gooseworks-ai/goose-skills / drafts/marketing/learn-my-brand
learn-my-brand
VerifiedLearn 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).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 14.5 KB |
| atoms/brain-write-back/ATOM.md | markdown | 6.8 KB |
| atoms/claims-audit/ATOM.md | markdown | 3.9 KB |
| atoms/voice-calibrate/ATOM.md | markdown | 3.1 KB |
| references/brain-map.md | markdown | 10.2 KB |
| references/brand-record-template.md | markdown | 6.2 KB |
| references/category-rules.md | markdown | 9.5 KB |
| references/claims-craft.md | markdown | 13.4 KB |
| references/intake-craft.md | markdown | 7.8 KB |
| references/voice-craft.md | markdown | 6.4 KB |
| skill.meta.json | config | 4.5 KB |
| tests/test-by-hand.md | markdown | 12.0 KB |
atoms/voice-calibrate/ATOM.md
View on GitHub---
name: voice-calibrate
description: >-
Internal step of learn-my-brand (hidden). Turns the brain's prose voice read and the brand's own lines into
falsifiable voice rules with do/don't pairs, banned words, terminology and channel/speaker flex, and gets the
owner's yes with the triad test and a keep-or-kill round.
---
# voice-calibrate
Load `../../references/voice-craft.md` first.
## Input
The kit's `voice`, `tone`, `aesthetic`; `existingAds` hooks; voice rules already in learnings (`kind` do / dont / must; owner-made ones beat the research read); 6–10 of the brand's own lines gathered by trust order (founder-written, best-performing, recent, agency, site). Pre-launch with little copy: 5–10 posts the founder pastes plus their messages in this chat, and say the result is provisional. Never invent a "real line".
## Procedure
1. **Screen** every sample line against the approved-claims and never-say lists; a line that carries an unapproved claim or addresses the reader's health, body or finances can't be a "we say" example. Show any clash between owner-made rules and the research read.
2. **Draft** personality is/is-not (3–4 pairs), 3–5 rules each with a real "we say" and a plausible "we don't say", terminology, mechanics, and a one-line flex for each channel and speaker the brand uses. Run the failure-mode checks in voice-craft.md; drop any rule that would fit the top two competitors equally.
3. **Triad test.** Pick one real line. Rewrite it three ways along one dial. Ask "Which is us?" Repeat for a second dial, and a third only if the first two disagree with the draft. Adjust the draft after each answer.
4. **Keep or kill.** Write five short lines in the draft voice (ad hook, email subject, social caption, support reply, and a B2B line if B2B). Ask the owner to keep or kill each and say why for kills. Turn each why into a rule in their words.
5. **Banned words.** Show the standing list plus any the owner named; ask which, if any, they keep on purpose.
6. **Show the guide** on one screen. Ask for corrections. Their yes, verbatim, is the sign-off.
## Output (to `atoms/brain-write-back`)
- The confirmed voice for the kit's `voice` field: personality, the rules with their pairs, terminology, mechanics and channel/speaker flex (siblings read the kit voice, its home; voice rules don't also go in learnings).
- Banned words: the full list in the kit voice under "Banned:" and in the record's Voice section; the `Banned words —` fact holds the full list, the owner's own words first.
- Voice status for the marker: `confirmed`, or `provisional` (then nothing voice-related is written; the draft lives in the Brand record).
- For a founder's or account's own voice: hand over to `../../../../../skills/marketing/voice-card/SKILL.md` to build the card.
- The owner's approval words verbatim.
## Rules
- If the approver is not in the chat, the guide goes to the sign-off sheet's voice line and the kit voice is left unchanged until they answer.
- Start from the brain's read; do not throw it away and re-distill from scratch.
- Show, then ask them to choose. Never ask for adjectives or ratings.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |