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-audience.md

View on GitHub
# Audience and JTBD Research Workflow

Use this workflow for audience research, segmentation, ICP, JTBD, buyer behavior, objections, purchase criteria, interview planning, and message implications.

## Trigger conditions

Run this workflow when the user asks to:

- determine who is most likely to buy;
- segment a market by behavior or buying situation;
- define ICP, buyer groups, or customer jobs;
- explain adoption, switching, hesitation, or rejection;
- synthesize interviews, reviews, sales notes, or usage data;
- prepare research for positioning, product, pricing, content, or acquisition.

Do not run a full audience study when the user only asks for a mechanical rewrite for an already documented segment.

## Status model

- `PASS`: the conclusion is supported by sufficient evidence for the stated decision.
- `NEEDS_DATA`: the result is a useful hypothesis but requires named validation.
- `BLOCKED`: the requested confidence or decision cannot be supported responsibly.

Never replace evidence coverage with a persona score or a fabricated confidence percentage.

## Required inputs

- Product, service, or proposed offer.
- Market and geography.
- Decision the research must inform.
- Purchase or usage context.
- Price or expected price range.
- Current customer evidence, or an explicit statement that none exists.
- Known alternatives, including manual work and doing nothing.

## Optional inputs

- Interview transcripts and customer messages.
- Sales calls, win-loss notes, support tickets, and churn reasons.
- Reviews, search queries, community discussions, and survey responses.
- Behavioral analytics and cohort data.
- Existing `MARKETING-BRIEF.md`, `BRAND-VOICE.md`, or `COMPETITOR-REPORT.md`.
- Acquisition channels, deal cycle, retention, and unit economics.
- Regulated or excluded segments.

## Dependencies and precedence
Behavioral and first-party evidence outranks demographic convention. Recent evidence from the target market outranks broad practitioner claims. A segment must represent a meaningfully different situation, desired progress, decision process, or route to value.

Do not force a fixed number of segments. Do not invent names, ages, income, thoughts, emotions, diagnoses, cognitive biases, or physical reactions.

## Retrieval plan

Run one to three focused queries from the directory containing `SKILL.md`:

```text
python scripts/retrieve_marketing_context.py --query "customer jobs switching forces purchase situation alternatives" --domain consumer-behavior --limit 5 --json
python scripts/retrieve_marketing_context.py --query "market segmentation ICP prioritization and validation" --domain strategy-research --limit 5 --json
python scripts/retrieve_marketing_context.py --query "willingness to pay pricing research and decision criteria" --domain pricing-promotions --limit 5 --json
```

Select only queries relevant to the decision. Use practitioner material to form hypotheses, not to claim facts about the user's customers.

## Live checks
Use live research for current market definitions, product alternatives, pricing, policy constraints, and demographic or economic statistics. Prefer official company pages, regulators, primary research, and current datasets. Record geography, sample, period, method, source URL, and check date.

## Workflow phases

### Phase 1: Frame the decision

Define what will change after the research: target segment, product scope, positioning, price, channel, content, or experiment. Specify the confidence needed and the cost of a wrong decision.

### Phase 2: Build an evidence inventory

Classify every input as first-party behavior, first-party statement, public primary evidence, review or community evidence, practitioner material, or agent hypothesis. Record source, date, market, sample, and limitations.

### Phase 3: Extract observations

Code observable situations, triggers, attempted alternatives, desired progress, constraints, decision criteria, anxieties, habits, adoption barriers, proof needs, and outcomes. Preserve contradictory evidence and minority patterns when they affect the decision.

Do not translate a complaint directly into a universal customer truth.

### Phase 4: Form segment hypotheses

Group observations by meaningful differences in context and behavior. For every proposed segment state:

- qualifying situation;
- desired progress;
- current alternative;
- trigger;
- decision criteria;
- barriers and risks;
- route to reach the segment;
- supporting evidence;
- counterevidence;
- status.

Merge segments that would receive the same offer, proof, channel, and product experience.

### Phase 5: Build JTBD and switching forces

Write job stories in the form: `When [situation], I want to [motivation or action], so I can [desired progress]`.

Separate functional, emotional, and social dimensions only when evidence supports them. Describe push, pull, habit, and anxiety as hypotheses unless directly observed. Do not attach psychological labels to people.

### Phase 6: Prioritize for the stated decision

Use transparent criteria such as problem intensity, frequency, reachable demand, evidence quality, product fit, willingness-to-pay evidence, sales friction, and strategic fit. Show the evidence behind each criterion. Use ordinal labels, not fake precision.

### Phase 7: Derive implications

For each priority segment define suitable positioning, proof, offer, channel, onboarding, content themes, objections, and disqualifiers. Clearly separate observed customer language from suggested marketing language.

### Phase 8: Design validation

Create a research plan for unresolved assumptions. Include participant criteria, recruiting route, interview questions, sample logic, analysis method, disconfirming evidence, and the decision threshold. Do not promise that a small convenience sample represents the market.

## Exact output contract

When file output is requested or artifact mode is active, save the final artifact as `AUDIENCE-RESEARCH.md`. Otherwise return the same contract in the response. Use these sections in this order:

1. `Decision, scope, version, and overall status`
2. `Evidence inventory and coverage`
3. `Observed patterns and contradictions`
4. `Segment hypotheses`
5. `Priority segments and rationale`
6. `JTBD and switching forces`
7. `Decision criteria, barriers, and proof needs`
8. `Positioning, offer, channel, and product implications`
9. `Customer language and prohibited extrapolations`
10. `Unknowns and competing explanations`
11. `Interview and validation plan`
12. `Quality gate results`
13. `Next decision and owner`

Each segment must carry source references and one of the three statuses.

## Quality gates

- Decision fit: the study supports a named business or product decision.
- Evidence separation: observation, synthesis, judgment, and hypothesis are distinct.
- Behavioral segmentation: segments differ by situation or behavior, not decorative demographics.
- Evidence coverage: priority segments have multiple supporting observations or remain `NEEDS_DATA`.
- Counterevidence: contradictions and alternative explanations are preserved.
- JTBD integrity: job stories contain a situation, motivation, and desired progress.
- No fake psychology: no invented bias, emotion, diagnosis, or bodily response.
- No fake demand: market size, willingness to pay, and urgency are not inferred without evidence.
- Actionability: each priority segment changes at least one product or marketing decision.
- Validation: the plan can disconfirm the preferred hypothesis.

## Stop and fallback rules

- If no customer evidence exists, produce a provisional segment hypothesis map and validation plan with overall status `NEEDS_DATA`.
- If the user requires definitive audience conclusions without evidence, mark the request `BLOCKED` and explain the minimum evidence needed.
- If the market or product is undefined, ask up to three material questions before segmentation.
- If live statistics cannot be verified, omit them and continue with qualitative evidence.
- If personal data appears, redact identifiers and use only non-identifying patterns.
- If sources represent a biased sample, state the bias and restrict conclusions to that sample.

## Completion criteria
The workflow is complete when `AUDIENCE-RESEARCH.md` exists or the complete contract is returned in the response, every segment is traceable to evidence or labeled as a hypothesis, all gates have statuses, no invented persona details remain, and the document ends with a concrete next decision and validation owner.
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