Results for “token”

Entry-point router for the local Pump.fun skill suite. Use when the user asks about launching Pump.fun tokens, bonding-curve or AMM trading, quotes, fees, claims, incentives, SDK work, agent/MCP integration, security, testing, or release workflows.

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

Converts long-form markdown documents (specs, RFCs, reports, plans) into a single-file HTML page with sticky table of contents, scrollspy, search filter, code-copy buttons, and customizable design tokens.

Run Microsoft Entra ID tenant reconnaissance, token acquisition and manipulation, and federation backdoor testing with the AADInternals PowerShell toolkit to validate identity-attack resilience.

Analyzes Vercel's design language, documenting its color system, typography, surface hierarchy, and gradient-based decorative system for use in design systems or brand analysis.

Builds accessible, responsive UI components and layouts with shadcn/ui, Tailwind CSS, theming, dark mode, and WCAG 2.1 AA compliance, applying behavioral science principles.

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

Extrai e documenta o sistema de design do projeto legado — paleta de cores, tipografia, espaçamentos, tokens e componentes a partir de CSS, arquivos de tema e screenshots. Use quando arquivos de estilo ou screenshots de interface estiverem disponíveis.

Provides copy-paste animation patterns for React and Next.js, including buttons, modals, toasts, stagger lists, page transitions, scroll reveals, and layout animations, all built on motion-foundations tokens.

Load pre-trained models from Hugging Face Hub, run pipeline inference, generate text, and fine-tune models on NLP, vision, audio, and multimodal tasks using the Transformers library.

Test web applications for Cross-Site Request Forgery vulnerabilities by crafting forged requests that exploit authenticated user sessions during authorized security assessments.

Conduct authorized red team initial access using EvilGinx3 adversary-in-the-middle phishing to capture session tokens and bypass multi-factor authentication.

Audits AGENTS.md and CLAUDE.md files for bloat, redundancy, and ineffective rules, then runs A/B evals to prove which instructions are dead weight.

Benchmarks long-context language models across 20 sub-tasks spanning 3k–200k tokens, covering retrieval, reasoning, summarization, and instruction understanding, with exact-match accuracy as the primary metric.

Design UI/UX in a Sage project — Figma to Blade, design tokens to Tailwind v4, Paper/Figma MCP integration, component design, layout design, responsive design, design-to-code workflow, visual design review, design system alignment, design approval before implementation

Gera um plano de reconstrução bottom-up a partir das specs do Reversa e executa cada tarefa sob demanda, uma por vez, preservando tokens. Use quando quiser reimplementar o software do zero a partir das especificações geradas. Ativação: /reversa-reconstructor

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any stand...

Deposit ERC-20 token supply into a Berry Juicer vault on Base to earn trading fees as USDC, then spend the yield as AI inference across 140+ models.

Provides Ethereum token and protocol standards including ERC-20, ERC-721, ERC-1155, ERC-4337, ERC-8004 agent identity, EIP-7702, EIP-3009 gasless transfers, and x402 HTTP payment protocol.

Identify and test open redirect vulnerabilities in web applications by analyzing URL redirection parameters, bypass techniques, and exploitation chains for phishing and token theft.

Perform reconnaissance, persistence, privilege escalation, and data pillaging on Microsoft 365/Entra ID tenants via the Microsoft Graph API using the GraphRunner PowerShell toolset.

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.

Implementation guide for ePrivacy Directive compliant double opt-in email consent. Covers confirmation email workflow design, token expiration handling, record-keeping requirements, suppression list management, and integration with CAN-SPAM Act and CASL requirements for multi-jurisdiction compliance.

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.

Guides developers through Google Ads API quickstart: credential setup, choosing from 6 client libraries/REST, configuring environments, and running a 'retrieve campaigns' script. Troubleshoots common setup errors.

Reverse-engineer a design system from frontend source code by analyzing component files, stylesheets, Tailwind configs, theme definitions, and design tokens to produce a comprehensive DESIGN.md document.

Takes a PRD, reference URL, screenshot, or keywords to produce a DESIGN.md specification, then generates production-ready web code that meets UI/UX, visual, motion, and responsive standards.

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.

Use when creating a new skill under .agents/skills/, editing an existing one, or deciding whether a technique deserves to become a skill at all - covers SKILL.md structure, the description field, and how to keep a skill discoverable and token-efficient.