Skills

Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.

agentic-ads

19801

nicofains1/agentic-ads

Skill Claude CodeCodex

Monetize your bot by showing relevant sponsored suggestions to users.

not rated 2 5mo ago A 17 tokens original MIT

tokencast

19802

krulewis/tokencast

Skill Claude Code

Automatically estimates token usage and dollar cost when a development plan is created. Triggers when: a pipeline plan is finalized, an implementation plan is produced, an architecture decision is made, or step counts and file lists are discussed. Reads the plan from conversation context to infer size, file count…

not rated 2 5mo ago B 80 tokens original MIT

codexa

19803

mirnoorata/codexa

Skill Claude CodeCodex

Use Codexa selectively for ambiguous, cross-cutting, or high-risk repository work that needs search, change planning, dependency context, or verification guidance beyond exact source inspection.

not rated 2 12d ago A 37 tokens original MIT

docs

19804

mysleekdesigns/crawlforge-mcp

Skill Claude CodeCodex

Scale up scraping and drive interactive pages. Use batchscrape for many URLs, getbatchresults to page through async output, scrapewithactions to interact before scraping, and generatellmstxt to produce a site's AI policy file.

not rated 2 changed yesterday A 0 tokens original MIT

iwac-mcp

19805

fmadore/iwac-mcp-server

Skill Claude CodeCodex

Structured academic research workflow for the Islam West Africa Collection (IWAC) MCP server. Use this skill when: Conducting research queries through the IWAC MCP server (iwac-mcp-server tools) Investigating questions about Islam and Muslims in West Africa using IWAC data Performing systematic searches across IWAC…

not rated 2 changed 27d ago A 158 tokens original MIT

batch-product-research

19806

BlockchainHB/launchfastmcp-skills

Skill Claude CodeCodex

Use this skill when the user wants to research multiple Amazon FBA keywords at once (batch research). Accepts a list of up to 20 keywords, runs parallel product research using sub-agents, and generates a professional HTML report + CSV. Automates the single-keyword product-research workflow across many keywords…

not rated 2 6mo ago A 69 tokens

pushtodisplay

19807

pushtodisplay/cli

Skill Claude CodeCodex

Send real-time display updates to boards, manage boards, and query devices using the PushToDisplay CLI or MCP server. Use when: the user wants to send content to a display board, create/manage boards, check device connections, or integrate PushToDisplay into a workflow. Trigger on: 'send to display', 'display board'…

not rated 2 15d ago A 117 tokens original MIT

purmemo

19808

purmemo-ai/purmemo-mcp

Skill Claude CodeCodex

Persistent AI conversation memory. Recall context at session start, save progress at session end. Essential for project continuity across sessions.

not rated 2 4d ago A 27 tokens

generate-content

19809

qingxuantang/tar-engine

Skill Claude CodeCodex

Generate draft text for one or more social platforms from a topic or URL. Wraps postall-agent generate. Activates when the user wish includes a content topic plus a publishing intent ("write a tweet about X", "draft a LinkedIn post on Y", "summarize this URL into a wechat article").

not rated 2 2mo ago A 68 tokens original Apache-2.0

build-scaling-experiment

19810

rctruta/sql-benchmarks-dagster

Skill Claude CodeCodex

Build and submit a scaling benchmark experiment. Use when the goal names a scale-varying investigation (e.g. how does X scale from N to M rows, is the growth linear, or at what size does Y break).

not rated 2 13d ago A 52 tokens original Apache-2.0

hotkeyless-ahk-invoke

19812

tim0-12432/HotkeylessAHK-mcp-skill

Skill Claude Code

Invoke desktop automation commands on the user's Windows machine via the Hotkeyless AHK HTTP server. Use when the user asks to open programs, press hotkeys, move the mouse, control media, or perform any desktop action. Requires discovering commands first using the hotkeyless-ahk-discovering skill.

not rated 2 1mo ago A 69 tokens original MIT

clawaimail

19813

joansongjr/clawaimail

Skill Claude CodeCodex

Give your AI agent a real email address. Send, receive, and manage emails via API.

not rated 2 6mo ago A 24 tokens original MIT

jquants-mcp-usage

19814

shigechika/jquants-mcp

Skill Claude CodeCodex

Operational guidance for jquants-mcp: daily briefing workflows, value screening, cache tiers, plan limits, and safe cache management.

not rated 2 12d ago A 35 tokens original MIT

inbox-to-action

19815

tarunlnmiit/inbox-to-action

Skill Claude CodeCodex

Triage an inbox in one agentic pass — fetch unread email, classify, summarize long threads, extract tasks, draft replies (never sends), flag calendar blocks. Keyless: you are the LLM. Trigger when the user says /inbox-to-action or asks to triage their inbox.

not rated 2 2mo ago A 65 tokens original MIT

patent-research-workflow

19816

smythmyke/patent-search-mcp-server

Skill Claude CodeCodex

Use when a user asks about a US patent — what it covers, whether it's still in force, who owns it, whether it survived PTAB challenges or was litigated, what happened during examination, or whether it's risky to a product. Drives the AI Patent Search Generator connector tools in the right order (cheap free lookups…

not rated 2 3mo ago A 95 tokens original MIT

tablecloth

19817

yourtablecloth/TableClothMcp

Skill Claude CodeCodex

A tool for opening Korean government and financial-service websites in a clean, temporary Windows Sandbox. It is used when someone wants to apply for, sign up for, log in to, or use a service.

not rated 2 1mo ago A 146 tokens AGPL-3.0

zxhwolfe-dev/aiworkstation-open-source-intelligence

Skill Codex

Use live AI Open Source Radar evidence to browse, discover, verify, compare and select open-source AI projects or plan candidate stacks. Use for Radar rankings and collections, project or license checks, alternatives, technology selection, stack planning, or the Radar Skills library; do not use for general AI news or…

not rated 2 1mo ago A 71 tokens original Apache-2.0

embedded-iot-mentor

19819

mh-mansouri/embedded-iot-mentor

Skill Claude CodeCodex

Mentor for embedded and IoT projects. Helps select IDEs, hardware kits, MCUs, and tools, and decides where the readings end up — phone, PC, dashboard, or alert. Gives time and cost estimates, step-by-step build plans from breadboard MVP to production PCB, alternatives for every major choice, and simple circuit-design…

not rated 2 4d ago A 174 tokens original MIT

smythmyke/govtoolspro-mcp-server

Skill Claude CodeCodex

Use when a user is evaluating a U.S. federal contracting opportunity (a SAM.gov notice, RFP/RFQ, solicitation number, NAICS code, or agency) and wants a bid/no-go decision, the competitive picture, a pricing benchmark, teaming partners, or a recompete pipeline. Drives the GovToolsPro connector tools in the right order…

not rated 2 27d ago A 90 tokens original MIT

chrome-extensions

19821

robertn702/webmcp-today

Skill Claude CodeCodex

Build and publish Chrome Extensions using Manifest V3 best practices. Use this skill whenever the user asks to create, modify, debug, or understand Chrome browser extensions, add-ons, or anything involving the Chrome Extensions API. Trigger on mentions of: 'Chrome extension', 'browser extension', 'manifest.json'…

not rated 2 24d ago A 178 tokens

causallayer-mcp

19822

smq9sn5jck-coder/causallayer-mcp

Skill Claude CodeCodex

This skill provides instructions for AI agents interacting with the CausalLayer Model Context Protocol (MCP) server. CausalLayer is a deterministic AI liability apportionment engine. It takes an incident report and mathematically proves which agent, vendor, or operator is liable based on counterfactual do-calculus…

not rated 2 1mo ago A 0 tokens original Apache-2.0

flato-design-mcp-guide

19823

sologovision/flato-design-mcp

Skill Claude CodeCodex

Use when creating, editing, inspecting, exporting, or troubleshooting Flato designs through Flato Design MCP tools such as flatowhoami, flatogetdesigncontext, flatocreatepages, flatoupdatepages, flatoupdatecanvas, and flatoexport.

not rated 2 3mo ago A 62 tokens original MIT

veriswarm

19824

veriswarm/veriswarm-sdk

Skill Claude CodeCodex

Trust scoring, PII protection, and audit for OpenClaw agents. Strips personal data before it reaches the LLM. Blocks dangerous tools. Detects prompt injection. Audits everything.

not rated 2 5d ago A 43 tokens 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: