Install
$ agentstack add skill-0xelitesystem-claude-skills-templates-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.
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
Applies a configured voice and tone guide to drafts. The voice itself lives in references/brand-voice.md so it can be customized without touching the skill logic.
Workflow
- Read
references/brand-voice.mdin full before editing anything. - Identify the input: a draft pasted by the user, an uploaded file, or a section of an existing document.
- Run the rewrite pass below.
- Output the rewritten version, then a short audit of what changed.
Rewrite pass
For each paragraph in the input:
- Check it against the voice attributes in the reference file.
- Check it against the banned-words list.
- Check it against the preferred-phrasings list.
- Rewrite if any check fails. Leave alone if all pass.
- Preserve the original meaning and key facts. Only change how it is said.
What to preserve
- Numbers, dates, names, quotes (exact)
- Section structure (headings, ordering, list items)
- Technical accuracy (do not soften precise language into vague language)
- Length within plus or minus 15% unless the user asked for shorter or longer
What to change
- Word choice that violates the banned-words list
- Sentence rhythm that conflicts with the stated voice (e.g., long flowing prose when the voice is "punchy")
- Formality level (casual versus formal)
- Filler and hedging that is not in the voice
- Default-AI patterns that creep in (em-dashes, "not just X but Y", tricolon abuse)
Output format
Render in two parts:
````
Rewritten
Changes
- (up to 5 total)
````
When the reference file is missing or empty
If references/brand-voice.md is missing, or contains only the placeholder template with no user content, do not guess at the voice. Tell the user the reference file needs content first, and offer to interview them with three specific questions:
- What three adjectives describe your voice? (e.g., direct, warm, technical)
- What words or phrases do you ban?
- Paste two sentences in your voice and two that fail.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: 0xelitesystem
- Source: 0xelitesystem/claude-skills-templates
- License: MIT
- Homepage: https://elitesystem.ai
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.