By sam-dumont
Apply Sam Dumont's direct, precise, warm writing voice to any written content in English or French, automatically removing AI-sounding language across reports, blog posts, technical docs, emails, Slack, and LinkedIn posts.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub sam-dumont/claude-skills --plugin sams-voiceResearch whether a metal band has ties to far-right, NSBM, or fascist movements. Uses parallel research agents with tiered verdicts for both historical and current status.
Advanced Python code quality gates beyond basic linting. Covers cognitive complexity (complexipy), code duplication (jscpd), architectural enforcement (import-linter), dependency hygiene (deptry), test quality gates (diff-cover, mutmut), docstring coverage (interrogate), and AI-generated code detection (sloppylint). Complements the code-quality skill with 20+ additional tools and exact thresholds.
Comprehensive Python code quality skill. Sets up and runs ruff (lint + format), mypy (type checking), xenon (cyclomatic complexity), vulture (dead code), file-length gates, and pre-commit hooks. Provides a full Makefile-based workflow using uv for fast package management.
Codifies Sam's mature architectural patterns for Python APIs, infrastructure/DevOps, Garmin/embedded systems, and frontend projects. Enforces Service→Repository→Database pattern, 80% test coverage, comprehensive CI/CD, and zero-tolerance security standards.
Comprehensive Python code security skill combining static analysis tools (Bandit, pip-audit, safety) with LLM-powered dynamic analysis. Claude actively reviews code for injection vulnerabilities, path traversal, insecure deserialization, secrets exposure, auth bypasses, and logic flaws that static tools miss.
Voice profile system for consistent, authentic writing. Apply, create, blend, and analyze voices. Includes 4 built-in profiles: technical-authority, friendly-explainer, executive-brief, and casual-conversational.
Reframes tasks as measurable outcomes using o16g principles. Adds outcome specification, execution guardrails, and validation to any workflow.
Research-backed writing toolkit: anti-AI prose principles, iterative review loop, author voice capture, and voice-matched content generation
Documentation review, cleanup, generation, voice extraction, and human-quality writing enforcement with AI slop detection and SICO-based voice profiling
Catch robotic-sounding writing and rewrite it in a voice you choose. One skill, 5 commands (/cadence write, learn, recast, deslop, voices) and a deterministic checker that scores prose and names every tell.
Remove AI-writing tells while preserving meaning, voice, and density.