Agent Codex
Use this agent when an assigned task changes the repository backend: Convex schema, domains, queries, mutations, actions, ownership checks, auth seams, billing seams, email seams, or frontend data contracts. Do not use it for interface composition or test-only work. Context: A feature contract says authenticated users…
Agent Codex
Use this agent when a task requires connecting, authorizing, provisioning, verifying, resuming, or disconnecting an external service such as Stripe, Convex, Resend, PostHog, or Netlify. Use it when browser consent or another human-only action must pause automation. Do not use it for product checkout behavior or for…
Agent Codex
Use this agent when an assigned task changes the product interface: routes, pages, sections, components, design tokens, fonts, motion, images, or client-side state. Do not use it for backend functions or test-only work. Context: A feature contract defines a new pricing route and supplies static plan data. user: "Build…
Agent Codex
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
Agent Codex
Use this agent when you need to debug and fix failing Playwright tests.
Agent Codex
Use this agent when you need to create comprehensive test plan for a web application or website.
Agent Codex
Use this agent when a request spans more than one implementation seam, begins as a product outcome rather than a bounded code task, or needs coordinated frontend, backend, connection, and verification work. Do not use it for a single already-bounded specialist task. Context: The repository has no implementation for…
Agent Codex
Use this agent when tests must be designed or implemented, when a repository gate is red, when a repair needs evidence and regression coverage, or when completed work needs independent verification. Do not use it to invent or expand product behavior. Context: A frontend and backend feature has been implemented with…
Skill Claude CodeCodex
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
Skill Claude CodeCodex
This skill should be used when the user asks to "configure Claude, Codex, Cursor, Hermes, or OpenClaw", "sync agent adapters", "check agent portability", "add an MCP server for every host", or diagnose why rules, skills, subagents, hooks, or OAuth-backed tools behave differently across AI coding hosts.
Skill Claude CodeCodex
When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for ChatGPT,' 'optimize for…
Skill Claude CodeCodex
Reverse-engineer a live website and rebuild it in the product stack — extraction-first, spec-driven, section by section. Use when the user wants to clone, replicate, rebuild, migrate, or closely follow an existing site or use one as the visual base for the product. Rights decide fidelity; the pipeline is the same…
Skill Claude CodeCodex
How Convex is structured inside Agentic Ship — file layout, function shape, naming, the data-access decision tree, and the auth seam. Use before writing any backend code, adding a table, or wiring a component to data.
Skill Claude CodeCodex
Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.
Skill Claude CodeCodex
Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
Skill Claude CodeCodex
Frontend security posture for AI-assisted projects — secret handling, supply chain, untrusted component code, prompt injection, XSS, response headers. Use before shipping, after adding dependencies, and whenever pasting code from a registry or the web.
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
Invoked by /plain-language. Reviews project text for plain-language compliance and produces structured findings with rewrites. Does not auto-activate on natural-language requests.
Skill Claude CodeCodex
Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation, permissions…
Skill Claude CodeCodex
Turn a product request into durable contracts, role-owned work, dependency-aware handoffs, human-input pauses, and evidence-backed completion. Use when starting a product, planning a feature, coordinating multiple agents, resuming work in another AI coding host, or replacing an ad-hoc prompt-only build loop.
Skill Claude CodeCodex
The go-live gate. Verify the selected billing provider is live, email leaves testMode with verification on, URLs are real, and no test-seed backdoor exists. Run before the first deploy and after any money, email, or auth change.
Skill Claude CodeCodex
When the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pages," "[keyword] + [city] pages," "comparison pages," "integration pages," "building many pages for SEO," "pSEO,"…
Skill Claude CodeCodex
When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured data," "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," "breadcrumb schema," "Google rich results," "knowledge panel,"…
Skill Claude CodeCodex
Security code review for vulnerabilities. Use when asked to "security review", "find vulnerabilities", "check for security issues", "audit security", "OWASP review", or review code for injection, XSS, authentication, authorization, cryptography issues. Provides systematic review with confidence-based reporting.