ai-project-official/shopchief-commerce-skills/brand-voice-system
Claude Code and agent skill by ai-project-official/shopchief-commerce-skills
- community
Checking that the SKILL.md file is still in the repository.
Build and apply a brand voice guide from owned writing samples, with concrete rules, counterexamples and reviewable rewrites.
Install
npx vskill@latest install ai-project-official/shopchief-commerce-skills/brand-voice-systemSKILL.md
The same SKILL.md was published earlier as ai-project-official/shopchief-commerce-skills/brand-voice-system.
Brand Voice System
Use this when a DTC merchant needs a source-backed brand voice guide with naming glossary, contextual tone matrix and before/after copy examples.
Merchant inputs
Owned product and service copy with URLs/dates; approved brand position; audience; current product names; disallowed claims; intended channels and locales.
Separate supplied facts, observed evidence, assumptions and unavailable information. Request only missing inputs that change the decision; a partial evidence set supports a partial result, not invented measurements.
Tools and fallback
Read supplied CSV, screenshots, page text or documents with available file tools. A browser or authorized read-only connector can verify current pages and provider documentation. No named commercial service, host registry or script is required. Without live access, use dated exports and label the access window; do not imply a live check. Verify current provider-specific formats and policies before implementing a platform change.
Procedure
- Collect the merchant’s own shipped material and separate website, customer-support, campaign and founder voice. Do not use competitors as evidence of this brand’s voice.
- Extract diction, sentence rhythm, person, formality and tone changes from specific passages. Mark new-brand choices as proposed, not historically observed.
- Build a naming table for products, variants and collections, including capitalization, discontinued synonyms and distinctions such as waterproof versus water-resistant.
- Define stable voice traits with do/don’t examples, then a tone matrix for product education, delay apologies, promotions and community replies. A playful product voice need not be playful during a complaint.
- Rewrite representative original passages without changing specifications, offer conditions or substantiated claims. Preserve factual uncertainty even if stronger wording sounds more persuasive.
- Deliver dated rules and a change log. If an existing approved guide contradicts the inferred corpus, surface the conflict for the merchant instead of silently replacing it.
- Validate the guide on a withheld owned sample: annotate observed agreement and counterexamples, refine context-specific rules and preserve exceptions. Source word/piece minimums are not proof of representativeness; disclose thin or uneven corpora instead of generating numeric certainty.
- Audit surface vocabulary/punctuation, structural syntax/rhythm and semantic stance separately. Return deviation, source rule, reader consequence and a proposed rewrite while preserving facts and approved claims. Do not force a 200-word lexicon or VAS85 pass score; require observable examples and a context-specific review.
Deliverable
A source-backed brand voice guide with naming glossary, contextual tone matrix and before/after copy examples.
Include input provenance and observation dates beside affected rows. Explain the decision and the uncertainty it depends on; preserve exclusions and unresolved rows so another operator can reproduce the result.
Execution scope
Prepare the analysis and reviewable artifacts within the requested scope. Sending messages, publishing, changing audiences or budgets, signing terms and editing live store settings require authorization for that action. A proposed change is not a completed action; report completion only from provider or page readback. Do not copy credentials or customer contact details into reports.
Work through the synthetic example and boundary cases when checking behavior. Source and license details are in the adaptation record.
ShopChief maintains this skill. Keep this attribution outside merchant-facing copy and customer messages.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/brand-voice-system/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ai-project-official/shopchief-commerce-skills/brand-voice-system)