--- title: Top AI/ML & Agent Tooling Skills for Codex slug: top-ai-ml-agent-tooling-skills-for-codex type: category-agent-cut category: ai-ml-agent-tooling agent: codex canonical: https://top-agent-skills.com/top-ai-ml-agent-tooling-skills-for-codex verified: 7 unverified: 15 updated: 2026-07-14 --- # Top AI/ML & Agent Tooling Skills for Codex For agent and integration tooling in Codex CLI, Composio is the broadest single install, with vendor skills for Supabase, Stripe, Notion, and Shopify covering focused builds against one product. All are verified through the SKILL.md path Codex adopted, so the same skill folder you use in Claude Code works here unchanged. ## Verified on Codex CLI (7) ### 1. antigravity-awesome-skills — score 65/100 (community) 1,234+ skills in one bundle. Single install across AI coding assistants. - Best for: Teams that want a comprehensive starting set rather than picking 30 individually. - Not ideal for: Lean setups — you will install many skills you never use. - Publisher: Antigravity · MIT - Verified on: claude-code, cursor, codex, gemini-cli, antigravity ```bash npx antigravity-awesome-skills --claude ``` Full entry: https://top-agent-skills.com/skill/antigravity-awesome-skills (https://top-agent-skills.com/skill/antigravity-awesome-skills.md) ### 2. composio — score 55/100 (verified-org) 1,000+ SaaS integrations as one skill. OAuth lifecycle, scoped credentials, structured actions. - Best for: Any agent that needs to act on real SaaS systems — Slack, Notion, GitHub, Stripe, Salesforce. - Not ideal for: Read-only research where MCPs would be lighter. - Publisher: Composio · Apache-2.0 - Verified on: claude-code, claude-ai, claude-api, cursor, codex, gemini-cli, antigravity ```bash npx skills add composiohq/skills ``` Full entry: https://top-agent-skills.com/skill/composio (https://top-agent-skills.com/skill/composio.md) ### 3. supabase-skill — score 51/100 (verified-org) Supabase done right. RLS policies, edge functions, realtime, auth — in idiomatic patterns. - Best for: Teams on Supabase who want the agent to write RLS-correct queries by default. - Publisher: Supabase · MIT - Verified on: claude-code, cursor, codex ```bash npx skills add supabase/agent-skills ``` Full entry: https://top-agent-skills.com/skill/supabase-skill (https://top-agent-skills.com/skill/supabase-skill.md) ### 4. stripe-payments — score 51/100 (verified-org) Stripe done right. Checkout, subscriptions, webhooks, idempotency, metered billing. - Best for: Teams adding Stripe where webhook handling and idempotency are easy to get wrong. - Publisher: Stripe · MIT - Verified on: claude-code, claude-api, cursor, codex ```bash npx skills add stripe/skills ``` Full entry: https://top-agent-skills.com/skill/stripe-payments (https://top-agent-skills.com/skill/stripe-payments.md) ### 5. shopify-storefront — score 51/100 (verified-org) Shopify Storefront API: cart, checkout, metafields, customer accounts, Hydrogen patterns. - Best for: Headless Shopify storefronts where you want the agent to build commerce flows correctly. - Publisher: Shopify · MIT - Verified on: claude-code, cursor, codex ```bash npx skills add shopify/skills ``` Full entry: https://top-agent-skills.com/skill/shopify-storefront (https://top-agent-skills.com/skill/shopify-storefront.md) ### 6. notion-api-skill — score 49/100 (verified-org) Notion API: page/database CRUD, block hierarchies, rich text, schema sync. Full entry: https://top-agent-skills.com/skill/notion-api-skill (https://top-agent-skills.com/skill/notion-api-skill.md) ### 7. alirezarezvani-skills — score 47/100 (community) 232+ skills across engineering, marketing, product, compliance, advisory. Full entry: https://top-agent-skills.com/skill/alirezarezvani-skills (https://top-agent-skills.com/skill/alirezarezvani-skills.md) ## In AI/ML & Agent Tooling but NOT verified on Codex CLI (15) These may well work — the SKILL.md format is shared. They are listed as unverified because this site lists an agent only where the install was run or the publisher documents a path for it. - loki-mode — Multi-agent orchestration. Spawn parallel subagents and merge their outputs reliably. (https://top-agent-skills.com/skill/loki-mode) - mcp-builder — Build new MCP servers. The official scaffold + design walkthrough. (https://top-agent-skills.com/skill/mcp-builder) - skill-creator — Build new skills interactively. Output is a clean SKILL.md ready to publish. (https://top-agent-skills.com/skill/skill-creator) - claude-api — Always-current Claude API reference and SDK docs. Bundled with Claude Code. (https://top-agent-skills.com/skill/claude-api) - qdrant-advisor — A self-updating vector-database skill: it fetches current Qdrant guidance at run time instead of shipping a snapshot that rots. (https://top-agent-skills.com/skill/qdrant-advisor) - weaviate — The vector-database skill that ships executable scripts rather than prose — the agent runs the query instead of describing it. (https://top-agent-skills.com/skill/weaviate-skill) - dbhub — One skill across Postgres, MySQL, SQL Server, MariaDB and SQLite — and its actual job is forcing explore-before-query on real schemas. (https://top-agent-skills.com/skill/dbhub) - create-payment-credential — Stripe's answer to agentic checkout: one-time payment credentials so an agent can buy without ever seeing the underlying card. (https://top-agent-skills.com/skill/stripe-link-checkout) - cowork-plugin-customizer — Tailor a plugin to your org's stack in one pass. (https://top-agent-skills.com/skill/cowork-plugin-customizer) - create-cowork-plugin — Scaffold a new plugin from scratch with guided prompts. (https://top-agent-skills.com/skill/create-cowork-plugin) - init — Bootstrap a CLAUDE.md so future sessions start informed. (https://top-agent-skills.com/skill/init-skill) - update-config — Edit settings.json safely. Hooks, perms, env, behaviors. (https://top-agent-skills.com/skill/update-config) - keybindings-help — Rebind keys and add chords without reading the keymap docs. (https://top-agent-skills.com/skill/keybindings-help) - fewer-permission-prompts — Cuts the permission-prompt friction by learning your safe-tool patterns. (https://top-agent-skills.com/skill/fewer-permission-prompts) - setup-cowork — Bootstrap the right plugin stack for your role in one guided pass. (https://top-agent-skills.com/skill/setup-cowork) ## Common question **Do skills written for Claude Code need editing to work in Codex?** Usually not — the spec fields Codex reads are the same two the spec requires. What can differ is anything agent-specific inside the instructions: a skill that names Claude Code tools or expects a particular allowed-tools list may degrade rather than fail. The compatibility list on each entry reflects what was actually tested, not what should work in principle. --- _Top Agent Skills. Machine-readable twin of https://top-agent-skills.com/top-ai-ml-agent-tooling-skills-for-codex._