voice-guard
Skill1 starsChanged 6 months agoMITView on GitHub
Quality gate for marketing copy. Use when: check this copy for ai tone, voice check this landing page, does this email sound human?, score this draft before we ship it, clean up the hype in this post, run voice guard on [file].
In this repository12 other files it gives its agents.
- content-opsSkill
- conversion-opsSkill
- creative-opsSkill
- finance-opsSkill
- growth-engineSkill
- outbound-engineSkill
- podcast-opsSkill
- revenue-intelligenceSkill
- sales-pipelineSkill
- sales-playbookSkill
- seo-opsSkill
- team-opsSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Check this copy for AI tone
- Distinctive: line 16
Run voice guard on [file]
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Voice Guard
Quality gate for marketing copy. Scores a draft for machine-sounding writing (filler openers, hype vocabulary, hedging, em-dash overuse, reflexive three-item lists, and flat sentence rhythm) and points at the exact phrases to fix. Run it on anything another skill generates before it ships.
When to Use
- Check this copy for AI tone
- Voice check this landing page
- Does this email sound human?
- Score this draft before we ship it
- Clean up the hype in this post
- Run voice guard on [file]
Workflow
- Collect the draft -- paste copy or point at a file produced by another skill
- Score -- run
python_runtime.voice.check_voice(text) - Triage -- group findings by kind; fix filler and hype first (largest penalties)
- Rewrite -- replace flagged phrases with concrete claims: numbers, named outcomes, specific users
- Re-score -- repeat until the band is
ship(85+) - Log -- keep the before/after scores with the asset so reviewers see what changed
Reference
Full methodology lives in README.md in this folder: configuration, scoring formulas, output formats, integration points, and worked examples. Read it before producing scored output.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

