Enforces coding standards while writing code to prevent common P0/P1 issues. Auto-activates when writing or editing code. Covers security, error handling, performance, and boundary conditions.
From claude-toolkitnpx claudepluginhub luistheabysswalker/claude-toolkitThis skill uses the workspace's default tool permissions.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Guides slash command development for Claude Code: structure, YAML frontmatter, dynamic arguments, bash execution, user interactions, organization, and best practices.
Apply these rules while writing code to avoid issues before review.
dangerouslySetInnerHTML, innerHTML, or unescaped template output with user datacatch {} or catch-and-log-only.catch() on promises, try-catch in async functionsIN (?) or $in[0] or .length - 1if (value) when 0, "", or false are valid — use explicit checksif (exists) then create)balance = get(); balance -= x; set(balance))UPDATE SET count = count + 1, not read-then-write)