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

scripts/mbpack_output.py

View on GitHub
from __future__ import annotations

import re
from typing import Any

from mbpack_codec import normalized_tokens


def collect_metadata_values(value: Any, values: set[str]) -> None:
    if isinstance(value, str):
        normalized = " ".join(value.strip().strip("\"'").split())
        if 3 <= len(normalized) <= 500:
            values.add(normalized)
        return
    if isinstance(value, dict):
        for nested in value.values():
            collect_metadata_values(nested, values)
        return
    if isinstance(value, (list, tuple)):
        for nested in value:
            collect_metadata_values(nested, values)


def label_variants(value: str) -> set[str]:
    cleaned = value.lstrip("- \u00a0")
    variants = {value, cleaned}
    if "://" in value:
        return variants
    stem = re.sub(r"\.(?:md|pdf|txt|docx?|epub)\Z", "", value, flags=re.IGNORECASE)
    variants.add(stem)
    unnumbered = re.sub(r"^\s*\d{1,4}[-_.\s]+", "", stem)
    variants.add(unnumbered)
    if " - " in unnumbered:
        trailing = unnumbered.rsplit(" - ", 1)[1].strip()
        if 3 <= len(trailing) <= 120:
            variants.add(trailing)
        without_parenthetical = re.sub(r"\s*\([^()]+\)\s*\Z", "", trailing)
        if 3 <= len(without_parenthetical) <= 120:
            variants.add(without_parenthetical)
    variants.update(
        match.strip()
        for match in re.findall(r"\(([^()]{3,120})\)", unnumbered)
    )
    comma_parts = [part.strip() for part in cleaned.split(",")]
    if 2 <= len(comma_parts) <= 5:
        variants.update(part for part in comma_parts if 3 <= len(part) <= 120)
    return {item for item in variants if 3 <= len(item) <= 500}


def source_metadata_values(provenance: dict[str, Any]) -> list[str]:
    values: set[str] = set()
    collect_metadata_values(provenance.get("bibliography"), values)
    title_signal = provenance.get("title_signal")
    if isinstance(title_signal, dict):
        for field in ("declared", "body"):
            collect_metadata_values(title_signal.get(field), values)
    for field in ("primary_source_url", "source_urls"):
        collect_metadata_values(provenance.get(field), values)
    collect_metadata_values(
        provenance.get("bibliographic_preamble_lines"),
        values,
    )
    expanded: set[str] = set()
    for value in values:
        expanded.update(label_variants(value))
    return sorted(expanded, key=lambda item: (-len(item), item.casefold()))[:64]


def source_author_stems(provenance: dict[str, Any]) -> list[str]:
    author_values: set[str] = set()
    bibliography = provenance.get("bibliography")
    if isinstance(bibliography, dict):
        for field in ("author", "authors", "creator", "creators"):
            collect_metadata_values(bibliography.get(field), author_values)
    title_signal = provenance.get("title_signal")
    if isinstance(title_signal, dict):
        body_signal = title_signal.get("body")
        if isinstance(body_signal, str) and "," in body_signal:
            author_values.add(body_signal)
    preamble_lines = provenance.get("bibliographic_preamble_lines")
    if isinstance(preamble_lines, list) and preamble_lines:
        first_line = preamble_lines[0]
        if isinstance(first_line, str) and "," in first_line:
            author_values.add(first_line)
    stems: set[str] = set()
    for value in author_values:
        for token in re.findall(r"[^\W\d_]{5,}", value, re.UNICODE):
            root_size = max(5, len(token) - 2)
            stems.add(token[:root_size])
    return sorted(stems, key=lambda item: (-len(item), item.casefold()))


def mask_source_metadata(text: str, provenance: dict[str, Any]) -> str:
    masked = text
    for value in source_metadata_values(provenance):
        pattern = re.compile(
            r"\s+".join(re.escape(part) for part in value.split()),
            re.IGNORECASE,
        )
        masked = pattern.sub("[HIDDEN_SOURCE_METADATA]", masked)
    for stem in source_author_stems(provenance):
        pattern = re.compile(
            rf"(?<![\w\[]){re.escape(stem)}[\w-]*",
            re.IGNORECASE,
        )
        masked = pattern.sub("[HIDDEN_SOURCE_AUTHOR]", masked)
    return masked


def query_anchor(text: str, query: str) -> int:
    folded = text.casefold()
    tokens = sorted(set(normalized_tokens(query)), key=lambda item: (-len(item), item))
    for token in tokens:
        position = folded.find(token.casefold())
        if position >= 0:
            return position
    return 0


def centered_excerpt(text: str, query: str, maximum: int) -> str:
    stripped = text.strip()
    if len(stripped) <= maximum:
        return stripped
    anchor = query_anchor(stripped, query)
    start = max(0, anchor - maximum // 3)
    if start:
        boundary = stripped.find(" ", start, min(len(stripped), start + 80))
        if boundary >= 0:
            start = boundary + 1
    prefix = "..." if start else ""
    available = maximum - len(prefix) - 3
    end = min(len(stripped), start + max(1, available))
    if end < len(stripped):
        boundary = stripped.rfind(" ", start + available * 3 // 4, end)
        if boundary > start:
            end = boundary
    suffix = "..." if end < len(stripped) else ""
    return prefix + stripped[start:end].strip() + suffix
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