Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 271,335 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Scaffolds a new AI Provider plugin for the Drupal AI module. Asks which operation types the provider supports (chat, embeddings, text-to-image, etc.), then generates the plugin class with the correct interface implementations, authentication setup, and model discovery.
Skill Claude CodeCodex
A conversational teaching workflow that helps someone learn a technical subject through dialogue, real errors, and their own explanations.
Skill Claude CodeCodex
Sync gitignored directories (clients/, partners/, scripts/, .env) between MacBook and Mac Mini over SSH using rsync. Use when the user types /sync-to-mini, /sync-from-mini, /sync-to-macbook, /sync-from-macbook, or /sync-machines.
Demerzels-lab/elsamultiskillagent
Skill Claude CodeCodex
Interact with FundraiseUp REST API to manage donations, recurring plans, supporters, campaigns, and donor portal access. Process online and offline donations, retrieve fundraising analytics, and integrate with nonprofit CRM systems.
Skill Claude CodeCodex
Create structured journal entries with YAML frontmatter, template-based sections, and compliance validation. Use when user asks to 'create journal entry', 'new journal', 'document [topic]', 'journal about [topic]', or needs to create timestamped .md files in YYYY/MM-Month/DD-Weekday/ directories. Supports six entry…
Skill Claude CodeCodex
Individual agents are powerful. But without coordination, they produce.
Skill Claude CodeCodex
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
Skill Claude CodeCodex
Generate polished Chinese consulting-style PDF reports from YouTube videos. Uses a transcription priority chain -- YouTube auto-subs first, Whisper fallback second (with quality gates and proper noun verification). Includes bot-detection bypass escalation when yt-dlp is blocked. Use when a user shares a YouTube link…
Skill Claude CodeCodex
A strategy framework for examining a company, its competitors, and its customers together.
bugrabilge/bilge-development-kit
Skill Claude CodeCodex
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, AI assistant design, prompt management, LLMOps monitoring, conversational interfaces, and context management.
Skill Claude CodeCodex
Aesthetic-direction design skill: reads a brief, infers the right visual style and direction, and ships interfaces that do not look templated. Umbrella for concrete style variants — minimalist, brutalist, soft/premium-agency. Use when the user wants a particular vibe or aesthetic, or wants a landing page or portfolio…
Skill Codex
UX writing and interface copy, from voice and button labels to error messages and empty states. Use when writing or reviewing any user-facing text: button and link labels, form errors, placeholders, settings labels, onboarding flows, notifications, or empty states. Triggers on UX writing, microcopy, interface copy…
MCP server Claude CodeCodexCursor +2
A Model Context Protocol server for persistent project-specific AI agent context. Runs locally from the opencontext-mcp npm package.
Mentor-Wizard/mentor-wizard-webapp
MCP server Claude CodeCodexCursor +2
One of 3 in .mcp.json
MCP server "laravel-boost" as configured in Mentor-Wizard/mentor-wizard-webapp. Runs in Docker (/var/www/artisan).
Skill Claude CodeCodex needs its repo
A voice-reporting skill that turns a work summary into an offline-generated voice message and locally transcribes a user's voice reply. It sends and receives these messages through Telegram.
Skill Claude CodeCodex
Review a pull request or a working-tree diff using structural analysis rather than reading the diff alone. Use when asked to review a PR, review changes, check a diff before merging, or say whether a change is safe to land. Combines Prism's impact analysis with whatever GitHub and issue-tracker tools the editor…
Skill Claude CodeCodex
Use when editing scripts/lib/spdx-version-extractor.js, scripts/lib/oci-sbom.js, scripts/lib/image-sbom-registry.js, scripts/lib/image-version-audit.js, scripts/lib/verified-image-sbom.js, scripts/lib/sbom-issue-report.js, scripts/lib/sbom-issue-sync.js, scripts/lib/bluefin-version-projection.js…
mindverse-ltd/macaron-artifacts
Skill Claude CodeCodex
Build compact interactive React UI inside chat or a persistent canvas when interaction makes the response more useful.
Skill Claude CodeCodex
Consulta de forma segura cursos, tareas, notas, anuncios y materiales de Blackboard UPC mediante Campus MCP.
Skill Claude CodeCodex
Write C#/.NET Sinch Functions with the Sinch.Functions.Runtime NuGet package. Use when writing or editing a function controller: answering and controlling calls with Voice API v2, IVR menus, placing, bridging or transferring calls, realtime AI voice agents, SMS/WhatsApp/RCS webhooks, custom HTTP endpoints, dependency…
Skill Claude CodeCodex
A presentation-building skill for creating editable PowerPoint files. It makes native text, shapes, charts, and tables rather than placing screenshots on slides, then checks the result for layout problems.
Skill Claude CodeCodex
Report Claude Code usage from Pacer — every rate-limit window, including per-model caps like Fable and each account on the machine — and pace heavy work against them, so hitting a limit during a long autonomous run or a large fan-out of subagents costs a resumable pause rather than the whole run. Use before and during…
Skill Claude CodeCodex
Build LLM pipelines, tool-using agents and parallel fan-outs in Python with yait-aichain (Skill, Chain, Pool, Agent, Tool) — provider-independent. Use when writing, fixing or reviewing code that imports yaitaichain.
Skill Claude CodeCodex
Delegate a multi-step coding task to sidekick — a local orchestrator that decomposes the task into a DAG of subtasks, fans out auto-approved coding sub-sessions on isolated git worktrees (Claude Code on the claude branch, Kimi/Moonshot on the kimi branch — same envelope either way), runs acceptance checks, and merges…
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: