bzellman
35 verified skills
atlas
macOS-only AppleScript control for the ChatGPT Atlas desktop app. Use only when the user explicitly asks to control Atlas tabs/bookmarks/history on macOS and the "ChatGPT Atlas" app is installed; do not trigger for general browser tasks or non-macOS environments.
testing
openai-docs
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains.
tools
self-healing-deploy
Self-healing merge-to-production pipeline. Use when the user approves a PR for merge, says "ship it", "deploy this", "merge and deploy", "take this to prod", or wants to promote code through environments. Handles CI monitoring, failure analysis and auto-fix, DB migrations, terraform apply, and progressive deployment (dev -> staging -> prod) with health verification at each stage. Also triggers for partial invocations like "promote to staging", "deploy to prod", "run migrations", or "check deploy status".
development
ios-design
Design and implement SwiftUI interfaces for <YOUR_APP> iOS app with design system compliance, Apple HIG principles, and visual references. Triggers when creating UI components, screens, or discussing iOS design. Gathers design library preferences, screenshot references, and requirements before implementation.
development
self-healing-deploy
Self-healing merge-to-production pipeline. Use when the user approves a PR for merge, says "ship it", "deploy this", "merge and deploy", "take this to prod", or wants to promote code through environments. Handles CI monitoring, failure analysis and auto-fix, DB migrations, terraform apply, and progressive deployment (dev -> staging -> prod) with health verification at each stage. Also triggers for partial invocations like "promote to staging", "deploy to prod", "run migrations", or "check deploy status".
development
<YOUR_IOS_BUILD>
Run <YOUR_APP> iOS builds and simulator tests through FULLSTACK_SCRIPTS/build-ios-formatted.sh and format-build-log.py. Use for build verification, test verification, or xcodebuild failure analysis when working in this repo.
development
dead-code-cleanup
Safely find and remove dead code from Swift files using an isolated git worktree. Creates a branch, runs analysis with build verification, and generates a report for review before merge.
development
customize
Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).
testing
triage
Use when the user provides multiple loosely-described items (bugs, features, ideas, fixes) in a single message and wants each researched against the codebase, classified, and turned into a GitHub issue. Handles batch input of mixed-type work items.
development
gh-fix-ci
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.
development
figma
Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.
tools
senior-architect
Comprehensive software architecture skill for designing scalable, maintainable systems across web, mobile, and backend stacks (React, Next.js, Node/Express, React Native, Swift, Kotlin, Flutter, Postgres, GraphQL, Go, Python). Use when designing system architecture, making technical decisions, creating architecture diagrams, evaluating trade-offs, or defining integration patterns.
development
security-threat-model
Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.
development
remotion-best-practices
Best practices for Remotion - Video creation in React
development
pr-handoff-to-codex
Use when a PR is ready for senior architect review and autonomous fix-up by Codex CLI. Uses adversarial counsel (3 specialized reviewers + 1 orchestrator) for comprehensive coverage. Gathers PR URL, GitHub issue URL, project standards, and build/test commands.
tools
preset
Intelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions. Automatically checks current region first and shows alternatives if needed. USE FOR: quick deployment, optimal region, best region, automatic region selection, fast setup, multi-region capacity check, high availability deployment, deploy to best location. DO NOT USE FOR: custom SKU selection (use customize), specific version selection (use customize), custom capacity configuration (use customize), PTU deployments (use customize).
testing
prd-to-pr
End-to-end pipeline from PRD to merged PR. Chains /prd-taskmaster → /shape-spec → plan refinement counsel (Opus 4.6 + Codex 5.4 extra high) → multi-agent implementation → /simplify → /pr-handoff-to-codex with adversarial review → Copilot feedback review → /self-healing-deploy. Use when user wants the full pipeline: "build this feature", "PRD to PR", "end to end".
development
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
development
dead-code-cleanup
Safely find and remove dead code from Swift files using an isolated git worktree. Creates a branch, runs analysis with build verification, and generates a report for review before merge.
development
prd-taskmaster
PRD generator that creates comprehensive requirements, publishes as a GitHub issue, and triggers /agent-os:shape-spec for orchestrated execution. No deferred scope — every requirement is a must-deliver. Use when user requests "PRD", "product requirements", or wants to plan a feature for implementation.
data-ai
microsoft-foundry
Deploy, evaluate, and manage Foundry agents end-to-end: Docker build, ACR push, hosted/prompt agent create, container start, batch eval, prompt optimization, prompt optimizer workflows, agent.yaml, dataset curation from traces. USE FOR: deploy agent to Foundry, hosted agent, create agent, invoke agent, evaluate agent, run batch eval, optimize prompt, improve prompt, prompt optimization, prompt optimizer, improve agent instructions, optimize agent instructions, optimize system prompt, deploy model, Foundry project, RBAC, role assignment, permissions, quota, capacity, region, troubleshoot agent, deployment failure, create dataset from traces, dataset versioning, eval trending, create AI Services, Cognitive Services, create Foundry resource, provision resource, knowledge index, agent monitoring, customize deployment, onboard, availability. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).
development
ios-simulator-skill
21 production-ready scripts for iOS app testing, building, and automation. Provides semantic UI navigation, build automation, accessibility testing, and simulator lifecycle management. Optimized for AI agents with minimal token output.
tools
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
data-ai
capacity
Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.
testing
bug-to-pr
End-to-end pipeline from bug report to merged fix PR. Chains bug triage & reproduction → root cause analysis → fix strategy counsel (Opus 4.6 + Codex 5.4 extra high) → targeted implementation → /simplify → /pr-handoff-to-codex with adversarial review → Copilot feedback review → /self-healing-deploy. Use when user reports a bug and expects a delivered fix: "fix this bug", "bug to PR", "debug and fix".
development
brand-guidelines
Applies <YOUR_APP>'s official brand colors and typography to any artifact. Use when brand colors, style guidelines, visual formatting, or company design standards apply.
development
brand-guidelines
Applies <YOUR_APP>'s official brand colors and typography to any artifact. Use when brand colors, style guidelines, visual formatting, or company design standards apply.
development
deploy-model
Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create).
tools
code-simplifier
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
development
chatgpt-apps
Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.
tools
install-tooling
Use when installing new skills or agents from curated lists or GitHub repositories, when the user says "install", "add skill", "add agent", or wants to set up new tooling in their Claude Code environment
tools
ios-design
Design and implement SwiftUI interfaces for <YOUR_APP> iOS app with design system compliance, Apple HIG principles, and visual references. Triggers when creating UI components, screens, or discussing iOS design. Gathers design library preferences, screenshot references, and requirements before implementation.
development
Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual checks by rendering pages (Poppler) and use Python tools such as `reportlab`, `pdfplumber`, and `pypdf` for generation and extraction.
tools
video-report
Generate a report about a video
business
workflow-orchestrator
Use when running 2+ /prd-to-pr or /bug-to-pr pipelines simultaneously, when user says "run these in parallel", "batch these PRDs/bugs", "orchestrate these workflows", or has multiple work items to ship end-to-end concurrently
devops