From claude-toolkit
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.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-toolkit:coding-standardsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Apply these rules **while writing code** to avoid issues before review.
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)npx claudepluginhub luistheabysswalker/claude-toolkitEnforces security-conscious coding: trust boundary identification, input validation, injection prevention, secrets management, and defense-in-depth authorization. Activates when handling user input, auth, DB queries, external APIs, file ops, or on security review requests.
Enforces quality and security in all AI-generated code: verifies packages, blocks insecure patterns, eliminates placeholders, ensures runnable and readable output.
Review code systematically for security vulnerabilities using OWASP Top 10, secure coding patterns, and static analysis best practices. Use when reviewing pull requests, conducting security code reviews, or implementing secure development practices.