voice-gate
Skill5 starsChanged 6 months agoApache-2.0View on GitHub
Hard-block voice gate. Reads a target file, runs the Tier 1 banlist check against `.claude/rules/voice-banlist.md`, returns a passed/blocked verdict. Use as a pre-flight gate for anything published in someone else's voice, before the quality-gate review pass.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- The-AIOS/aiostheir own version, first seen Nov 3, 2026
- idoforgod/cys-bookwriting-skillstheir own version, first seen Oct 25, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- The-AIOS/aios★ 113same name
- idoforgod/cys-bookwriting-skills★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- db-healthSkill
- dreamSkill
- forum-pulseSkill
- genesisSkill
- grill-meSkill
- handoffSkill
- hireSkill
- inbox-processSkill
- kaizenSkill
- quality-gateSkill
- quarterly-reviewSkill
- session-endSkill
- session-startSkill
- sync-upstreamSkill
- twin-updateSkill
- weekly-reviewSkill
- write-a-skillSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 28
Rule of thumb: if in doubt, invoke. The asymmetry is one turn of overhead against a voice violation that ships and cannot be recalled.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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 Gate — hard-block pre-flight
Validates a deliverable against .claude/rules/voice-banlist.md and returns a
structured verdict.
Prerequisite: a banlist at .claude/rules/voice-banlist.md. The repo ships
voice-banlist.example.md — European Portuguese, plus the language-neutral AI
tells. Copy it, cut what does not apply to you, and add what your own writing
keeps getting wrong. A banlist copied wholesale from someone else's voice blocks
sentences you would have wanted and lets through the ones you would not.
When to invoke
Anything a third party will read in someone else's voice:
- Owner-voice external commercial writing (client and supplier email, quotations)
- Co-authored or academic prose that the user will sign
- Branded, published content (posts, deck copy, visual copy)
Rule of thumb: if in doubt, invoke. The asymmetry is one turn of overhead against a voice violation that ships and cannot be recalled.
Usage
/voice-gate <path>Behaviour
- Resolves the path (absolute, or relative to the project root).
- Runs
.claude/skills/voice-gate/check.shagainst the file. - Returns:
VERDICT=passed→ exit 0. Safe to hand on.VERDICT=blocked→ exit 1, with violations by category. Refine and re-invoke.VERDICT=error→ exit 2. File missing or unreadable.
Context is read from voice-context: front matter when present, otherwise
inferred from the path. Files in a documentation context exit clean: docs that
catalogue these patterns would otherwise flag every example they teach.
Composition with quality-gate
Voice-gate runs before the quality-gate review pass. This ordering is deliberate:
- Voice-gate catches deterministic Tier 1 violations cheaply and mechanically.
- The reviewer then spends their attention on substantive critique — voice fit, structure, factual integrity — instead of on textbook AI tells a regex could have caught.
Order for a gated deliverable:
- Agent produces the draft
/voice-gate <file>→ must pass/quality-gate <file>→ review pass (mandatory for A/B/C class; see.claude/protocols/quality-gate.md)- Delivery
Out of scope
Voice-gate does not replace human review for nuance — tone fit, persona, register. It blocks only unambiguous Tier 1 violations. The judgement about whether something sounds right still belongs to a reader.
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.

