$ show blader/humanizer
Humanizer is a skill (prompt) for AI agents that rewrites AI-generated text to sound human-written without altering factual content. It is built on Wikipedia's 'Signs of AI writing' guide and provides 26 numbered patterns grouped into six categories (staging, rhythm, inflation, formatting, leftovers, wrong reader). The skill is distributed as a single markdown file (SKILL.md) with YAML metadata, installable via plugin manifests for Claude Code, Cursor, and other agents through the Skills CLI. The repository also includes a validation script, issue templates, and CI workflows to maintain consistency across package files. While not a traditional software application, it functions as a tool that agents execute, with clear entry points (/humanizer command) and a well-defined workflow (mark tells, draft rewrite, check, finalize). The codebase is meticulously maintained with active issue triage, regular releases, and automated validation.
The LLM identified 3 files worth highlighting for reuse:
A self-contained Python script that validates consistency across Humanizer's package files (SKILL.md, README.md, CHANGELOG.md, plugin manifests). It checks version alignment, pattern numbering, description matching, word count limits, and YAML metadata without external dependencies. This pattern is reusable for any multi-file project that needs to enforce cross-file consistency, especially for prompt-based or documentation-heavy repositories.
A well-structured GitHub issue template for proposing new AI writing patterns. It requires an example, a human-written alternative, and an explanation of why existing patterns don't cover it. The template enforces quality contributions by asking contributors to check against existing patterns first, reducing duplicate or redundant suggestions. This pattern is reusable for any project that maintains a curated list of patterns or rules.
A detailed bug report template for rewrite issues, capturing input text, exact invocation details, output, and expected behavior with pattern references. It includes a dropdown for problem type and requires quoting the problematic sentence. This pattern is reusable for any AI-assisted editing tool or prompt-based system that needs precise bug reproduction.