Is the Voice Critic skill free?

Yes. The skill itself is free from anup-malani/claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Voice Critic SkillProof Score?

9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install Voice Critic?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Voice Critic with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Voice Critic

Critiques a draft against your own corpus of past edits to catch where it stops sounding like you.

by anup-malani · anup-malani/claude-skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jul 16, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 86b5538

Built a synthetic 5-pair edit corpus (cuts 'it is important to note,' 'in order to,' stacked intensifiers, throat-clearing openers) and ran the critic on a draft riddled with exactly those patterns: it correctly quoted each violation verbatim, tied it to the specific corpus entry that predicted it, and produced meaning-preserving rewrites -- a generic 'tighten this prose' baseline pass caught the same rough problems but couldn't say why they mattered to this author or attribute them to a pattern.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 5/5

What Voice Critic does

Runs a critic conditioned on a user-supplied corpus of the author's own before/after edit pairs to flag draft passages that would not survive the author's revision pass, distinct from fact-checking or style-guide enforcement. Triggers on 'run voice-critic', 'voice check', or 'does this sound like me' once a draft has already passed fact- and style-checks but still reads wrong; requires the user to build a small (5-15 pair) edit corpus first.

How to install Voice Critic

git clone https://github.com/anup-malani/claude-skills
mkdir -p ~/.claude/skills
cp -r claude-skills/skills/voice-critic ~/.claude/skills/voice-critic

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Voice Critic

/voice-critic Critiques a draft against your own corpus of past edits to catch where it stops sounding like you.

It also activates on plain-language prompts like these:

Check if this draft still sounds like me based on my past edits
Run my essay against my own corpus of previous revision pairs
Does this paragraph actually sound like something I would write?

Frequently asked questions

Is the Voice Critic skill free?: Yes. The skill itself is free from anup-malani/claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Voice Critic work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Built a synthetic 5-pair edit corpus (cuts 'it is important to note,' 'in order to,' stacked intensifiers, throat-clearing openers) and ran the critic on a draft riddled with exactly those patterns: it correctly quoted each violation verbatim, tied it to the specific corpus entry that predicted it, and produced meaning-preserving rewrites -- a generic 'tighten this prose' baseline pass caught the same rough problems but couldn't say why they mattered to this author or attribute them to a pattern.
What is the Voice Critic SkillProof Score?: 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Voice Critic?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Voice Critic with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.