Brand Voice
Lock in a consistent brand voice, style, and tone across all written content. Analyze existing content to extract voice rules, then apply those rules to new writing.
Install
$ agentstack add skill-on-deck-society-love-stack-brand-voice ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-on-deck-society-love-stack-brand-voice) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Brand Voice
When activated, help the user maintain a consistent brand voice across their writing. Works in two modes: voice extraction and voice application.
Mode 1: Voice Extraction
When the user provides existing content (blog posts, marketing copy, social posts, emails, a style guide), extract the brand voice rules:
- Sentence length patterns (short and punchy, long and lyrical, mixed)
- Punctuation habits (heavy em dash use, no em dashes, frequent parenthetical asides, declarative periods)
- Vocabulary preferences (colloquial vs formal, industry jargon tolerance, specific words they use or avoid)
- Tonal range (irreverent, earnest, authoritative, conspiratorial, warm)
- Structural patterns (how paragraphs open, how they close, use of lists vs prose)
- Signature phrases or linguistic quirks
- Taboos (words, phrases, or styles the brand never uses)
Output a structured voice profile the user can save as a reference doc.
Mode 2: Voice Application
When the user asks to write new content "in our brand voice" or "like the rest of our copy":
- Check if a voice profile exists in the project (look for voice.md, brand-voice.md, tone-of-voice.md, or similar in the project root or /docs)
- If found, apply those rules to the new content
- If not found, ask the user to either point to reference content or run voice extraction first
When writing in-voice content, produce a draft that actively mirrors the extracted patterns. Flag any place where the voice feels forced or where the content's requirements conflict with the voice.
When to Invoke
Invoke when the user says: "match our brand voice", "write this in our tone", "make this sound like us", "extract our voice from these posts", "does this sound like our brand", or similar.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: on-deck-society
- Source: on-deck-society/love-stack
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.