Ask Codex to evaluate a plugin or skill, give you a full analysis of a named plugin such as game-studio, explain why it scored that way, show what to fix first, explain its token budget, measure real token usage, benchmark a plugin, or tell you what to run next. Plugin Eval keeps the path engineer-friendly: start with a natural chat request, then use the local `plugin-eval start` entrypoint or the routed workflow command it recommends.
Plugin plugin-eval from marketplace openai-plugins-converted in robinebers/converted-plugins. Commands read from the repo's manifest — 1 month ago.
evaluate-pluginEvaluate a local Codex plugin in engineer-friendly language. Use when the user says "evaluate this plugin", "audit this plugin", "why did this score that way", "what should I fix first", "help me benchmark this plugin", or asks for a plugin-wide report before comparing versions.
evaluate-skillEvaluate a local Codex skill in engineer-friendly terms. Use when the user says "evaluate this skill", "give me an analysis of the game dev skill", "audit this skill", "why did this score that way", "what should I fix first", or asks for a skill-specific report before benchmarking it.
improve-skillTurn plugin-eval findings into a concrete rewrite brief for a Codex skill. Use when the user already evaluated a skill and now wants Codex to improve it, especially after asking what to fix first.
metric-pack-designerDesign custom metric packs for plugin-eval so teams can add local evaluation rubrics that emit schema-compatible checks and metrics. Use when the user wants their own evaluation criteria or visualizations.
plugin-evalHelp engineers evaluate a local skill or plugin, explain why it scored that way, show what to fix first, measure real token usage, benchmark starter scenarios, or decide what to run next. Use when the user says things like "evaluate this skill", "give me an analysis of the game dev skill", "why did
Bring Vercel ecosystem guidance into Codex with curated skills and the connected Vercel app. Packages the upstream vercel/vercel-plugin skills, agents, and commands under the local `vercel` plugin identity for the Codex plugin marketplace.
47 skills · 6 commands · 3 agents · app connector
Procedural knowledge that guides AI coding agents to the right Twilio APIs for any use case. Covers channel selection, production best practices, compliance requirements, and common pitfalls across Messaging, Voice, Verify, SendGrid, and 30+ products. Skills follow a progressive disclosure architecture — your agent sees lightweight metadata at startup and loads full guidance only when a task matches.
55 skills
Internal life-science research workflows that help Codex interpret a user's research question, normalize the relevant entities, choose the right skills, and synthesize evidence-backed answers across public resources. The plugin spans human genetics, functional genomics, expression, pathways, protein structure, chemistry, pharmacology, literature, clinical evidence, and public study discovery, with a research-router entrypoint for broad tasks and optional subagent-assisted parallel work when evidence lanes are independent.
50 skills
Figma workflows for implementing designs in code, creating Code Connect templates for published Figma components, and generating project-specific design system rules for repeatable Figma-to-code work.
8 skills · 4 commands · 4 agents · app connector
macOS development workflows for discovering local projects, building and running desktop apps, implementing native SwiftUI scenes, bridging into AppKit when necessary, adding lightweight Logger telemetry, triaging test failures, inspecting signing and entitlements, and debugging desktop-specific build or runtime errors.
11 skills · 3 commands
Official Expo-authored skills for building Expo Router UI, authoring API routes, configuring data fetching and styling, writing Expo native modules, creating dev clients, upgrading Expo SDKs, wiring Codex app Run actions, and deploying Expo apps with EAS workflows, builds, hosting, TestFlight, App Store, and Play Store guidance.
13 skills · 1 command
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
6 skills
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.