Backend Unslop
Audit API and database code for validation, query, error-handling, and security mistakes.
Skills are written instructions your agent loads when a task calls for them. Each listing shows what the skill covers and how to install it.
Audit API and database code for validation, query, error-handling, and security mistakes.
Review English and Bahasa Indonesia product copy for vague wording, readability, and length.
Review AI-written React, Next.js, and Tailwind code for implementation mistakes.
Review native and cross-platform mobile code for crash risks, permissions, and accessibility gaps.
Guide an AI agent through storyboarding, building, and reviewing product animations.
Give an AI agent a design workflow for typography, color, layout, tokens, and visual review.
Find ineffective tests, run the available suite, and report whether tests actually executed.
Check interface contrast, accessibility, design tokens, and interaction states.
A skill is a folder with a SKILL.md file. The file says when the skill applies and which steps to follow. Some skills also include scripts, templates, or reference notes.
Your agent reads the short description of each installed skill. When a request matches, it loads the full instructions and follows them. Your prompts stay short and the results stay consistent.
Claude Code reads skills from ~/.claude/skills or a project's .claude/skills folder. Codex reads them from its own skills folder. Each listing's setup notes give the exact command.
You paste a prompt into one chat. A skill stays installed, and your agent loads it whenever a task matches its description.