Skill Claude CodeCodex
Use this skill when the user wants to update their project's CLAUDE.md or AGENTS.md, verify their Claude Code setup, or check for improvements to their project configuration. Triggers on requests like: "update my project docs", "verify my claude setup", "check my project configuration", "audit my .claude directory"…
Skill Claude CodeCodex
Use when creating /goal directives, reusable testable outcome-oriented success standards for agentic workflows. Use whenever the user asks to create a goal, write a /goal directive, define what good looks like, set success criteria for an agent, define a reusable instruction, create a quality standard, write…
MCP server Claude CodeCodexCursor +2
MCP Server for webhook.site API integration with layered architecture. Runs locally from the webhook-mcp-server Python package.
Agent Claude Code
Reviews code for quality, correctness, and maintainability.
Agent Claude Code
Reviews documentation for accuracy, completeness, and clarity.
Agent Claude Code
Creates distinctive, production-grade frontend UI — components, pages, layouts, and design systems. Use when building any web UI, landing page, dashboard, or component. Generates creative, polished code that avoids generic AI aesthetics.
Agent Claude Code
Reviews code for performance issues — memory leaks, slow queries, unnecessary computation, bundle size, and runtime bottlenecks. Use proactively after changes to hot paths, data processing, or API endpoints.
Agent Claude Code
Reviews code changes for security vulnerabilities.
Hook Claude Code
Runs before the agent uses a tool for Edit, Write and Bash tool calls, executing protect-files.mjs, warn-large-files.mjs and block-dangerous-commands.mjs via node (3 commands). From zebbern/termstack.
Hook Claude Code
Runs after a tool call finishes for Edit and Write tool calls, executing format-on-save.mjs via node. From zebbern/termstack.
Hook Claude Code
Runs when the agent sends a notification, running an inline shell check. From zebbern/termstack.
Settings file Claude Code
MCP configuration declaring 3 servers: filesystem, playwright, sequential-thinking.
Skill Claude CodeCodex
Find and fix a bug or issue — from any source (GitHub issue, error message, user report, or observed behavior).
Skill Claude CodeCodex
Review code changes or a pull request — delegates to specialist agents for code quality, security, performance, and documentation.
Skill Claude CodeCodex
Safely refactor code with test coverage as a safety net.
Skill Claude CodeCodex
Scan changes, commit, push, and create a PR — with confirmation at each step.
Skill Claude CodeCodex
Test-Driven Development loop — write a failing test first, then the minimum code to pass it, then refactor. Repeat.
Skill Claude CodeCodex
Write comprehensive tests for new or changed code. Use automatically when new features are added, functions are created, or behavior is modified.
Agent
Accessibility Reviewer — WCAG 2.2 AA compliance audit. Checks keyboard navigation, screen reader support, color contrast, and semantic HTML. Read-only — does not modify code.
Agent
Quality-first workflow coordinator. Clarifies intent, researches current guidance, uses discordask, discordembed, and discordnotify for user communication, and delegates the full lifecycle to subagents.
Agent
Architect — Produces the High-Level Design (HLD) and breaks the feature into sequenced, independent implementation tasks with detailed task plans.
Agent
Audit Expert — Cross-validates PRD, Figma design, and API contracts to surface gaps, contradictions, and missing requirements before planning begins.
Agent
Browser Tester — Test the live application from a user's perspective using browser automation. Starts servers, navigates the UI, validates user flows, takes screenshots, and reports findings.
Agent
Devil's Advocate plan reviewer. Reviews plans one-objection-at-a-time checking feasibility, gaps, risks, and edge cases. Produces end-game synthesis with resilience verdict.