 KB
references/workflow-email.mdmarkdown8.8 KB
references/workflow-full-system.mdmarkdown9.2 KB
references/workflow-headlines.mdmarkdown8.4 KB
references/workflow-landing-cro.mdmarkdown6.9 KB
references/workflow-paid-ads.mdmarkdown10.1 KB
references/workflow-social.mdmarkdown9.2 KB
scripts/marketing_context_output.pyscript7.3 KB
scripts/marketing_context_query.pyscript8.6 KB
scripts/materialize_legacy_pack.pyscript12.1 KB
scripts/mbpack_codec.pyscript4.1 KB
scripts/mbpack_output.pyscript5.2 KB
scripts/retrieve_marketing_context.pyscript13.1 KB
scripts/search_knowledge.pyscript7.2 KB
scripts/search_legacy_pack.pyscript131 B
scripts/search_private_pack.pyscript11.0 KB
scripts/search_research_catalog.pyscript6.2 KB
scripts/verify_public_install.pyscript7.1 KB

references/workflow-landing-cro.md

View on GitHub
# Landing Page CRO Workflow

Use this workflow for a landing page, product page, pricing page, signup page, lead form, or other bounded conversion surface.

## Trigger conditions

- The user asks why a page does not convert or how to improve its conversion path.
- The user requests a section-by-section landing page audit.
- The user requests CTA, form, proof, offer, mobile, or experiment recommendations.
- The user asks for a conversion-focused rewrite grounded in the actual page.

## Primary output

Create `LANDING-CRO.md` when file output is requested or artifact mode is active. Otherwise return the same structure in the response.

## Input contract

Required:

- Page URL, page export, screenshot set, or complete page copy.
- Primary audience, traffic intent, and conversion event.
- Product, offer, market, and language.

Useful but optional:

- Traffic sources and message used before the visit.
- Device mix and major browser constraints.
- Baseline conversion rate with denominator, period, and event definition.
- Funnel steps after the page.
- Heatmaps, recordings, form analytics, experiments, and customer objections.
- Brand voice, legal requirements, and implementation constraints.

Do not block on absent analytics. Replace unsupported performance claims with instrumentation and test requirements.

## Dependencies

- Inspect the rendered page or supplied visual representation before diagnosing layout.
- Run retrieval before applying behavioral or persuasion claims.
- Use current official tools or documentation for performance, accessibility, and platform rules.
- Use `workflow-audit.md` when the decision spans the whole site or marketing system.

## Retrieval plan

Run two or three focused queries:

```text
python scripts/retrieve_marketing_context.py --query "landing page value proposition message match proof objections" --domain offer-messaging-copy --limit 5 --json
python scripts/retrieve_marketing_context.py --query "conversion friction form choice trust onboarding" --domain cro-funnels --limit 5 --json
python scripts/retrieve_marketing_context.py --query "controlled experiment conversion metric sample decision rule" --domain measurement-analytics --limit 5 --include-discovery --json
```

Adjust queries to the page type and audience. Verify discovery sources before using factual claims.

## Live checks

- Capture the final URL, observed date, page type, title, offer, price, CTA, and form behavior.
- Review the page at relevant viewport sizes when possible.
- Trace the primary CTA through the next step without submitting purchases or personal data.
- Check broken links, visible validation, policy links, and trust claims.
- Use current performance evidence when available. Do not infer speed from HTML alone.
- Verify any platform-specific checkout, tracking, or advertising requirement from official documentation.

## Analysis phases

### Phase 1: Define the conversion job

State who arrives, from where, with what intent, what they must understand, what action they should take, and what uncertainty blocks them. Separate the page goal from downstream business outcomes.

### Phase 2: Map the page

List sections in visual order. For each section record its purpose, customer question, evidence, CTA, and transition to the next section. Mark missing context instead of assuming it exists below an inaccessible fold.

### Phase 3: Test message match

Compare acquisition promise, hero message, offer, proof, and CTA. Evaluate clarity, specificity, differentiation, credibility, and continuity. Identify unsupported claims and hidden prerequisites.

### Phase 4: Inspect the decision sequence

Assess whether the page answers, in an appropriate order:

1. Is this for me?
2. What outcome or progress is offered?
3. Why should I believe it?
4. Why choose this alternative?
5. What does it cost or require?
6. What happens after I act?

Do not force this order when observed user intent supports another sequence.

### Phase 5: Inspect friction and trust

Review CTA hierarchy, navigation exits, forms, field necessity, error recovery, privacy explanation, payment or signup uncertainty, social proof quality, guarantees, contactability, and accessibility. Distinguish missing proof from weak presentation of existing proof.

### Phase 6: Review mobile and technical experience

Check content order, readability, tap targets, form inputs, sticky elements, overlays, layout shifts, media weight, and keyboard access using available evidence. Refer technical defects to implementation owners without inventing root causes.

### Phase 7: Create corrections

For each priority issue provide an exact change. Include revised copy or section logic where appropriate. Never add fabricated outcomes, urgency, testimonials, customer counts, or guarantees.

### Phase 8: Build the experiment backlog

For each test define hypothesis, target segment, changed element, primary metric, guardrail metric, instrumentation, minimum runtime logic, and decision rule. Do not supply a universal expected lift or sample size without actual baseline and variance data.

## LANDING-CRO.md contract

Use these headings in this order:

1. Executive conversion diagnosis
2. Scope, inputs, and limitations
3. Audience, traffic intent, and conversion job
4. Page and conversion-path map
5. Section-by-section findings
6. Message match and offer clarity
7. Proof, trust, and objection handling
8. CTA, form, and interaction friction
9. Mobile, accessibility, and performance observations
10. Prioritized corrections
11. Before and after copy or structure
12. Experiment backlog
13. Measurement requirements
14. Evidence notes and open questions

Each prioritized correction must include `Observation`, `Customer consequence`, `Change`, `Evidence`, `Confidence`, `Effort`, and `Metric`.

## Quality gates

- All layout findings come from an inspected rendering, screenshot, or explicit limitation.
- The analysis distinguishes traffic problems, offer problems, page problems, and downstream funnel problems.
- No benchmark or expected lift is presented as universal.
- Revenue scenarios use supplied traffic, conversion, value, and period with a visible formula.
- Rewrites preserve real capabilities, price, terms, and brand voice.
- Tests change a defined variable and have measurable decision rules.
- Current technical and policy claims are verified.
- The output contains no unresolved placeholders.

## Fallback

If the page cannot be loaded, request full-page screenshots, copy, form fields, CTA destination, and mobile captures. If only copy is available, limit conclusions to messaging and stated flow. If analytics are unavailable, define the events and baseline collection period needed before testing. If the offer is unclear, produce diagnostic questions before proposing a rewrite.

## Completion criteria

The workflow is complete only when the main conversion constraint is explicit, the top corrections are implementable, rewritten elements contain no invented proof, experiments are measurable, and the report clearly separates observations from hypotheses.
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall