Sam Voice
Apply Sam Dumont's personal writing voice and style when drafting reports, blog posts, technical documentation, client communications, Slack messages, LinkedIn posts, or any written content. Use this skill whenever Sam asks to write, draft, review, or improve text in his voice - including phrases like "write this for me", "draft a post", "in my style", "my voice", "write a report", "blog post", "client email", "Slack message", or any content creation task where Sam's personal tone should come through. Also trigger when Sam asks to translate content while maintaining his voice. Works in both En
Install
/plugin marketplace add sam-dumont/claude-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add sam-dumont/claude-skills --skill sam-voicegit clone --depth 1 https://github.com/sam-dumont/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/plugins/sams-voice/skills/sams-voice ~/.claude/skills/sam-voicePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Sam Dumont - Writing Voice Guide This skill defines Sam's writing voice for content generation across all formats and both languages (English and French). The voice is the same person in both languages - direct, technically precise, warm but no-nonsense. ## CRITICAL: Zero tolerance for LLM-isms Sam DESPISES typical AI-generated language. Before producing ANY text using this skill, mentally scan your output for every item in the ban lists below and replace or remove them. This is the single most important rule in this skill. If the output reads like it could have been generated by a chatbot, it has failed. The ban lists below are not exhaustive. The general principle: if a word or phrase feels like something a corporate chatbot would write, do not use it. ### Banned English words NEVER use these words in Sam's voice. They are the most statistically overrepresented words in LLM-generated text, backed by peer-reviewed research (Kobak et al. 2025, Liang et al. 2024): **Adjectives:** delve/delving, actionable, bespoke, bustling, captivating, commendable, comprehensive (as filler), cutting-edge, daunting, ever-evolving, game-changing, groundbreaking, holistic, impactful, innovative, insightful, intricate, invaluable, meticulous, multifaceted, notable, noteworthy, nuanced, paramount, pivotal, profound, remarkable, revolutionary, robust (outside technical contexts), seamless, state-of-the-art, substantial, tailored,
Details
- Skill name
sam-voice- Repository
- sam-dumont/claude-skills
- Path
plugins/sams-voice/skills/sams-voice/SKILL.md- License
- MIT
- Repo updated
- 3 November 2026
FAQ
What does the Sam Voice skill do?
Apply Sam Dumont's personal writing voice and style when drafting reports, blog posts, technical documentation, client communications, Slack messages, LinkedIn posts, or any written content. Use this skill whenever Sam asks to write, draft, review, or improve text in his voice - including phrases like "write this for me", "draft a post", "in my style", "my voice", "write a report", "blog post", "client email", "Slack message", or any content creation task where Sam's personal tone should come through. Also trigger when Sam asks to translate content while maintaining his voice. Works in both En
How do I install the Sam Voice skill?
Claude Code plugin: /plugin marketplace add sam-dumont/claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Sam Voice popular?
It lives in sam-dumont/claude-skills, which has 38 GitHub stars and 4 forks.
Related skills
Advanced Code Quality
38sam-dumont/claude-skills
Use when going beyond basic linting to enforce advanced Python code quality gates. Triggers on: cognitive complexity, code duplication detection, architectural enforcement, import boundaries, dependency hygiene, test quality beyond coverage, mutation testing, docstring coverage, type coverage, AI-generated code detection, AI slop detection, complexipy, jscpd, import-linter, deptry, diff-cover, mutmut, interrogate, sloppylint, refurb, pylint design checks, wily, radon maintainability, pytestarch, griffe, "bulletproof Python", "tighten quality gates", "advanced quality checks", "beyond ruff and
Code Quality
38sam-dumont/claude-skills
Automatically triggered when setting up Python code quality tooling, configuring linters, adding type checking, improving code standards, running code quality checks, setting up pre-commit hooks, or auditing Python code for quality issues. Applies when discussing: ruff setup, mypy configuration, code formatting, linting rules, cyclomatic complexity, dead code detection, file length limits, pre-commit hooks, Makefile targets for quality, uv-based workflows, pyproject.toml configuration, or "check my code quality". Also triggers on: "set up linting", "add type checking", "configure ruff", "forma
Code Security
38sam-dumont/claude-skills
Automatically triggered when running security scans, auditing code for vulnerabilities, checking dependencies for CVEs, reviewing code for security issues, or hardening Python applications. Applies when discussing: security audit, vulnerability scan, bandit, pip-audit, dependency vulnerabilities, OWASP, injection, path traversal, secrets detection, insecure deserialization, auth bypass, or "is this code secure?". Also triggers on: "run security checks", "find vulnerabilities", "security review", "check for CVEs", "audit dependencies", "security lint", "pen test this code", "harden this applica
Youtube Transcript
62ElliotJLT/Claude-Skill-Potions
Extracts YouTube video transcripts and saves them as structured markdown files with metadata and timestamped content. When a user shares a YouTube URL, IMMEDIATELY runs the extraction script, creates a local folder, and saves the transcript. Handles both manual and auto-generated captions.
Transactions and Concurrency
49dynamics365ninja/d365fo-cli
Scope transactions and survive concurrency in D365FO — ttsbegin/ttscommit rules, optimistic concurrency and UpdateConflict retry, UnitOfWork, and the error-handling patterns that go with them. Invoke when the user asks about transactions, tts levels, locking, update conflicts, retry, or where to put try/catch.
Apiyi Gpt Image 2 All Gen
43wuchubuzai2018/expert-skills-hub
AI图片生成技能,使用ChatGPT最新生图 gpt-image-2-all,当用户需要生成图片、视觉信息图、创建图像、编辑/修改/调整已有图片时使用此技能。基于API易平台(https://api.apiyi.com/)的ChatGPT最新生图gpt-image-2-all模型(gpt-image-2-all)的图片生成服务,无需访问外网。该模型以 $0.03/张 按次计费,支持文生图、单图编辑、多图融合、自然语言改图,文字还原度高、中文提示词友好。尺寸通过prompt描述控制(无显式size参数)与NanoBanana2不同的关键点:无size参数,需在prompt开头描述尺寸;统一$0.03/张无分辨率阶梯;使用对话式端点/v1/chat/completions为主推。
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.