Jeremylongworth Source@AgentSkills

Plan, implement, debug, and review real-time 3D game development work. Use when Codex is asked to build or improve 3D gameplay, cameras, controllers, physics interactions, animation integration, spatial UI, scene architecture, composition/component architecture, performance, rendering, Three.js, Unity, Unreal, Godot, or custom-engine 3D systems.

Create, structure, balance, and review game content. Use when Codex is asked to design levels, missions, quests, encounters, enemies, items, rewards, progression, tutorials, puzzles, biomes, factions, economies, live-ops content, design docs, or playable content plans.

Design, audit, and improve lifecycle marketing, CRM segmentation, email campaigns, nurture flows, onboarding, retention, winback, lead scoring, consent, deliverability, CAN-SPAM-aware workflows, and customer communications. Use when Codex is asked about email marketing, lifecycle stages, CRM journeys, automation, or subscriber health.

Design creator sponsorship packages and deliverable bundles. Use when Codex is asked to create influencer sponsorship tiers, package options, deliverable menus, content bundle structures, add-ons, campaign options, or sponsor offer framing.

Review agent skill supply-chain risk. Use when Codex is asked to inspect third-party skill sources, dependencies, install commands, package managers, remote downloads, version pins, provenance, or update risks before installation or publication.

Explain variance between actuals, targets, forecasts, plans, prior periods, or cohorts. Use when Codex is asked to write finance commentary, explain budget or revenue variance, compare KPI actuals to plan, summarize month-over-month changes, or prepare variance notes for review.

Evaluate AI vendors, tools, platforms, and agent systems for executive decision support. Use when Codex is asked to compare AI vendors, draft vendor evaluation matrices, assess AI platform fit, prepare procurement questions, or review AI tool risk.

Create, adapt, and review AI video generation prompt packs for tools such as Gemini/Veo, Sora, Runway, Pika, Luma, and similar systems. Use when Codex is asked for video generation prompts, Shorts prompts, AI ad concepts, timing maps, scene prompts, negative prompts, voiceover/audio directions, reference-image guidance, or post-generation review criteria.

Plan, create, audit, and improve SEO and content marketing. Use when Codex is asked about helpful content, Google Search, E-E-A-T, topic clusters, editorial calendars, landing pages, keyword intent, on-page SEO, technical SEO basics, content briefs, organic acquisition, or content performance.

Design creator monetization offer ladders. Use when Codex is asked to map a creator's free, low-ticket, mid-ticket, premium, affiliate, membership, course, merch, coaching, community, or sponsor offers into a coherent revenue path.

Build creator sponsorship deliverables trackers and campaign status tables. Use when Codex is asked to track influencer sponsor deliverables, content due dates, draft status, approvals, links, usage rights, reporting dates, invoices, or campaign handoffs.

Plan, create, optimize, import, export, and review game-ready 3D assets. Use when Codex is asked to work on props, environment pieces, modular kits, materials, textures, LODs, collision, pivots, scale, naming, asset budgets, Unity/Unreal/Godot imports, or production handoff for 3D game assets.

Design, build, repair, and review 3D models for games. Use when Codex is asked about mesh construction, topology, retopology, UV unwrapping, normals, bevels, baking, hard-surface modeling, organic modeling, sculpt-to-low-poly workflows, deformation, rig-readiness, or model cleanup.

Repurpose creator content into newsletters or turn newsletters into social content. Use when Codex is asked to write a newsletter version, email intro, subject lines, creator digest, social-to-newsletter adaptation, or newsletter-to-social repurposing plan.

Create pitch deck structures and slide-by-slide outlines for startup fundraising. Use when Codex is asked for a pitch deck outline, seed deck structure, Series A deck flow, investor deck story, slide titles, speaker notes, or deck gap review.

Create creator publishing checklists for social posts, videos, newsletters, podcasts, sponsored content, and campaigns. Use when Codex is asked to prepare a pre-publish QA checklist, review captions, assets, disclosures, links, tags, metadata, or post-launch checks.

Score agent skill outputs with a rubric. Use when Codex is asked to evaluate a skill output, compare outputs, apply a quality rubric, summarize reviewer scoring, or decide whether a skill output is good enough to promote.

Generate or plan focused unit tests for functions, modules, components, and services. Use when Codex is asked to add unit tests, improve unit coverage, define test cases, create fixtures, or guard logic changes with small deterministic tests.

Prepare provider-neutral AI media prompt briefs for creator image, video, audio, voiceover, thumbnail, b-roll, and batch content workflows. Use when Codex is asked to turn a creator concept into AI media prompt packs with creative intent, format, source references, constraints, exclusions, rights/provenance notes, acceptance criteria, and human-review gates without using provider-specific syntax or executing generation.

Build and review AI use-case portfolios for executives and transformation leads. Use when Codex is asked to inventory AI opportunities, map business use cases, score AI initiatives, compare automation candidates, or create an AI opportunity map.

Maintain changelogs for software, skillsets, libraries, and documentation projects. Use when Codex is asked to update CHANGELOG.md, normalize entries, add unreleased changes, prepare a version section, or keep release history consistent.

Plan containerization for apps, services, jobs, and development environments. Use when Codex is asked to create or review Dockerfiles, container images, compose files, runtime users, build layers, healthchecks, ports, volumes, or container security.

Prepare creator sponsorship negotiation plans. Use when Codex is asked to prepare influencer deal negotiation points, counteroffer notes, tradeoffs, concession plans, sponsor objection responses, or partnership terms for manager or creator review.

Shape fundraising narratives for startup founders. Use when Codex is asked to create a seed or Series A narrative, founder pitch story, investor positioning, raise thesis, traction story, market narrative, or fundraising memo for review.

Create, critique, and refine game characters for visual clarity, gameplay readability, story role, and production readiness. Use when Codex is asked to design playable characters, NPCs, enemies, creatures, costumes, silhouettes, shape language, factions, abilities, personality, character sheets, or 3D character production notes.

Plan integration tests across modules, APIs, databases, queues, services, and external dependencies. Use when Codex is asked to test interactions, persistence, contracts, adapters, or dependency boundaries beyond unit tests.

Review operational bottlenecks for owners, agencies, and small business operators. Use when Codex is asked to find operational constraints, map workflow bottlenecks, prioritize process fixes, review staffing or delegation constraints, or create an owner operations action plan.

Plan performance tests for frontend, backend, APIs, databases, jobs, and releases. Use when Codex is asked to define load tests, latency checks, Core Web Vitals, throughput, memory, query performance, or performance regression gates.

Review pricing and margin for owners, agencies, service businesses, and small operators. Use when Codex is asked to analyze pricing, margin pressure, discounting, package economics, service profitability, or owner pricing action options.

Create YouTube and video thumbnail/title creative briefs. Use when Codex is asked to write title packs, thumbnail concepts, visual contrast notes, curiosity gaps, A/B test ideas, or title-thumbnail alignment checks.

Prepare customer success account health reviews, renewal risk summaries, QBR briefs, onboarding/adoption plans, expansion signals, and customer success action plans. Use when Codex is asked about account health, customer retention risk, usage adoption, renewal readiness, customer value reviews, success plans, QBRs, or post-sale customer follow-up.

Review database schemas for backend applications and APIs. Use when Codex is asked to critique tables, migrations, indexes, constraints, relationships, tenant boundaries, data integrity, query fit, or schema evolution risk.

Turn successful pilots into governed scale roadmaps. Use when Codex is asked to move an AI pilot to production, create a pilot-to-scale roadmap, define scaling gates, summarize pilot learnings, or plan rollout from experiment to business value.

Produce safe install recommendations for agent skills and skillsets. Use when Codex is asked whether a skill is safe to install, how to install with least privilege, what to inspect before install, or what approval conditions are required.

Design lightweight benchmarks for agent skills and skillsets. Use when Codex is asked to prove whether a skill improves outputs, define benchmark scenarios, compare baseline versus skill-enabled behavior, or create a skill evaluation plan.

Build, audit, and refactor Tailwind CSS interfaces and design systems. Use when Codex is asked about Tailwind classes, component variants, utility consistency, tokens, theme variables, responsive patterns, class detection, dynamic class issues, production CSS size, design-system enforcement, or Tailwind UI polish.

Review creator sponsorship usage-rights questions and checklist items. Use when Codex is asked to identify influencer usage rights, paid media usage, whitelisting, licensing, exclusivity, term length, territory, ownership, brand approvals, or rights questions for counsel or manager review.

Plan accessibility tests for web, app, game, document, and workflow experiences. Use when Codex is asked to define keyboard, screen reader, contrast, focus, ARIA, reduced motion, captions, forms, or WCAG-oriented validation.

Design, run, and audit account-based marketing for high-value B2B accounts. Use when Codex is asked about ABM strategy, target account selection, buying committees, account tiers, 1:1/1:few/1:many plays, sales-marketing alignment, personalization, account engagement, enterprise campaigns, expansion, or named-account pipeline.

Create AI governance checklists and readiness reviews for GenAI, agentic AI, and AI-enabled workflows. Use when Codex is asked to define AI governance, policy controls, model/data governance, review gates, responsible AI checklist, or AI rollout readiness.

Compare baseline and skill-enabled agent outputs. Use when Codex is asked to run, simulate, or document a before/after skill evaluation, decide whether a skill improved an output, or write a skill evaluation report.

Prepare draft diligence responses and diligence FAQs for startup fundraising. Use when Codex is asked to answer investor diligence questions, create a diligence FAQ, prepare response drafts, organize evidence, identify risky claims, or route diligence questions to owners.

Prepare finance close and reporting checklists from supplied policies and close context. Use when Codex is asked to draft a month-end close checklist, reporting package checklist, reconciliation checklist, finance handoff, or close readiness summary for review.

Design, implement, debug, and review multiplayer game systems. Use when Codex is asked about client/server architecture, authoritative servers, listen servers, dedicated servers, peer-to-peer, replication, prediction, interpolation, rollback, lag compensation, matchmaking, lobbies, sessions, state synchronization, netcode, anti-cheat risk, network testing, Unity Netcode, Unreal networking, Godot multiplayer, or custom multiplayer backends.

Build, debug, optimize, and review 2D HTML5 games with Phaser. Use when Codex is asked about Phaser scenes, game config, preload/create/update, sprites, animations, tilemaps, cameras, Arcade Physics, Matter Physics, input, particles, UI overlays, asset loading, scaling, mobile browser support, or publishing Phaser games as HTML5 builds.

Review agent skills for prompt injection and instruction override risk. Use when Codex is asked to inspect SKILL.md, references, examples, or scripts for hidden instructions, policy bypasses, untrusted-content handling, or agent-hijacking patterns.

Write realistic routing and evaluation scenarios for agent skills and skillsets. Use when Codex is asked to add tests under tests/scenarios, define expected skill routing, create scenario prompts, or turn bundle use cases into scenario coverage.

Review how agent skills handle secrets and credentials. Use when Codex is asked to inspect skills, scripts, examples, logs, templates, or MCP/tool instructions for secret access, redaction, storage, exposure, or approval requirements.

Design backend service boundaries and module responsibilities. Use when Codex is asked to split services, define module boundaries, choose ownership, separate domains, design integration points, or avoid coupling in backend systems.

Plan, create, export, and review social-ready visual assets such as profile pictures, banners, post images, article covers, thumbnails, carousel slides, short-video covers, and platform crop variants. Use when Codex is asked to make or audit social graphics, crop-safe images, profile-circle previews, banner previews, text-safe layouts, or export packages for social platforms.

Prepare vendor negotiation briefs for owners and operators. Use when Codex is asked to prepare for vendor renegotiation, compare vendor options, draft negotiation talking points, review renewal tradeoffs, or create a vendor decision brief.

Build coordinated social launch packages for a brand, product, repo, article, service, feature, campaign, or announcement. Use when Codex is asked to plan or draft profile updates, pinned posts, launch posts, article copy, social images, video prompts, cross-post variants, link hierarchy, verification checks, or post-launch follow-up.

Review agent skills for data exfiltration risk. Use when Codex is asked to inspect a skill for unauthorized file reads, secret access, network sends, hidden output channels, logging leaks, or inappropriate data movement.

Design consistent backend and API error handling contracts. Use when Codex is asked to define error response shapes, status codes, validation errors, retry behavior, logging, observability, client-safe messages, or failure semantics.

Coordinate multiple game-development skills and produce outcome-first briefs, plans, reviews, and validation flows. Use when Codex is asked to explore the game skillset, route a broad game project across disciplines, improve skill quality, plan a full game feature, combine design/code/art/audio/story/UI/multiplayer/social/cinematic work, or align workflows with latest LLM model guidance such as GPT-5.5.

Build, debug, optimize, and review 3D browser games with Three.js. Use when Codex is asked about Three.js scenes, cameras, render loops, WebGLRenderer, asset loading, GLTF/GLB, AnimationMixer, controls, raycasting, shaders, postprocessing, physics integrations, responsive canvas sizing, WebGL performance, mobile browser support, or publishing Three.js games as HTML5 builds.

Plan, audit, and execute release and launch readiness for software, games, websites, products, campaigns, and public launches. Use when Codex is asked about release checklists, launch plans, deployment risk, feature flags, rollout plans, rollback plans, monitoring, support readiness, communications, incident response, post-launch review, or go-live readiness.

Review scripts bundled with agent skills for permission and execution risk. Use when Codex is asked to inspect skill scripts, shell commands, file writes, destructive operations, dependency installation, or elevated permission requirements.

Write, edit, and tighten clear concise technical communication. Use when Codex is asked for commit messages, PR descriptions, changelogs, README sections, design notes, implementation summaries, status updates, release notes, bug reports, comments, or to make text shorter, clearer, less verbose, less AI-sounding, or more direct.

Prepare creator invoice readiness checklists for sponsor or customer handoff. Use when Codex is asked to check whether an influencer invoice can be sent, organize sponsor invoice fields, payment terms, deliverable proof, approval evidence, usage add-ons, PO/vendor details, tax/accounting review needs, missing fields, or invoice handoff notes.