hardikpandya/stop-slop

Source
GitHub
First trending
Category
Skills
GitHub stars
17,248

This page introduces an external open-source repository. It is not an HDATF product.

hardikpandya/stop-slop

What it does

Stop Slop is a skill file that teaches Claude or another LLM to find and remove patterns typical of AI writing, such as banned phrases and structural clichés. It scores prose on directness, rhythm, trust, authenticity and density.

How it helps ATF

Could be a reference for a writing review skill in the ATF Works assistant for reports, wiki pages or daily work logs. Its layout of one core file with reference files loaded on demand is worth comparing with how Harness loads skills.

License

MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.

More in this category

  • Leonxlnx/taste-skill
    Taste Skill is a set of portable Agent Skills that push AI coding agents toward better layout, typography, motion and spacing in the interfaces they build. It also includes image-generation skills for web, mobile and brand reference boards.
  • anthropics/claude-plugins-official
    An Anthropic-managed directory of Claude Code plugins, split into internal plugins and third-party plugins. Each plugin follows a standard structure with metadata and optional MCP server config, commands, agents and skills.
  • microsoft/SkillOpt
    SkillOpt trains reusable natural-language skills for LLM agents without changing model weights. It edits a skill based on agent trajectories, accepts updates only when they pass validation, and outputs the best version as a best_skill.md file.
  • anthropics/claude-for-legal
    Reference agents, skills and data connectors for legal workflows such as privacy, litigation and IP, packaged as Claude plugins or for the Claude Managed Agents API. Every output is a draft for attorney review.
  • shadcn/improve
    An agent skill that audits a codebase and writes self-contained implementation plans as markdown files for cheaper models to execute. The skill does not write code itself, and an execute mode dispatches a cheaper executor and reviews its work.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.

View on GitHub (opens in a new tab)