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-audit.md

View on GitHub
# Marketing Audit Workflow

Use this workflow to diagnose a website, funnel, or marketing system and produce a prioritized, evidence-grounded audit.

## Trigger conditions

- The user asks for a marketing audit, website review, funnel diagnosis, or growth diagnosis.
- The user asks what is wrong, what to improve, or why a site is not converting.
- The user asks for a client-ready assessment across multiple marketing dimensions.

Do not use this workflow for a narrow copy edit or a technical-only SEO crawl.

## Primary output

Create `MARKETING-AUDIT.md` when file output is requested or a writable artifact workflow is active. Otherwise return the same contract in the response.

## Input contract

Required:

- Target URL, page export, or supplied marketing materials.
- Product or service and intended audience.
- Primary business outcome and conversion event.
- Market and language.

Useful but optional:

- Current traffic, conversion, revenue, retention, or pipeline metrics with periods.
- Acquisition sources and priority device types.
- Known competitors, customer research, brand guidance, and analytics exports.
- Team, budget, compliance, technology, and timing constraints.

Ask for a missing input only when its absence would make the diagnosis materially misleading.

## Dependencies

- Inspect real user-provided material before scoring or recommending changes.
- Run retrieval before making strategic or behavioral claims.
- Use live access for current pages, competitor facts, policies, and platform behavior.
- Use `workflow-landing-cro.md` for a deeper single-page conversion analysis.
- Use `workflow-competitors.md` when competitive positioning is a major decision.

## Retrieval plan

Run two or three queries tailored to the site:

```text
python scripts/retrieve_marketing_context.py --query "value proposition message clarity proof buyer decision" --domain offer-messaging-copy --limit 5 --json
python scripts/retrieve_marketing_context.py --query "conversion friction forms trust onboarding experiment" --domain cro-funnels --limit 5 --json
python scripts/retrieve_marketing_context.py --query "marketing measurement attribution incrementality KPI" --domain measurement-analytics --limit 5 --include-discovery --json
```

Open canonical discovery sources before citing them. Do not convert a practitioner example into an expected result.

## Live checks

- Load the homepage and only the internal pages needed for the stated conversion path.
- Record final URLs, access status, observed date, and material rendering limitations.
- Check current pricing, offer terms, forms, CTAs, proof, policies, and contact paths.
- Inspect mobile behavior or screenshots when mobile is material.
- Check official search or platform documentation before making current technical claims.
- Treat third-party reviews as customer perception evidence, not verified product facts.

## Audit phases

### Phase 1: Scope the decision

Define what the audit must help the user decide. Identify the primary visitor, source, intent, conversion event, and current growth constraint. Record assumptions.

### Phase 2: Capture the current state

Trace the path from acquisition message through landing, consideration, conversion, and follow-up. Preserve exact observed copy where needed for diagnosis. Do not infer hidden analytics, backend behavior, or campaign settings.

### Phase 3: Analyze six dimensions

1. Audience and message fit: customer state, problem clarity, value proposition, differentiation, and objection coverage.
2. Conversion path: CTA hierarchy, friction, forms, proof, risk reduction, and next-step clarity.
3. Content and discoverability: information architecture, intent coverage, internal linking, and current search requirements.
4. Brand and trust: consistency, substantiated proof, identity, contactability, policies, and credibility.
5. Competitive position: alternatives, category conventions, meaningful differences, and unclaimed positions.
6. Measurement and growth: event definitions, data gaps, channel logic, retention, and experiment readiness.

### Phase 4: Build the issue register

For every issue capture:

- Observation and exact location.
- Customer or business consequence.
- Evidence class and confidence.
- Recommended change.
- Dependency and implementation effort.
- Metric and decision rule.

Use `critical`, `high`, `medium`, or `low` priority. Do not attach a numerical lift unless it is calculated from supplied data and explicitly framed as a scenario.

### Phase 5: Produce concrete corrections

For the highest-priority message or experience issues, include a specific replacement, revised sequence, instrumentation change, or test design. Preserve the user's brand voice and operational constraints.

### Phase 6: Optional scoring

Score only if the user requests it. Publish the rubric before the score. Use observed criteria rated from 0 to 5, mark unavailable criteria as `N/A`, and exclude `N/A` from the denominator. A score is a diagnostic index, not a market benchmark.

### Phase 7: Sequence action

Group recommendations into immediate fixes, validation work, experiments, and longer investments. Show dependencies and owner roles.

## MARKETING-AUDIT.md contract

Use these headings in this order:

1. Executive diagnosis
2. Scope, inputs, and limitations
3. Business context and assumptions
4. Current customer journey
5. Audience and message fit
6. Conversion path
7. Content and discoverability
8. Brand and trust
9. Competitive position
10. Measurement and growth
11. Prioritized issue register
12. Concrete corrections and examples
13. Measurement and experiment plan
14. 30-day action plan
15. Evidence notes and open questions

Every major finding must state `Observed`, `Why it matters`, `Recommended action`, `Evidence`, and `Confidence`.

## Quality gates

- Every criticism points to an observed element or explicitly stated coverage gap.
- No hidden data, competitor detail, benchmark, result, or customer motive is invented.
- Recommendations address the diagnosed constraint rather than generic best practice.
- Current search, advertising, email, and policy claims are live-checked when relevant.
- Before and after copy preserves the real offer and does not add unsupported proof.
- Metrics include definitions, sources, periods, and owners.
- Priorities reflect impact path, confidence, effort, and dependencies.
- The report contains no unresolved placeholders.

## Fallback

If the URL is unavailable, request an export, screenshots, page copy, or analytics summary. Continue with supplied materials and label all unobserved surfaces. If no baseline metrics exist, diagnose measurement readiness and define the baseline period. If evidence is insufficient for a conclusion, report the question and the cheapest validation method.

## Completion criteria

The audit is complete only when the user can see the primary constraint, the evidence behind it, the exact first actions, the required measurement, and the limits of the analysis. Do not mark complete when core pages were inaccessible without clearly stating that limitation.
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: 471kUpdated 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: 471kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 471kUpdated 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