Skills SDK for Codex/AI coding agents: author, validate, evaluate, and sync runtime projections through ask.
This repository also configures its own agents. See what Agent-Skills tells them →
Skill Claude CodeCodex
Create, migrate, or validate Better Auth implementation work. Use when the user wants Better Auth added or changed in code, including OAuth, passkeys, 2FA, magic links, or org flows.
Skill Claude CodeCodex
Run, audit, and design authorized Recon Workbench workflows when scoped target interrogation needs evidence artifacts, redaction, validation, and safe reporting.
Skill Claude CodeCodex
Analyze git-history security ownership when sensitive files, CODEOWNERS coverage, bus factor, contributor concentration, and remediation evidence need mapping.
Skill Claude CodeCodex
Binary calibration pack for recurring workflow guardrail recommendations.
Skill Codex
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
Skill Codex
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, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs…
Skill Codex
Create, review and validate software onboarding, task guides, UI help, FAQs and troubleshooting for non-technical end users. Use when people need to learn how to use a product or dashboard from verified interface evidence; route developer, API and administrator documentation to technical-writer.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: