Skip to content

gooseworks-ai/goose-skills / drafts/marketing/learn-my-brand

learn-my-brand

Verified

Learn my brand once and stop asking me every time. Use when someone says learn my brand, set up my brand, here's our brand book, remember how we talk, what can we claim, can we say this, approve our claims, sign off our voice, our price or product changed, the client approved the claims, pick up where we left off, or check our claims are still current. Reads what GooseWorks already found about the brand, asks only the gaps as drafts to confirm, audits every claim (including ones research marked approved) and gets the ones that matter signed off with proof, scope and review date, turns the voice into rules the owner confirms, checks logo, colours and fonts, and saves it all as it goes so every other job loads it instead of asking. Ends with an unknowns list and a read-back. Not for who our customers are and what they say (use research-audience) or writing positioning from scratch (not covered yet).

skill.meta.json

View on GitHub
{
  "slug": "learn-my-brand",
  "tier": "playbook",
  "version": "0.1.0",
  "pillar": "2 — Positioning, messaging and brand",
  "intents": [
    "learn my brand",
    "set up my brand",
    "here's our brand book",
    "stop asking me the same questions",
    "what are we allowed to claim",
    "approve our claims",
    "sign off our brand voice",
    "remember how we talk",
    "our price changed",
    "we launched a new product",
    "we rebranded",
    "this claim is wrong",
    "check our claims are still current",
    "can we say this",
    "the client approved the claims",
    "pick up where we left off"
  ],
  "reads": [
    "brand brain: server research result — summary, kit (logo, palette, fonts, voice read, audience, value props, tagline, proof points, approvedClaims, existing ads), products, onboarding, accounts, saved sources (written by the GooseWorks server's brand research)",
    "brand brain: learnings (written by this playbook, analyze-performance, and the server's feedback distiller)",
    "brand brain: customer evidence and documents via knowledge_search (written by the server's review import, research-market, and this playbook)",
    "brand brain: tracked competitors and suggestions (written by the server's research and research-competitors)",
    "workspace brand/situation.md: the founder's situation from where-to-start, 'Founder said' lines only, confirmed before use (written by where-to-start) — moved into the Brand record when confirmed",
    "lines another playbook cut for lack of approval, brought here by the human (one-claim mode; playbooks never call each other)",
    "voice cards in brand/voices/ (written through atoms/voice-card by this playbook, run-organic-social and make-content)"
  ],
  "writes": [
    "brand kit: voice (the confirmed guide), audience, description, value props (only approved claims), brand type, colours; knowledge: positioning (owner's one-liner), tagline — user_correction with the owner's words (read by every playbook through brand_read kit)",
    "brand products: offers with end dates, notes (hero, what it does not do), ad_eligibility + reason (read by make-static-ads, make-video-ads, make-product-photos, email-lifecycle, plan-campaign)",
    "brand onboarding: role, platforms (read by where-to-start and the server's own setup)",
    "brand learnings through atoms/save-learning, one idea each, in one call: one 'Claims you may use —' fact per approved claim (offers and policies stated in copy included), one 'Never say —' fact per never-say line, 'Not public —' facts, one 'Banned words —' fact, one 'Policy:' fact per operating rule, and the marker with status signed-off|pending-client|not-signed, approver owner|client, voice confirmed|provisional (read by every writing and making playbook through atoms/claims-gate, and by the server's ad and video engines)",
    "Brand record brand/records/<date>-v<N>.md (brand coworker scope), imported as 'Brand record — <Brand> — <date> v<N>' through atoms/save-to-brain: claims with variants and proof, sign-off sheet, not-approved and retired claims, voice status and full banned list, never-say, business facts, contradiction decisions, palette and fonts, unknowns (read by atoms/claims-gate for variants and proof, and by this playbook's update, resume and sweep modes; the unknowns ledger is for the owner and the next run)",
    "tracked competitors the owner names (read by research-competitors)",
    "uploaded brand files: logo, brand book, decks, evidence (read by the makers and via knowledge_search)",
    "voice cards brand/voices/<handle>.md for a founder's or account's own voice, through atoms/voice-card (read by run-organic-social, make-content)"
  ],
  "needs": {
    "mcp": [
      "gooseworks:file_list",
      "gooseworks:get_started",
      "gooseworks:brand_read",
      "gooseworks:brand_setup_status",
      "gooseworks:brand_update",
      "gooseworks:knowledge_search",
      "gooseworks:knowledge_import",
      "gooseworks:job_get",
      "gooseworks:media_upload",
      "gooseworks:media_list",
      "gooseworks:competitor_read",
      "gooseworks:competitor_save",
      "gooseworks:tools_load",
      "gooseworks:automation_upsert",
      "gooseworks:file_write",
      "gooseworks:file_read",
      "gooseworks:campaign_read",
      "gooseworks:media_update",
      "gooseworks:knowledge_sync",
      "gooseworks:media_analyze"
    ]
  },
  "atoms": [
    "claims-audit",
    "voice-calibrate",
    "brain-write-back"
  ],
  "shared_atoms": [
    "claims-gate",
    "save-learning",
    "save-to-brain",
    "voice-card"
  ]
}
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