OpenRouter for agents and sandbox environments. Provides a control plane and configuration options for persistent agent workers. Route runtime + substrates, provision specialist presets, and supervise your fleet.
Skill Claude CodeCodex
Browser automation patterns via the browser tools (Playwright). Use when the user asks me to navigate a website, fill a form, scrape data, or test a UI flow.
Skill Claude CodeCodex
Comprehensive self-promotion and content strategy covering positioning arcs, content calendars, weekly rhythms, and quality gates for X and LinkedIn. Use when planning content, discussing personal brand, building a content calendar, or when the user says "content strategy", "what should I post", "content plan", or…
Skill Claude CodeCodex
Marketing copy for homepages, landing pages, pricing pages, and conversion-focused web pages. Use when writing headlines, CTAs, landing page copy, pricing page copy, feature pages, or when the user says "write copy", "landing page", "homepage copy", "CTA", "headline", "conversion copy", or "marketing copy." Based on…
Skill Claude CodeCodex
Compare the current implementation against the minimal correct algorithm. Use when debugging regressions, reviewing complex fixes, or when the user asks what should happen versus what is happening now.
Skill Claude Code
Create Cursor hooks. Use when you want to create a hook, write hooks.json, add hook scripts, or automate behavior around agent events.
Skill Claude CodeCodex
Create Cursor rules for persistent AI guidance. Use when you want to create a rule, add coding standards, set up project conventions, configure file-specific patterns, create RULE.md files, or asks about .cursor/rules/ or AGENTS.md.
Skill Claude CodeCodex needs its repo
Create Cursor Agent Skills. Use when authoring a new skill or asking about SKILL.md structure.
Skill Claude Code
Create custom subagents for specialized AI tasks. Use when you want to create a new type of subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants with custom prompts.
Skill Claude CodeCodex
Quality gate via a second AI model. Spawn a different model to review work before committing. Grades against the originating skill's Contract. Use when you want a second opinion from a different model, or the user says "second opinion", "cross-modal review", "double check this", or "get another perspective".
Skill Claude CodeCodex
Check the current author's commits from the last 24 hours and proactively find and fix any bugs they introduced. Use when the user asks for a daily bugfix check, wants to review today's commits for issues, or asks to "check my recent code for bugs." Combines commit review with the recent-code-bugfix workflow.
Skill Claude Code
Run mutating SQL (INSERT, UPDATE, DELETE, DDL) against Supabase databases. Requires explicit user invocation. Use for migrations, seed data, schema changes, or data fixes.
Skill Claude Code
Run read-only SQL queries against Supabase databases (local or remote). Use when inspecting schema, debugging data, checking migrations, or answering questions about database state.
Skill Claude Code needs its repo
Run DCS test profiles against controlplane (Go), host-agent (Rust), storage-daemon, or live clusters. Use when testing DCS changes locally or triggering CI test suites.
Skill Codex
How Agent Machines work -- providers (Dedalus, E2B, Sprites), agent runtimes (Hermes, OpenClaw, Claude Code, Codex), MCP catalog, bootstrap, and closed-loop verification. Use when asked about the runtime, scaling, sleep/wake, destroy, or inspecting this environment.
Skill Claude CodeCodex
Run vercel-labs/deepsec — an agent-powered vulnerability scanner — against any local codebase. Use when Kevin says "deepsec", "security scan", "scan this repo for vulns", "find security bugs in ", "audit for vulnerabilities", "production security review", or before shipping a new service. Performs a regex pre-scan…
Skill Claude CodeCodex
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
Skill Claude CodeCodex
Design audit with UX usability tests. Adapted from GStack's /design-review (Garry Tan, github.com/garrytan/gstack) for Cursor + agent-browser. 6-phase audit: first impression, design system extraction, page-by-page visual audit with 80-item checklist, interaction flow review with goodwill tracking, cross-page…
Skill Claude CodeCodex
Auto-run the relevant codebase doctor(s) after large edit sessions or before committing. Detects which subsystems were touched and runs the matching doctor. Use when the agent has completed a significant edit (5+ files), before claiming work is done, or when the user says "run doctors", "health check", "doctor pass"…
Skill Claude Code
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -…
Skill Claude Code
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include…
Skill Claude CodeCodex
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great. Use when reviewing animation decisions, component polish, or motion design, or when the user says "Emil", "animation review", "component polish", "motion details"…
Skill Claude CodeCodex
Scientific method for software. Use when debugging, reviewing surprising behavior, or before claiming code works -- always tether assumptions to reality with a small experiment.
Skill Claude Code
Compare implementation against canonical open-source references. Clone exemplars into /tmp, diff edge cases, error paths, and protocol invariants. Use when building a new subsystem, after a refactor, or when reviewing code that implements a known standard (POSIX, FUSE, WAL, S3, NFS, etc.).
Skill Claude CodeCodex
Dedalus philosophy on conditional logic, error paths, and why we never write fallbacks. Use when writing or reviewing any branching logic that selects between strategies, modes, or error-recovery paths.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: