Everything for Codex

Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,786 indexed, measured the same four ways as everything else here.

glin-profanity

6193

glincker/glin-profanity

Skill Claude CodeCodex

Detect and filter profanity in text across 24 languages, including obfuscated forms like fck, f.u.c.k and leetspeak, using the glin-profanity JS or Python package. Use when adding content moderation, chat filtering or input checks to an app.

not rated 69 +2 yesterday A 62 tokens original MIT

visionpower

6194

RunhuaHuang/VisionPower

Skill Claude CodeCodex

Image-understanding tool for non-multimodal (text-only) models. Uses an external vision model to read screenshot text (OCR), interpret charts and diagrams, describe photos or UI mockups, and return the results as text. Models that can understand images directly must not call this skill; use their own vision capability…

not rated 68 changed 1mo ago B SkillSpector: warn 94 tokens original MIT

attio-skill-generator

6195

kesslerio/attio-mcp-server

Skill Claude CodeCodex

Generate use-case-specific Attio workflow skills from templates. Use when creating new skills for lead qualification, deal management, customer onboarding, or custom Attio workflows.

not rated 68 +1 8d ago A 38 tokens

token-enhancer

6196

xelektron/token-enhancer

MCP server Claude CodeCodexCursor +2

Cuts AI agent web-fetching costs by up to 99.9% by stripping junk from web pages before they reach your LLM. Runs locally from the xelektron-token-enhancer Python package.

not rated 68 7mo ago A tokens not measured original MIT

semanticscholar-skill

6197

Agents365-ai/semanticscholar-skill

Skill Claude CodeCodex

Use when searching academic papers, looking up citations, finding authors, or getting paper recommendations using the Semantic Scholar API. Triggers on queries about research papers, academic search, citation analysis, or literature discovery.

not rated 68 3mo ago A SkillSpector: warn 48 tokens original MIT

upskill

6198

Autoloops/upskill

Skill Claude CodeCodex

A live, growing registry of agent skills published by Anthropic, OpenAI, Vercel, Microsoft, Cloudflare, Stripe, HashiCorp, Supabase, and many others. Search it before starting any non-trivial task, fetch the top result, follow it instead of going freehand. After using a skill, report back so the registry ranks it…

not rated 68 6mo ago A 96 tokens original MIT

anygen-data-analysis

6199

AnyGenIO/anygen-skills

Skill Claude CodeCodex

Use this skill any time the user wants to analyze data, create charts, or build data visualizations. This includes: sales analysis, financial modeling, cohort analysis, funnel analysis, A/B test results, KPI tracking, data reports, revenue breakdowns, user retention analysis, conversion rate analysis, CSV…

not rated 68 7mo ago A 128 tokens

onecite

6200

HzaCode/OneCite

Skill Claude CodeCodex

Validate, clean, and audit academic references with OneCite from a local repository checkout. Use when a workflow needs deterministic citation verification, BibTeX cleanup, benchmark gating, or template discovery.

not rated 68 3mo ago A SkillSpector: pass 42 tokens original MIT

k-kolomeitsev/data-structure-protocol

Skill Claude CodeCodex

Build and navigate DSP (Data Structure Protocol) — graph-based long-term structural memory of codebases for LLM agents. Stores entities (modules, functions), their dependencies (imports), public API (shared/exports), and reasons for every connection. Use when: (1) project has a .dsp/ directory, (2) user asks to set up…

not rated 68 3mo ago A SkillSpector: pass 133 tokens original Apache-2.0

better-bear

6203

KuvopLLC/better-bear

MCP server Claude CodeCodexCursor +2

MCP server for Bear notes — read, search, create, edit, tag, and manage notes via CloudKit. Runs locally from the better-bear npm package.

not rated 68 today A tokens not measured original MIT

auto-skill-installer

6204

lingbol088-spec/auto-skill-installer

Skill Codex

Detect missing capabilities during an AI agent task, search local skill folders plus configured GitHub skill registries, then install and validate the best matching skill before continuing. Use when an agent has loaded this skill and realizes another skill would make the current job safer, faster, or more accurate.…

not rated 68 3mo ago A SkillSpector: pass 77 tokens original MIT

vhs-terminal-recorder

6205

tmchow/agent-skills

Skill Claude CodeCodex

This skill should be used when the user names Charmbracelet VHS, asks to use the vhs CLI, wants a terminal recording, terminal GIF, terminal MP4/WebM, .tape file, scripted terminal demo, or a reproducible command-line screencast. Do NOT use for generic browser recording, full desktop screen capture, or unscripted…

not rated 68 2mo ago A SkillSpector: pass 86 tokens original MIT

telegram

6206

jonathanmalkin/jules

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

MCP server "telegram", hosted remotely at localhost, as configured in jonathanmalkin/jules.

not rated 68 +1 5mo ago A tokens not measured original MIT

chinese-write-checker

6207

taxueseek/say-it-human

Skill Claude CodeCodex

A Chinese-language review process for checking an article from an editor's, reader's, writer's, and publishing platform's viewpoints.

not rated 68 2mo ago A SkillSpector: pass 211 tokens original MIT

md-to-docx

6208

pickle-an/md-to-docx-skill

Skill Claude CodeCodex

A document conversion tool that turns Markdown, a plain-text writing format, into a formatted DOCX Word document.

not rated 68 7mo ago A 47 tokens

codebase-context

6209

PatrickSys/codebase-context

MCP server Claude CodeCodexCursor +2

MCP server "codebase-context", hosted remotely at 127.0.0.1, as configured in PatrickSys/codebase-context.

not rated 68 3d ago A tokens not measured

verifying-compose-ui

6210

rnett/gradle-mcp

Skill Claude CodeCodex

Verifying Compose UI by rendering components or previews and inspecting the resulting images and state transitions. Activate for visual behavior that requires runtime rendering; use ordinary tests for nonvisual logic.

not rated 68 changed 2mo ago A SkillSpector: pass 40 tokens original Apache-2.0

skillnote

6211

luna-prompts/skillnote

Skill Claude CodeCodex

Self-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs them to disk before each task, and collects which-helped/which-failed signals from the agent so the registry improves over time.

not rated 68 8d ago A ✓ AI review 54 tokens original MIT

Dicklesworthstone/remote_compilation_helper

Skill Claude CodeCodex

Build terminal UIs with Charmbracelet (Bubble Tea, Lip Gloss, Gum). Use when: Go TUI, shell prompts/spinners, "make CLI prettier", adaptive layouts, async rendering, focus state machines, sparklines, heatmaps, kanban boards, SSH apps.

not rated 68 +1 today A 65 tokens

musicfree-plugin-dev

6213

maotoumao/musicfree-skills

Skill Claude CodeCodex

A guide for developing plugins for MusicFree, a music-player application, including plugins that connect it to a music website or API.

not rated 68 +1 8mo ago A 109 tokens AGPL-3.0

cae-visualization

6214

NVIDIA-Omniverse/kit-cae

Skill Claude CodeCodex

Visualize and analyze simulation data using NVIDIA Kit-CAE (Omniverse). Supports native CAE USD-plugin formats including CGNS, VTK, EnSight Gold, OpenFOAM, NumPy, EDEM, NanoVDB, FLASH AMR, Eclipse reservoir data, and Trimesh assets. Covers volume rendering, faces, geometry and volume slices, iso-surfaces, streamlines…

not rated 68 11d ago A 144 tokens

pkm-vault-master

6215

oalanicolas/ia

Skill Claude CodeCodex

This skill should be used when organizing and structuring Personal Knowledge Management (PKM) vaults, particularly Obsidian vaults using the Linking Your Thinking (LYT) methodology. Use this skill when the user asks to analyze notes, create MOCs (Maps of Content), find related notes, organize folders, generate…

not rated 68 +2 11mo ago A 105 tokens

wireshark

6216

khuynh22/mcp-wireshark

MCP server Claude CodeCodexCursor +2

MCP server "wireshark" as configured in khuynh22/mcp-wireshark. Launched with mcp-wireshark.

not rated 68 3mo ago A tokens not measured original MIT

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: