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-full-system.md

View on GitHub
# Full Marketing System Workflow

Use this workflow for a complete marketing system, integrated go-to-market plan, full launch, multi-channel strategy, or consolidated client report. Do not use it for a single post, email, landing section, or isolated audit question.

## Trigger conditions

- The user asks for a complete marketing strategy, marketing system, launch plan, or full growth plan.
- The request spans at least three workstreams such as audience, positioning, funnel, content, paid media, lifecycle, or measurement.
- The user asks to consolidate existing marketing artifacts into one decision-ready system.
- The user asks to resume a previously started Marketing Brain run.

## Primary output

Create `MARKETING-SYSTEM.md` as the decision document.

When artifact mode is authorized and the workspace is writable, also create `MARKETING-SYSTEM-MANIFEST.json` from `assets/templates/marketing-system-manifest.json` and the supporting files listed below. Otherwise, return `MARKETING-SYSTEM.md` in the response and include the manifest as a final JSON block.

## Input contract

Capture these fields before planning:

- Business outcome, decision deadline, product, offer, business model, geography, and language.
- Priority audience and evidence, plus the current funnel, channels, assets, team, budget, and constraints.
- Baseline metrics with definitions and periods, plus requested depth, deliverables, and exclusions.

Ask only for missing information that would materially change the strategy. Record all non-blocking assumptions in the manifest.

## Dependencies

- Run retrieval from the directory containing `SKILL.md`.
- Use user-provided files as business context and live primary sources for current external facts.
- Read only the workflow files needed by the selected workstreams.
- Use subagents only when the environment supports them and the workstreams are independent.

## Retrieval plan

Run two or three focused queries rather than one broad query:

```text
python scripts/retrieve_marketing_context.py --query "category demand customer jobs switching barriers positioning" --domain strategy-research --limit 6 --json
python scripts/retrieve_marketing_context.py --query "offer messaging proof friction buyer decision" --domain offer-messaging-copy --limit 6 --json
python scripts/retrieve_marketing_context.py --query "channel measurement incrementality retention experiment design" --domain measurement-analytics --limit 6 --include-discovery --json
```

Change the wording and domains to match the business. Open canonical sources before using discovery results.

## Live checks

- Verify the product website, pricing, public claims, conversion path, and named competitors.
- Verify platform-specific, legal, and policy-sensitive recommendations against current official sources.
- Attach an observed date and market context to facts that can change.

## Dependency DAG

| Stage | Depends on | Can run in parallel | Required output |
|---|---|---|---|
| Intake | User request | No | Normalized brief and assumptions |
| Evidence collection | Intake | Yes | Evidence ledger and coverage gaps |
| Audience research | Intake, evidence | Yes | Audience decisions and unresolved questions |
| Competitor research | Intake, evidence | Yes | Competitive map and verified facts |
| Current-state audit | Intake, evidence | Yes | Constraints, assets, and funnel issues |
| Strategy spine | Audience, competitors, audit | No | Segment, positioning, offer, journey, goals |
| Measurement design | Strategy spine | Yes | KPI tree, instrumentation, experiments |
| Brand voice | Strategy spine | Yes | `BRAND-VOICE.md` when in scope |
| Landing CRO | Strategy spine, audit | Yes | `LANDING-CRO.md` when in scope |
| Social and SMM | Strategy spine, brand voice | Yes | `SOCIAL-CALENDAR.md` when in scope |
| Email lifecycle | Strategy spine, brand voice | Yes | `EMAIL-SEQUENCES.md` when in scope |
| Paid advertising | Strategy spine, landing CRO, measurement | Yes | `AD-CAMPAIGNS.md` when in scope |
| Headline lab | Strategy spine, brand voice, selected surface | Yes | `HEADLINE-LAB.md` when in scope |
| Quality review | All selected workstreams | No | Gate results and corrections |
| Final synthesis | Quality review | No | Marketing system and roadmap |

Do not start channel production before the strategy spine is coherent. A full run may omit irrelevant workstreams, but the manifest must record every omission and reason.

## Execution phases

### Phase 1: Normalize the brief

Define the decision, audience, market, customer progress, business economics, constraints, and success horizon. Separate facts from assumptions and open questions.

### Phase 2: Build the evidence ledger

Classify each material claim as `user_fact`, `verified_card`, `live_primary`, `legacy_excerpt`, `informed_judgment`, or `hypothesis`. Preserve source scope, date, limitations, and opaque IDs where applicable.

### Phase 3: Run discovery workstreams

Run audience, competitor, and current-state analysis. If subagents are available, give each one only the normalized brief, relevant evidence subset, selected workflow, and required output. Otherwise run the same workstreams sequentially.

### Phase 4: Create the strategy spine

Decide the priority segment, JTBD, alternative, positioning, differentiated mechanism, offer, proof, objections, customer journey, and primary growth constraint. Resolve contradictions before production.

### Phase 5: Design execution systems

Select only channels supported by audience behavior, economics, capabilities, and constraints. For every selected specialist workstream, load and execute its routed workflow: brand voice, landing CRO, social, email, paid ads, or headlines. Define partnerships or sales enablement directly when relevant. Tie every activity to a customer state and business decision.

### Phase 6: Design measurement

Define the KPI tree, event definitions, data sources, review cadence, experiment backlog, decision thresholds, and attribution limitations. Do not invent benchmarks or expected lift.

### Phase 7: Synthesize and sequence

Convert the system into priorities, dependencies, owners, a 30-60-90 day roadmap, stop conditions, and next decisions. Distinguish committed work from experiments.

## Supporting artifacts

In artifact mode, create only the files used by the selected run:

- Context: `MARKETING-BRIEF.md` and `EVIDENCE-LEDGER.md`.
- Discovery: `AUDIENCE-RESEARCH.md`, `COMPETITOR-REPORT.md`, and `MARKETING-AUDIT.md`.
- Strategy spine: `POSITIONING-AND-OFFER.md`, `CHANNEL-PLAN.md`, `MEASUREMENT-PLAN.md`, and `EXPERIMENT-BACKLOG.md`.
- Selected production: `BRAND-VOICE.md`, `LANDING-CRO.md`, `SOCIAL-CALENDAR.md`, `EMAIL-SEQUENCES.md`, `AD-CAMPAIGNS.md`, and `HEADLINE-LAB.md` when their workstreams are in scope.
- Final: `MARKETING-SYSTEM.md` and `MARKETING-SYSTEM-MANIFEST.json`.

## Manifest contract

`MARKETING-SYSTEM-MANIFEST.json` must contain:

```json
{
  "schema_version": "1.0", "run_id": "stable-run-id",
  "status": "in_progress|partial|complete",
  "created_at": "ISO-8601", "updated_at": "ISO-8601",
  "inputs": [], "assumptions": [], "open_questions": [],
  "workstreams": [{"id": "audience", "status": "complete", "depends_on": [], "artifact": "AUDIENCE-RESEARCH.md"}],
  "artifacts": [{"path": "MARKETING-SYSTEM.md", "status": "complete"}],
  "evidence": {"ledger": "EVIDENCE-LEDGER.md", "coverage_gaps": []},
  "quality_gates": [{"id": "claim_integrity", "status": "pass|fail|not_applicable"}]
}
```

Update the manifest after every completed phase. On resume, rerun only failed, missing, or input-invalidated workstreams.

## MARKETING-SYSTEM.md contract

Use these headings in this order:

1. Executive decision summary
2. Business context and assumptions
3. Evidence coverage and uncertainty
4. Priority audience and customer job
5. Positioning, offer, and proof
6. Customer journey and funnel
7. Channel system
8. Content and campaign system
9. Measurement and experiments
10. Prioritized 30-60-90 day roadmap
11. Risks, dependencies, and stop conditions
12. Immediate next actions

## Quality gates

- Every factual or numerical claim has a valid source class and scope, and none is invented.
- Audience, positioning, offer, voice, CTA, channels, and metrics are internally consistent.
- Calculations preserve units, time periods, and absolute versus relative change.
- Volatile facts have a live primary source and observed date; recommendations have an owner, metric, and decision rule.
- Required artifacts with `PASS` status contain no unresolved placeholders. Other statuses name every missing input, owner, and resolution action.

## Fallback

If live access is unavailable, use user-provided exports and mark current facts as unverified. If baseline data is absent, provide measurement requirements instead of forecasts. If evidence coverage is weak, narrow the claims and convert uncertain recommendations into tests. If the task is too broad for the available context, complete the strategy spine first and record deferred workstreams in the manifest.

## Completion criteria

The workflow is complete only when the primary document is decision-ready, selected artifacts agree with it, quality gates pass or are explicitly unresolved, the manifest reflects the actual state, and the user can identify the next owner action without further interpretation.
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