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.
Skill Claude CodeCodex
Use when the user wants a paper audited for integrity issues — image misuse, numerical anomalies, logical gaps — and needs a reviewable evidence report. Works on external papers (PDF / DOI / arXiv) and on outputs from a local paper-writer run. Single-stage skill.
Skill Claude CodeOpenCode
A robustness-testing tool for computational operators, which are small pieces of code that perform tensor calculations.
Skill Claude CodeCodex
Find and read StyleGallery guidance (layout patterns, recipes, motion, state management, platform guides, design terminology, expression) with the stylegallery CLI or the stylegallery-mcp search/read tools. Use when a UI task needs a layout pattern, recipe, or interaction contract and the right document is not already…
ParthJadhav/ios-marketing-capture
Skill Claude CodeCodex
Use when the user wants to automate capture of marketing screenshots for a SwiftUI iOS app across multiple locales, devices, or appearances. Covers full-screen shots, isolated element renders (carousel cards, widgets), and reproducible output naming. Triggers on marketing screenshots, locale screenshots, widget…
Skill Claude CodeCodex
A playbook for promoting an open-source project, meaning software whose code is publicly available for others to use and change. It covers planning, launch activities, developer communities, media channels, and attracting contributors.
agent-ecosystem/skill-validator
Skill Claude CodeCodex
Review a proposed Agent Skill for structural validity and content quality before publishing. Runs the skill-validator CLI to check for structural issues, scores the skill with an LLM judge, and interprets results to advise authors on what to address. Use when a user wants to review, validate, or quality-check an Agent…
Skill Claude CodeCodex
This skill provides three primary modes for Android security testing.
Skill Claude CodeCodex
Check if recent cybersecurity alerts from 10 international CERTs affect your current project. Use when the user asks about security vulnerabilities, CVEs, "is my project affected", "any new security alerts", "check for vulnerabilities", "cyberowlai", or "/cyberowlai". Also trigger when the user is working on…
Skill Claude CodeCodex
Autonomous work mode that lets Claude work continuously while the user is away. Activates pre-flight risk assessment, dangerous-ops approval, and a blocker decision framework. Use "/nonstop" to activate, "/nonstop off" to deactivate. Use this skill whenever the user says things like "go nonstop", "keep working"…
Skill Codex
Use when the user asks Codex to inspect, import, enable, disable, deploy, update, repair, migrate, or uninstall Skill Flow skill groups through the skill-flow CLI or bridge protocol.
Skill Claude CodeCodex
Patterns for invoking the Apify CLI (apify) from agents. Covers authentication, creating/running/pushing Actors, calling Actors in the cloud, and reading results from datasets and key-value stores.
Skill Claude CodeCodex
A smart assistant for NetEase Cloud Music, a Chinese music-streaming service. It uses ncm-cli to search music, manage playlists, control playback, and send recommendations through messaging services such as Feishu.
Skill Claude CodeCodex
Football (soccer) data — standings, schedules, match stats, xG, transfers, player profiles, head-to-head, Elo, and forecasts. No API keys. Covers Premier League, La Liga, Bundesliga, Serie A, Ligue 1, MLS, Champions League, World Cup, and more (see getcompetitions). Use when: user asks about soccer standings…
Skill Claude Code
liter-llm e2e fixture schema: per-category fixture files, call names, mock provider responses, env and skip, and assertion types. Use when adding or editing a liter-llm e2e fixture.
Skill Claude CodeCodex
Connect yourself to a new messaging platform or interface (Discord, Slack, Matrix, WhatsApp, email, a web chat, SMS...) by writing a channel skill; also the reference for the channel protocol used by every channel skill, including telegram. Read before creating, changing or debugging any channel.
Skill Claude CodeCodex
Set up and query business data across 100+ sources (Stripe, HubSpot, Salesforce, etc.) via SQL. Agent-driven setup, cross-source joins, mutations.
Skill Claude CodeCodex
Search the web for current information.
Skill Claude CodeCodex
Create or update the Panel UI component of a complete schema v2 NextClaw Mini App or an explicitly loose local Panel. Use after nextclaw-app-creator selects Panel-only or Panel + Service, or for right-side UI, Service Actions, Agent-powered panels, React/Vite panels, and App bridge capability questions.
Skill Claude CodeCodex
Sandbox API reference, proven patterns, and library recommendations for evaluateexpression.
thoughtbot/rails-audit-thoughtbot
Skill Claude CodeCodex
Perform comprehensive code audits of Ruby on Rails applications based on thoughtbot best practices. Use this skill when the user requests a code audit, code review, quality assessment, or analysis of a Rails application. The skill analyzes the entire codebase focusing on testing practices (RSpec), security…
Skill Claude CodeCodex
End-to-end (E2E) test generation and execution with KaneCLI. Generate tests from a PRD, specification, or user-provided description via the assurance commands (use-cases, acceptance criteria, scenarios, runnable test.md tests; never write test cases by hand). Execute them on desktop web (Chrome, the default), Android…
Skill Claude CodeCodex
Access reMarkable tablet documents, notebooks, PDFs, and EPUBs. Use when the user wants to read, search, browse, or extract text from their reMarkable tablet. Supports handwriting OCR, typed text, annotations, highlights, and page rendering to PNG/SVG. Triggers: "reMarkable", "tablet notes", "handwritten notes"…
Skill Claude CodeCodex
Use first on every non-trivial task (adding tests, page objects, factories or env vars, renaming enums, debugging, refactoring, multi-skill changes) and when asked how to work with AI here or which skill applies. Not for a one-line fix, typo or single import (direct mode, see Critical).
Skill Claude CodeCodex
Persistent, consensus-validated memory for AI agents via SAGE MCP server. Gives you institutional memory that survives across conversations — memories go through consensus validation (a BFT quorum on a multi-validator network; a single signed validator on a personal install), carry confidence scores, and decay over…
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: