Skills for Codex

211,278 that install into Codex. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.

whiteboard-video

2497

gnipbao/codex-whiteboard-video-skill

Skill Codex

Generate smooth hand-drawn whiteboard and story videos directly inside Codex from text scripts, GPT Image 2 color storyboards, scene plans, SVGs, line art, or local images. Supports 30 built-in visual styles, automatic recommendations, custom media recipes, natural-block coarse/detail drawing with block-local or…

not rated 311 +5 changed 10d ago A 105 tokens original MIT

jayanthmb14/forthepeople

Skill Claude CodeCodex

Skill for expanding ForThePeople.in to new districts. Use when adding Bengaluru Urban, Mysuru, or any new Indian district to the platform. Triggers: 'add district', 'expand to Bangalore', 'expand to Mysore', 'unlock district', 'new city', 'seed data for district', 'add Bengaluru', 'add Mysuru', 'district-specific…

not rated 310 today A 145 tokens

wechat-ai-layout

2499

DavidLam-oss/obsidian-wechat-converter

Skill Claude CodeCodex

A content-layout workflow that converts an article's structure into a restricted JSON layout for a WeChat public-account renderer. WeChat public accounts are channels for publishing articles and media in the WeChat app.

not rated 312 +4 today A SkillSpector: pass 75 tokens original MIT

jina-cli

2500

geekjourneyx/jina-cli

Skill Claude CodeCodex

Reads web content and searches the web using Jina AI Reader API. Use when extracting content from URLs, reading social media posts (X/Twitter), or web searching for current information.

not rated 309 6mo ago C 41 tokens original MIT

loopany

2501

superdesigndev/loopany-platform

Skill Claude CodeCodex

Create, update, and evolve scheduled Loopany agent loops from a coding session. Use when the user wants to turn a task they just did into a recurring/scheduled loop, edit an existing loop's schedule or instructions, or asks to build a Loopany loop. A loop can carry a goal (a finish line) and completes itself when the…

not rated 310 +2 28d ago A 85 tokens

agent-fetch

2502

teng-lin/agent-fetch

Skill Claude CodeCodex

Fetch and extract full article content from URLs. Returns complete text with structure (headings, links, lists) instead of summaries. Multiple extraction strategies, browser impersonation, cookies, crawling, custom selectors, 200-700ms.

not rated 308 +1 6mo ago A 50 tokens original MIT

pr-reviewer

2503

Fu-Jie/openwebui-extensions

Skill Claude CodeCodex needs its repo

Fetches PR review comments, analyzes requested changes, implements fixes, commits and pushes the resolution. Use after a reviewer has left comments on an open PR to close the feedback loop efficiently.

not rated 309 +3 9d ago A SkillSpector: warn 41 tokens original MIT

add-command

2504

Doist/todoist-cli

Skill Claude CodeCodex needs its repo

Guide for adding new CLI commands or subcommands to todoist-cli. Use when implementing new SDK endpoints, adding subcommands to existing command groups, or extending CLI functionality.

not rated 309 +2 2d ago A SkillSpector: warn 37 tokens original MIT

add-data-sources

2505

nirholas/cryptocurrency.cv

Skill Claude CodeCodex

Prompts to integrate 70+ new crypto data sources into free-crypto-news, wiring them through the ProviderChain framework with circuit breakers, anomaly detection, and consensus. Covers market data, on-chain analytics, DeFi, derivatives, social, news, Solana ecosystem, L2s, NFTs, prediction markets, RWA, MEV, and more.

not rated 308 +4 5d ago A 78 tokens

exploit-xss

2506

crazyMarky/pentest-skills

Skill Claude CodeCodex

Cross-site scripting (XSS) vulnerability detection and exploitation. Supports reflected XSS, stored XSS, DOM-based XSS, and blind XSS testing. Use this skill when user mentions XSS, cross-site scripting, script injection, or needs to test JavaScript injection in parameters, forms, headers, or DOM sources.

not rated 308 +4 3mo ago A SkillSpector: warn 71 tokens original Apache-2.0

llm-intern-skill

2507

wanyichen06/LLMInternSkill

Skill Claude CodeCodex

Use when polishing, diagnosing, tailoring, or exporting resumes for LLM, RAG, Agent, Agentic RL, post-training, pretraining, AIGC, search/ranking, multimodal, AI backend, or LLM algorithm internships from raw resume text, a materials folder, and/or a target job description. Audits evidence, maps JD fit, enforces truth…

not rated 310 +7 1mo ago A 116 tokens original MIT

surreal-pop-collage

2508

2998980-hue/surreal-pop-collage

Skill Claude CodeCodex

A skill for turning a supplied photo into a surreal pop collage. It keeps the main subject recognizable in black and white, replaces parts of the background with flat color shapes, and adds one oversized impossible object.

not rated 311 +13 1mo ago A 116 tokens original MIT

finn-build

2509

finna/Finn-loop

Skill Claude CodeCodex

Claim the next safe agent-ready issue from Linear, implement it, and open a PR. Use when asked to run Finn-loop's builder, work the approved queue, or fix Finn-loop review feedback. Designed for /loop; one pass does one unit of work.

not rated 307 +3 1mo ago A SkillSpector: pass 57 tokens original MIT

academic-investigation

2510

yadnuses/Academic-Detective

Skill Claude CodeCodex

A structured system for investigating researchers, their qualifications, publications, affiliations, relationships, and possible academic misconduct.

not rated 307 +1 3mo ago A 98 tokens original MIT

finalrun-generate-test

2511

droid-ash/finalrun-agent

Skill Claude CodeCodex

Generate test and suite specifications in the strict FinalRun YAML format. Handles automated test planning, folder grouping by feature, repo app configuration, environment-specific overrides in .finalrun/env/.yaml, and validation via finalrun check.

not rated 308 +2 1mo ago A SkillSpector: pass 51 tokens original Apache-2.0

[object Object]

2512

lifedever/PasteMemo-app

Skill Claude CodeCodex

A clipboard-triggered coding-agent skill. The available information does not explain any further action it performs.

not rated 307 +3 today A 310 tokens GPL-3.0

insights-dashboard

2513

buildswithpaul/Frappe_Assistant_Core

Skill Claude CodeCodex

Use this skill whenever the user wants to create, build, set up, or fix a dashboard in Frappe Insights (also called "Insights", "Frappe Insights v3", or the analytics module). Trigger on phrases like: "create an Insights dashboard", "build a dashboard in Insights", "add a chart to a workbook", "create a workbook"…

not rated 308 +4 2d ago A 133 tokens AGPL-3.0

lc-curate-context

2514

cyberchitta/llm-context.py

Skill Claude CodeCodex

Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for your own context, a chat, or a sub-agent you dispatch. Load when choosing what code to put in front of a model, packing…

not rated 306 18d ago A SkillSpector: pass 90 tokens original Apache-2.0

happy-app-audit

2515

iamzhihuix/happy-claude-skills

Skill Claude CodeCodex

Audit a local macOS app's telemetry / reporting behavior using static analysis only. Reverse-engineers an .app bundle to identify embedded SDKs (AppLog/TEA, Parfait, TTNet, mars, MMKV, Sentry, Firebase, Bugly, Umeng, etc.), mapped upload endpoints, local on-disk queues, and privacy-relevant fields — without packet…

not rated 306 4mo ago A 152 tokens original MIT

summarize-slides

2516

Li-Baichuan-James/summarize-slides-skill

Skill Claude CodeCodex

A workflow for turning lecture PDFs or course slides into concise study materials, such as revision notes and exam cheat sheets.

not rated 307 +4 4mo ago A 66 tokens original MIT

develop-disguise

2517

cha0upup/LeoAI

Skill Claude CodeCodex

A specialised helper for creating or updating Disguises on a platform, including the code that changes and restores traffic data.

not rated 306 +6 5d ago A 72 tokens GPL-3.0

lemmalog

2518

JordyZomer/lemmalog

Skill Claude CodeCodex

Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…

not rated 308 +18 changed 9d ago A SkillSpector: pass 105 tokens original MIT

gendangzou-skill

2519

MobiusQuant/Gendangzou-skill

Skill Claude CodeCodex

A Chinese-language research tool for analyzing sectors in China's stock market using platform, API, and independently installable application data.

not rated 306 +2 1mo ago A 89 tokens original Apache-2.0

better-drizzle

2520

almeidazs/better-drizzle

Skill Claude CodeCodex

Expert guidance for better-drizzle repository work. Use whenever the user is building, refactoring, reviewing, debugging, documenting, or migrating code that uses better-drizzle, Drizzle delegates, plugins, transactions, pagination, filters, raw SQL, or performance-sensitive repository helpers. Also use when the task…

not rated 307 +1 12d ago A SkillSpector: pass 78 tokens original Apache-2.0

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: