henryhawke

@henryhawke source repo

77 skills
0 followers
3 days ago last updated

▌
Review · henryhawke
Review code changes with the Bugbot or Security Review subagent.

0 installs
▌
Deploy To Vercel · henryhawke bundle
Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

0 installs
▌
React Best Practices · henryhawke bundle
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

0 installs
▌
Building MCP Server On Cloudflare · henryhawke bundle
Builds remote MCP (Model Context Protocol) servers on Cloudflare Workers with tools, OAuth authentication, and production deployment. Generates server code, configures auth providers, and deploys to Workers. Use when: user wants to "build MCP server", "create MCP tools", "remote MCP", "deploy MCP", add "OAuth to MCP", or mentions Model Context Protocol on Cloudflare. Also triggers on "MCP authentication" or "MCP deployment". Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

0 installs
▌
Update Cursor Settings · henryhawke
Modify Cursor/VSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.

1 install
▌
Workflow Orchestration · henryhawke bundle
Use for designing durable workflows with Temporal Python SDK, implementing saga patterns, distributed transactions, and long-running processes. Covers workflow vs activity separation, state management, testing strategies, and production deployment.

1 install
▌
Subject Systems Auditor · henryhawke bundle
End-to-end audit for one explicit subject (service, feature, workflow, API, system idea, or capability) across every system touchpoint. Use when a user asks to audit/review/assess one subject for bugs, regressions, security gaps, performance or cost issues, architecture risks, missing tests, operational gaps, and concrete optimization or innovation opportunities.

1 install
▌
Supabase Edge Functions · henryhawke
Use for creating, deploying, debugging, and optimizing Supabase Edge Functions. Covers Deno runtime, request handling, auth validation, CORS, shared utilities, service-based architecture, and the deploy_edge_function MCP tool.

1 install
▌
UI Component Spec Build · henryhawke
Produce a compact component spec plus modular implementation guidance for React or TypeScript UI work. Use when Codex needs to design or build a component, page section, or frontend feature with explicit accessibility, responsiveness, state, testing, and maintainability requirements.

1 install
▌
State Data Orchestration · henryhawke
Design state boundaries, reducers, failure modes, and error-boundary placement for complex UI features. Use when Codex needs to reason about local state, shared state, server data, URL state, optimistic updates, or resilience before implementation.

1 install
▌
Design Fwf Toxic Candy UI · henryhawke bundle
Design, critique, mock up, or implement Fart With Friends mobile UI in the polished Toxic Candy Arcade visual system. Use for FWF screen redesigns, Flutter UI work, image mockups, design-system decisions, interaction states, component styling, motion direction, or visual QA that should preserve the app's real navigation, privacy, audio, map, inbox, Saved, onboarding, and profile contracts.

2 installs
▌
Git Advanced Workflows · henryhawke
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

1 install
▌
Update CLI Config · henryhawke
View and modify Cursor CLI configuration settings in ~/.cursor/cli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.

1 install
▌
Accessibility Gate · henryhawke
Run a testable accessibility review with WCAG mapping, keyboard and focus analysis, and semantic or ARIA remediation guidance. Use when Codex needs to audit a page or component and produce a formal accessibility gate instead of generic UX feedback.

1 install
▌
Responsive Theming · henryhawke
Design responsive layouts, breakpoints, tokens, and preference-aware styling strategies for UI surfaces. Use when Codex needs a responsive or themed UI plan with explicit layout shifts, media-query behavior, and viewport test coverage.

1 install
▌
Security Hardening · henryhawke
Generate threat-driven hardening plans with control mapping, header strategy, and CI verification steps. Use when Codex needs a practical security posture for frontend, backend, or full-stack work with explicit assumptions, controls, and validation.

1 install
▌
Openai Docs · henryhawke bundle
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, latest/current/default-model prompting guidance, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.

1 install
▌
Supabase Migrations · henryhawke
Use for Supabase database migrations including schema changes, triggers, functions, indexes, RLS policies, pg_cron jobs, and PostGIS spatial setup. Covers the apply_migration MCP tool, zero-downtime strategies, and migration best practices.

1 install
▌
Systems Programming · henryhawke bundle
Use for Go (goroutines, channels, generics), Rust (async/Tokio, ownership, lifetimes), C++ (modern features, RAII, templates), and C (memory management, system calls, embedded) development. Covers concurrency patterns, memory safety, and performance optimization.

1 install
▌
Cloud Infrastructure · henryhawke bundle
Use for cloud architecture on AWS/Azure/GCP, Terraform/OpenTofu IaC, Kubernetes/GitOps, service mesh (Istio/Linkerd), hybrid/multi-cloud strategies, networking, cost optimization, and security. Covers serverless, microservices deployment, and compliance.

1 install
▌
Performance Budgeter · henryhawke
Create measurable performance budgets, Core Web Vitals targets, and verification plans for web surfaces. Use when Codex needs a concrete performance plan with remediation priorities instead of vague optimization advice.

1 install
▌
Two Axis Code Review · henryhawke bundle
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

1 install
▌
Architecture Adr Pack · henryhawke
Produce durable architecture artifacts such as ADRs, C4-style diagrams, API semantics notes, and implementation roadmaps. Use when Codex needs to formalize system design decisions instead of only describing architecture informally.

1 install
▌
CI Pipeline Generator · henryhawke
Generate minimal but complete CI pipelines with explicit quality gates, caching, and failure behavior. Use when Codex needs to author or review GitHub Actions or similar pipelines for linting, typechecking, tests, security checks, or deployment readiness.

1 install
▌
I18N Locale Readiness · henryhawke
Prepare UI work for translation, locale formatting, pluralization, and multilingual edge cases. Use when Codex needs a stable i18n plan, ICU-style messages, Intl formatting guidance, or locale-readiness review before shipping UI copy.

1 install
▌
Javascript Typescript · henryhawke bundle
Use for JavaScript ES6+ development, TypeScript advanced types, Node.js backend patterns, async/await, promises, testing with Jest/Vitest, and modern tooling. Covers generics, conditional types, mapped types, and enterprise patterns.

1 install
▌
Refactor Without Fear · henryhawke
Plan and execute behavior-preserving refactors with explicit invariants, checkpoints, and verification steps. Use when Codex needs to improve maintainability or structure without silently changing externally visible behavior.

1 install
▌
Architecture Optimizer · henryhawke
Review and optimize codebases for scalability, cost efficiency, and architectural coherence. Use when you need to identify disconnected code patterns, ensure UI components integrate seamlessly, verify end-to-end implementations, reduce backend costs, or audit features for cohesion. Triggers include architecture reviews, cost optimization requests, integration audits, and scalability analysis.

1 install
▌
Sisyphus · henryhawke
Continuously diagnoses and fixes CI, build, and deployment failures one candidate at a time, then commits, pushes to the deployment branch, and monitors each authorized attempt until the requested remote deployment is green or genuinely blocked. Use when the user invokes Sisyphus or asks to keep fixing GitHub Actions, Cloud Build, Cloud Run, or a similar deployment without retry churn; a local branch or local pass is never the terminal result.

1 install
▌
Supabase · henryhawke
Use for Supabase platform development including project management, database queries, auth configuration, storage, realtime channels, Edge Functions deployment, branching, and MCP tool usage. Covers Flutter/Dart client, JavaScript client, PostgREST, and Supabase CLI patterns.

1 install
▌
Debugging · henryhawke bundle
Use when debugging errors, crashes, test failures, unexpected behavior, performance issues, or production incidents. Covers systematic root cause analysis, Flutter debugging, Edge Function debugging, log analysis, git bisect, and common failure patterns.

1 install
▌
Env Setup · henryhawke
Explain, inspect, configure, and troubleshoot Cloud Agent development environments. Use when the user asks about environment setup or changing/improving the environment.

1 install
▌
Auctioneer · henryhawke bundle
Runs bounded MrMaple Auctions bot-arena, Auction Doctor, and storefront realtime QA using a Ralph-style evidence loop and logical razors to isolate root causes and produce regression-tested fixes. Use only when the user invokes /auctioneer or explicitly asks to exercise auction bots, diagnose bid services, investigate auction failures, or verify frontend bid convergence.

1 install
▌
Statusline · henryhawke
Configure a custom status line in the CLI. Use when the user mentions status line, statusline, statusLine, CLI status bar, prompt footer customization, or wants to add session context above the prompt.

1 install
▌
Streamline · henryhawke bundle
Diagnose, redesign, implement, and validate end-to-end product workflows across web, mobile, desktop, admin, dashboard, settings, forms, onboarding, operations, and multi-role services. Use when asked to simplify a workflow, reduce unnecessary effort, improve findability, consolidate scattered actions, remove duplicate work, clarify navigation or state, improve recovery, accelerate expert work, or make an agent-built interface intentional, accessible, resilient, and measurably easier to complete correctly.

3 installs
▌
Code Review · henryhawke bundle
Use when reviewing code changes, PRs, or doing quality analysis. Covers security vulnerability detection, performance analysis, architectural review, Flutter/Dart patterns, Edge Function patterns, and actionable feedback with confidence-based filtering.

1 install
▌
Content SEO · henryhawke bundle
Use for SEO optimization, content strategy, keyword research, meta tag optimization, featured snippet targeting, content auditing, E-E-A-T signals, schema markup, and content marketing across channels.

1 install
▌
Create Hook · henryhawke
Create Cursor hooks. Use when you want to create a hook, write hooks.json, add hook scripts, or automate behavior around agent events.

1 install
▌
Create Rule · henryhawke
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.

1 install
▌
Iterate Code · henryhawke
Codebase-only Ralph loop — decompose an objective into small verifiable work units, complete and verify them one per iteration with evidence-first discipline, and track both progress and the meta of the run (velocity, stuck patterns, drift) in a persistent ledger. Use when asked to /iterate-code, grind through a backlog/plan, or autonomously work a codebase to completion without a UI/simulator.

1 install
▌
Split To Prs · henryhawke
Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.

1 install
▌
Supabase Rls · henryhawke
Use for designing and implementing Supabase Row Level Security (RLS) policies. Covers policy patterns for CRUD operations, auth integration, role-based access, multi-tenant isolation, performance optimization, and security auditing with get_advisors.

1 install
▌
Web Optimize · henryhawke bundle
Audit, diagnose, prioritize, implement, and validate total web quality across performance, Core Web Vitals (LCP, INP, CLS), accessibility and WCAG 2.2, technical and on-page SEO, and browser best practices. Use for requests to audit or optimize a website, page, route, storefront, or web app; improve Lighthouse or PageSpeed results; speed up loading or interactions; fix layout shifts; review keyboard, screen-reader, contrast, forms, or ARIA behavior; inspect crawlability, metadata, canonicals, sitemaps, structured data, or international SEO; or produce an evidence-backed remediation plan spanning these areas.

1 install
▌
Documentation · henryhawke bundle
Use for technical documentation generation including API docs (OpenAPI 3.1), architecture guides, tutorials, reference materials, ADRs, changelogs, and Mermaid diagrams. Creates comprehensive docs from existing codebases.

1 install
▌
Observability · henryhawke bundle
Use for application performance optimization, OpenTelemetry, distributed tracing (Jaeger/Tempo), metrics (Prometheus), dashboards (Grafana), SLI/SLO implementation, load testing, caching strategies, and Core Web Vitals optimization.

1 install
▌
Review Bugbot · henryhawke
Review code changes with Bugbot subagent.

1 install
▌
Verify Fwf UI · henryhawke bundle
Validate Fart With Friends Flutter UI changes against canonical visual, interaction, accessibility, privacy, consent, map, audio, reaction, and shell-navigation contracts. Use for UI review, pre-merge verification, regression testing, mockup-to-code comparison, or auditing a screen's loading, empty, error, offline, reduced-motion, and microinteraction states.

1 install
▌
Security Audit · henryhawke bundle
Use for security audits, vulnerability assessment, OWASP Top 10 checks, Supabase RLS verification, Edge Function auth review, secret scanning, dependency auditing, and DevSecOps pipeline setup. Covers both manual review and automated scanning.

1 install
▌
Cicd Deployment · henryhawke bundle
Use for CI/CD pipeline design, GitHub Actions, GitLab CI, ArgoCD/Flux GitOps, progressive delivery, container security, zero-downtime deployments, secrets management, and deployment automation.

1 install
▌
Create Subagent · henryhawke
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.

1 install
▌
Review Security · henryhawke
Review code changes with Security Review subagent.

1 install
▌
Skill Harvester · henryhawke
Extract normalized, evidence-backed skill records from code, diffs, architecture docs, tests, tickets, screenshots, or meeting notes. Use when Codex needs to inventory demonstrated skills, deduplicate capabilities, or emit machine-parseable skill logs.

1 install
▌
Task Management · henryhawke bundle
Use for coordinating development tasks, breaking down features into implementation steps, managing dependencies between tasks, tracking progress, and integrating with Task Master AI and Linear for project management.

1 install
▌
Code Refactoring · henryhawke bundle
Use when the user wants to refactor code, modernize legacy codebases, migrate frameworks, reduce technical debt, or update dependencies. Handles backward compatibility and gradual modernization strategies.

1 install
▌
Implement Fwf UI · henryhawke bundle
Implement or refactor Fart With Friends Flutter screens, widgets, themes, interaction states, audio/reaction capture, Fart Map filtering, shell navigation, and accessibility according to the canonical FWF UI system. Use for code changes under lib/presentation or lib/core/theme and for translating approved Toxic Candy mockups into production Flutter without breaking privacy, consent, offline, or route contracts.

1 install
▌
Test Author Gate · henryhawke
Design user-centered unit, integration, and e2e test plans with coverage and anti-flake gates. Use when Codex needs to write or review a test strategy that spans levels, risk areas, CI reliability, and measurable pass criteria.

1 install
▌
Dev Server Healer · henryhawke bundle
Start or repair a local dev server by looping: start server, wait for logs, extract errors, fix issues, restart until clean, then open the local URL. Use when asked to run a dev server, debug startup/runtime errors, or keep restarting until it runs without errors.

1 install
▌
Incident Response · henryhawke bundle
Use for production incident response, outage triage, root cause analysis, blameless post-mortems, runbook creation, and SRE practices. Covers Supabase-specific debugging (Edge Function failures, database issues, auth problems), log analysis, and incident communication.

1 install
▌
Migrate To Skills · henryhawke
Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when you want to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.

1 install
▌
Shopify App Ralph · henryhawke bundle
Run a bounded Ralph-style implementation loop over a Shopify app's backend, embedded admin, app proxy, and theme app extension using `shopify app dev` and the Codex in-app Browser. Use when the user explicitly invokes `$shopify-app-ralph` or asks Codex to iteratively build, debug, or polish Shopify app frontend/backend behavior against a local dev server and development-store preview without waiting for a production or Cloud Run deploy.

1 install
▌
Loop · henryhawke
Run a prompt or skill in this session on a recurring or variable interval (e.g. /loop 5m /foo).

1 install
▌
Opium · henryhawke bundle
Read-only, repository-wide completion and readiness auditing that reconciles canonical requirements with current source, tests, migrations, CI, deployment, and operational evidence. Use when the user invokes /opium or $opium, asks whether a codebase is complete, requests an exhaustive gap/readiness analysis, wants the latest ten verification runs audited for totality, needs an evidence-backed critical path, or asks to create or adapt a completion-audit prompt without executing it.

3 installs
▌
Shell · henryhawke
Runs the rest of a /shell request as a literal shell command. Use only when the user explicitly invokes /shell and wants the following text executed directly in the terminal.

1 install
▌
AI LLM · henryhawke bundle
Use for LLM application development, RAG systems, prompt engineering, AI agent orchestration, vector databases, embedding strategies, similarity search, LangChain architecture, LLM evaluation, and AI context management.

1 install
▌
Canvas · henryhawke bundle
A Cursor Canvas is a live React app that the user can open beside the chat. You MUST use a canvas when the agent produces a standalone analytical artifact — quantitative analyses, billing investigations, security audits, architecture reviews, data-heavy content, timelines, charts, tables, interactive explorations, repeatable tools, or any response that benefits from visual layout. Especially prefer a canvas when presenting results from MCP tools (Datadog, Databricks, Linear, Sentry, Slack, etc.) where the data is the deliverable — render it in a rich canvas rather than dumping it into a markdown table or code block. If you catch yourself about to write a markdown table, stop and use a canvas instead. You MUST also read this skill whenever you create, edit, or debug any .canvas.tsx file.

1 install
▌
Mobile · henryhawke bundle
Use for Flutter/Dart mobile development including widget architecture, Riverpod state management, Freezed models, GoRouter navigation, offline-first patterns, platform channels, audio/camera/location services, and App Store/Play Store submission. Also covers React Native and native iOS with SwiftUI.

1 install
▌
Babysit · henryhawke
Keep a PR merge-ready by triaging comments, resolving clear conflicts, and fixing CI in a loop.

1 install
▌
Backend · henryhawke bundle
Use for backend API development including Supabase Edge Functions (Deno), REST API design, request/response patterns, auth middleware, error handling, input validation, CORS, rate limiting, and service-based architecture. Covers both Deno/TypeScript (Supabase) and Node.js/Python backends.

1 install
▌
Hal9000 · henryhawke bundle
This skill should be used when the user invokes `$hal9000`, asks to "autonomously improve this repository", "find and do the next valuable engineering work", "act as a solution architect", or requests a persistent repository orchestrator that discovers, implements, and verifies meaningful capability rather than waiting for one predefined task.

1 install
▌
Iterate · henryhawke
Ralph-style simulator iteration loop — build the app, drive every screen/flow in the iOS Simulator (signup, sign-in, friends, sends, listen/reaction, map, saved, profile, settings), screenshot and evaluate each against the product contract, fix the worst finding, rebuild, and repeat until the checklist is genuinely green. Use when asked to /iterate, iterate on screens/UX in the simulator, or visually polish the app end to end.

1 install
▌
Onboard · henryhawke
Use /onboard for a focused Cursor onboarding flow that learns basic preferences, picks a first goal, and routes the user to the right next action.

1 install
▌
Testing · henryhawke bundle
Use for test strategy design, writing unit/integration/e2e tests, TDD workflows, test debugging, and CI/CD test integration. Covers Flutter testing (widget tests, golden tests, integration tests), Bun test runner, pytest, Jest/Vitest, and Playwright. Includes framework-specific patterns and test debugging.

1 install
▌
Ask Matt · henryhawke bundle
Ask which skill or flow fits your situation. A router over the skills in this repo.

1 install
▌
Automate · henryhawke
Use this skill to create Cursor Automations.

1 install
▌
Database · henryhawke bundle
Use for PostgreSQL schema design, query optimization, indexing strategies (B-tree/GIN/GiST/BRIN), EXPLAIN analysis, N+1 resolution, materialized views, partitioning, PostGIS spatial queries, triggers, pg_cron, and database migration planning. Covers Supabase-specific patterns including RLS and cost optimization.

1 install
▌
Frontend · henryhawke bundle
Build, refactor, debug, and review web UI in React, Next.js, Vite, Tailwind, CSS Modules, and design-system-driven applications. Use when Codex needs to implement or refine components, pages, forms, navigation, responsive layouts, client-side state, loading or error or empty states, frontend performance, accessibility, or visual polish while preserving or intentionally evolving an existing product's patterns.

1 install
▌
Sdk · henryhawke
Guide users building apps, scripts, CI pipelines, or automations on top of the Cursor SDK - TypeScript (`@cursor/sdk`) or Python (`cursor-sdk` / `cursor_sdk`). Use when the user mentions integrating, installing, or writing code against the Cursor SDK; says `Agent.create`, `Agent.prompt`, `Agent.resume`, `agent.send`, `run.stream`, `run.messages`, `CursorAgentError`, `@cursor/sdk`, `cursor-sdk`, or `cursor_sdk`; asks to run Cursor agents programmatically from a script, CI/CD pipeline, GitHub Action, backend service, or other code outside the Cursor IDE; wants to pick between local and cloud runtime, configure MCP servers for an SDK agent, or handle streaming, cancellation, or errors; or is wiring Cursor into an automation, bot, or REST `/v1/agents` migration. Use eagerly rather than answering from memory; the SDK surface evolves and this skill is the source of truth for the external packages.

1 install

77 published skills