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-paid-ads.md

View on GitHub
# Paid Advertising Workflow

Use this workflow to design, audit, or produce a paid acquisition system with verifiable claims, explicit economics, and testable decisions.

## Trigger conditions

- The user asks for paid ads, media strategy, campaign architecture, targeting, retargeting, or budget allocation.
- The user asks for search, social, display, video, marketplace, or app campaign copy, creative briefs, or diagnosis of CPA, CAC, ROAS, conversion, fatigue, or message match.
- The user asks for an experiment plan, launch plan, or optimization backlog for paid media.

Do not use this workflow for organic social content or a landing-only audit.

## Primary output

Create `AD-CAMPAIGNS.md` when file output is requested or artifact mode is active. Otherwise return the same contract in the response. The first line after the title must be `Workflow status: PASS`, `Workflow status: NEEDS_DATA`, or `Workflow status: BLOCKED`.

## Input contract

Required:

- Business objective, conversion event, offer, product facts, market, and language.
- Priority audience or customer state and the evidence supporting it.
- Candidate platforms, landing destinations, real creative capabilities, and budget constraint with currency and period.
- Legal, policy, brand, geography, timing, and operational constraints.

Required before launch-ready status:

- Tracking events, attribution window, consent behavior, and data owner.
- Baseline volume and economics with definitions, periods, and source systems.
- Approved claims, proof, terms, price, availability, destination QA, and account evidence sufficient to verify configuration.

Useful but optional:

- Historical spend, impressions, clicks, conversions, revenue, margin, retention, and cohort data.
- Creative-level results, search terms, placements, audiences, exclusions, change history, competitor research, interviews, sales notes, and landing experiments.
- Production lead times, localization needs, inventory limits, and sales capacity.

Ask only for missing inputs that change feasibility, economics, compliance, measurement, or launch safety.

## Dependencies

- Load `AUDIENCE-RESEARCH.md`, `COMPETITOR-REPORT.md`, `LANDING-CRO.md`, and brand guidance when present and relevant.
- Run retrieval before selecting persuasion, targeting, measurement, or experiment mechanics, and verify current platform capabilities, specifications, and policies from official documentation.
- Use account data for performance diagnosis and user-supplied economics for financial scenarios.
- Never infer a platform result, audience size, auction price, conversion rate, or revenue outcome.

## Retrieval plan

Run two or three focused queries adapted to the funnel and channel:

```text
python scripts/retrieve_marketing_context.py --query "paid acquisition audience intent creative offer message match" --domain paid-acquisition --limit 5 --json
python scripts/retrieve_marketing_context.py --query "advertising incrementality attribution control group experiment" --domain measurement-analytics --limit 5 --include-discovery --json
python scripts/retrieve_marketing_context.py --query "advertising claim disclosure privacy targeting policy" --domain law-policy-ethics --limit 5 --include-discovery --json
```

Use `offer-messaging-copy` for creative claims and `cro-funnels` for landing continuity. Open canonical discovery sources before relying on them.

## Live official checks

- Verify current campaign objectives, optimization events, placements, audience controls, exclusions, and account requirements in official platform documentation.
- Verify current ad formats, field limits, asset specifications, destination rules, review policies, and special-category or regulated-content rules for each selected placement.
- Verify conversion API, pixel, tag, consent mode, offline event, and attribution configuration against official implementation documentation.
- Verify current offer, price, terms, inventory, proof, landing claims, and conversion path on canonical product surfaces.
- Record the verification date and source for every changing requirement.

Do not reuse a static CPM, CPC, CPA, ROAS, audience-size, format, or platform-policy claim from a legacy source.

## Execution phases

### Phase 1: Normalize the paid media brief

Define the business decision, audience, customer state, offer, conversion event, market, time horizon, budget constraint, capacity, and risk. Separate facts, assumptions, and missing launch inputs.

### Phase 2: Validate offer and channel fit

Check whether paid traffic has a credible offer, proof, destination, operational capacity, and measurable next state. Choose platforms by intent, audience evidence, creative fit, policy eligibility, and measurement capability.

### Phase 3: Map the funnel and economics

Map impression, visit, lead, qualified opportunity, sale, retained customer, and margin where relevant. Show formulas and user inputs. Use scenarios rather than forecasts when a baseline is missing or unstable.

For break-even logic, state the exact value definition and period. Do not mix revenue ROAS with contribution-margin return or CAC with cost per lead.

### Phase 4: Establish measurement readiness

Define events, deduplication, consent, source of truth, attribution limits, offline outcomes, quality checks, and reporting latency. Identify what the platform can optimize and what the business actually values.

### Phase 5: Design campaign architecture

Define platform role, campaign objective, optimization event, audience or intent group, placement logic, exclusions, naming, budget control, learning boundaries, and destination. Avoid needless fragmentation.

### Phase 6: Build the audience and intent plan

Separate prospecting, high-intent demand capture, customer expansion, and remarketing only when lawful and useful. Define inclusion evidence, exclusion logic, overlap risk, suppression, and privacy constraints.

### Phase 7: Build the creative matrix

Cross audience state with problem, promised progress, mechanism, proof, objection, and format. For each concept write complete copy and an original visual or video brief. Remove unsupported authority, urgency, scarcity, comparison, and outcome claims.

### Phase 8: Verify message match

Compare ad promise, audience intent, landing headline, offer, proof, CTA, terms, and post-click event. Record every mismatch and the owner required to fix it before launch.

### Phase 9: Allocate budget by decision

Allocate budget to learn or scale a defined decision, not by a universal platform split. Preserve currency and period. Respect minimum operational volume only when current platform guidance or account data supports it.

### Phase 10: Design experiments

For each test define hypothesis, changed variable, assignment unit, primary metric, guardrails, minimum detectable effect or decision threshold, power or Bayesian method, maturity window, and stop rule.

Do not use a universal impression count, fixed runtime, or expected lift. Account for repeated looks, delayed outcomes, seasonality, and multiple comparisons where material.

### Phase 11: Create launch and optimization controls

Define preflight QA, approval, pacing, anomaly alerts, change log, review cadence, scale conditions, pause conditions, creative refresh triggers, and owner roles. Separate platform-reported results from incrementality evidence.

## AD-CAMPAIGNS.md contract

Use these headings in this order:

1. Executive paid media decision
2. Workflow status and blocking data
3. Scope, audience, offer, and assumptions
4. Verified platform and policy requirements
5. Funnel, economics, and scenario formulas
6. Measurement and attribution readiness
7. Platform roles and campaign architecture
8. Audience, intent, exclusion, and suppression plan
9. Creative matrix and complete ad variants
10. Landing message-match review
11. Budget allocation and pacing logic
12. Experiment backlog and decision rules
13. Launch checklist and optimization runbook
14. Evidence ledger, risks, and open questions

For every ad variant include `ID`, `Platform`, `Placement`, `Audience state`, `Campaign objective`, `Concept`, `Primary text`, `Headline`, `Description when supported`, `CTA`, `Destination`, `Visual or video brief`, `Proof source`, `Policy check`, `Primary metric`, `Guardrail`, and `Asset status`.

## Quality gate status

- `PASS`: current platform and policy facts are verified, claims and destinations are accurate, tracking and consent are ready, economics use valid inputs, full assets are complete, and launch controls have owners and decision rules.
- `NEEDS_DATA`: a safe strategy or draft is possible, but account data, budget, tracking, consent, baseline economics, proof, destination QA, creative capacity, or current platform verification is incomplete. List every gap and launch consequence.
- `BLOCKED`: the request requires illegal or prohibited advertising, discriminatory targeting, deceptive claims, fabricated proof, hidden terms, unsafe regulated claims, unauthorized data use, or another defect that cannot be repaired within scope.

Assign exactly one status. Creative completeness alone never qualifies a plan as `PASS`.

## Stop and fallback rules

- Stop launch-ready planning if the product, offer, audience, conversion event, or destination is unknown.
- Stop activation if tracking, consent, claim approval, or policy eligibility is unresolved.
- If budget is unknown, provide allocation logic and decision tiers without invented amounts.
- If baseline economics are absent, provide break-even formulas and required inputs without CPA, CAC, or ROAS predictions.
- If account access or official verification is absent, limit findings to supplied exports, mark affected assets `NEEDS_DATA`, and do not call them upload-ready.
- If landing message match fails, require the correction before recommending spend.

## Completion criteria

The workflow is complete only when platform roles are defensible, campaign structure supports a business decision, every claim and requirement is verified, economics are transparent, measurement and consent are ready or explicitly unresolved, creative and landing messages match, experiments have valid decision rules, the assigned status is justified, and an owner can launch or resolve each remaining gap without guessing.
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