Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Scaffolds REST API endpoints with route handler, validation, error handling, and tests. Use when asked to create a new API endpoint or route.
Reviews staged git changes and provides feedback on code quality, potential bugs, and security issues before committing. Use when asked to review changes or before creating a commit.
Generates production-ready React components with TypeScript, Tailwind CSS, proper accessibility, and test scaffolding. Use when asked to create a new React component.
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
Security-focused code review for staged changes or specified files. Checks for injection, auth flaws, crypto misuse, data exposure, and insecure patterns. Works with any language.
Run a comprehensive security audit against a codebase. Covers OWASP Top 10, secrets exposure, dependency vulnerabilities, misconfigurations, and insecure patterns. Language-agnostic.
Generate a STRIDE-based threat model from codebase and architecture analysis. Identifies assets, trust boundaries, data flows, threats, and mitigations. Language-agnostic.