Results for “token”

Optimize a complete candidate context package by deduplicating, filtering, ordering, and allocating its token budget. Use when retrieved or assembled material is noisy or exceeds the useful context budget; use context-ranking for scoring chunks and context-compression for shrinking selected content.

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.

Installs and configures the official Google Ads MCP Server to connect AI assistants to Google Ads accounts for querying campaigns and retrieving reporting metrics using natural language.

Execute AEM Edge Delivery Services admin operations: manage content, cache, code, indexes, sitemaps, snapshots, logs, users, jobs, sites, config, secrets, API keys, tokens, profiles, and versioning. Also supports Document Authoring operations.

Investigate tokens, wallets, and on-chain entities with natural-language answers backed by on-chain data. Detect insiders, whales, pump-and-dump, wash trading, and wallet networks on Base.

Guarantee valid JSON, XML, or code structure during text generation using Pydantic models for type-safe outputs, supporting local models (Transformers, vLLM, llama.cpp) and maximizing inference speed with structured generation.

Analyzes and recreates Wired magazine's editorial design language: a strict black-and-white duet, proprietary serif/sans typographic system, square buttons, magazine-style story grid, and hairline borders.

Manages Coda documents via the REST API v1, including listing, creating, updating, deleting docs, managing tables, rows, pages, triggering automations, and exploring doc structure. Requires a CODA_API_TOKEN environment variable and explicit confirmation for destructive operations.

Provides a suite of five product team skills covering OKR alignment, feature prioritization, sprint planning, user research, and design systems, with scripts and templates for each role.

API service-layer patterns — axios/fetch client with interceptors, domain-scoped service objects (UserService, ProductService), auth-token refresh, request cancellation, and error normalisation. Use when adding or reviewing HTTP call sites, organising services under api/ or services/, or centralising cross-cutting request concerns.

Expert guidance for Groq, the LLM inference platform that provides the fastest token generation speeds available, powered by custom LPU (Language Processing Unit) hardware. Helps developers integrate Groq's API for real-time AI applications where latency matters — chatbots, code completion, and streaming responses.

Extract a comprehensive design system (DESIGN.md) directly from frontend source code — React, Vue, Svelte, Angular, plain HTML/CSS, or any web framework. Analyzes component files, stylesheets, Tailwind configs, theme definitions, and design tokens to produce a rich, Stitch-compatible design system document. Use this skill whenever the user wants to reverse-engineer a design system from an existing codebase, audit the visual language of a project, extract design tokens from source files, or understand the styling patterns in a frontend repo — even if they just say "what does this app look like?" or "pull out the design from this code."

Implements a feature phase by phase from a phased JSON or Markdown plan, with configurable unit-test and quality-gate choices per phase, token-budgeted execution, resumable state, and TDD handoff.

Interage com o YouTrack via REST API para operações que o MCP oficial não cobre, como boards, sprints, relatórios de tempo, anexos e comandos em lote. Requer YOUTRACK_BASE_URL e token.

HTTP middleware, JWT authentication, auth middleware, custom guards, JWT guard, route middleware, request filter, middleware group, Acorn middleware, guard, rate limiting, CORS, CheckRole, throttle, bearer token, request filtering, middleware registration, HTTP Kernel — using Acorn's Laravel middleware stack inside WordPress/Sage/Bedrock

This skill should be used when the user asks to "send tokens", "transfer ETH", "send to ENS", "transfer to wallet", "send to @username", "transfer to Farcaster", "send to Twitter handle", or any asset transfer operation. Provides guidance on recipient resolution and transfer formats.

Read-only audit of hosting, database, storage, egress, and serverless spend (Supabase, Vercel, S3/R2, edge). Use when "hosting bill is high", "cut infra costs", or a bill jumps. CI minutes → audit-cicd. Model tokens → plan-llm-cost-guardrails. Consumes test-load numbers.

Use when the user wants to create or edit forms, collect or query entries, bulk-update form data, check invoices or payment history, or manage their Jinshuju (金数据) account and team members. Also activate for keywords: 金数据, 表单, 问卷, 报名表, form_token, 数据录入, 数据查询, 批量修改.

Browse PeerTube federated video from the terminal: view videos and channels, search across instances, check server stats, and manage your account. Uses OAuth2 authentication with token persistence. Use when the user mentions PeerTube, federated video, decentralized video platforms, or browsing/uploading to a PeerTube instance.

Audits Azure Storage accounts for misconfigurations including public blob access, weak network rules, missing encryption, permissive SAS tokens, and disabled logging using Azure CLI, PowerShell, and Defender for Storage.

Toolkit de alta performance para análise de intervalos genômicos em Rust com bindings Python. Use ao trabalhar com regiões genômicas, arquivos BED, tracks de cobertura, detecção de sobreposições, tokenização para modelos de ML, ou análise de fragmentos em genômica computacional e aplicações de aprendizado de máquina.

Optimize context usage for the session by reducing bloat, improving token efficiency, and focusing on relevant areas. Use when context is growing large, responses are slow, or switching between unrelated tasks. Covers context analysis, compacting, targeted pruning, MCP-first strategies, and focused scoping by area.

Run a PDCA quality audit on LLM/AI features: traces, prompts, costs, evals, grounding, hallucination. Use for "audit LLM quality", "check Langfuse", "audit prompts", "check AI quality", "audit AI costs", "check traces". Jailbreak/OWASP LLM → audit-llm-security. Token caps → plan-llm-cost-guardrails.

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.

Use when a Claude-Design export already exists and you must adapt it into a production page before render-verify — real data, honest empty states, existing tokens/components (never ship mock numbers). Prefer this over claude-design when generation is done and adaptation starts.

Routes product requests to one of 12 bundled skills covering prioritization, OKRs, UX research, design tokens, competitive teardown, analytics, experiments, discovery, roadmaps, spec-to-repo, landing pages, and SaaS scaffolding.

Audits OAuth 2.0 permissions across identity providers to identify over-privileged third-party integrations, excessive API scopes, and unused token grants, enforcing least-privilege access.

Find over-permissive RBAC roles and service-account token abuse paths in Kubernetes using kubectl auth can-i, rbac-police, kubectl-who-can, and rakkess during authorized cluster security reviews.

Deploys canary tokens and honeytokens (fake AWS credentials, DNS canaries, document beacons, database records) that trigger alerts when accessed by attackers. Uses the Canarytokens API and custom webhook integrations for breach detection.

Detect and respond to Adversary-in-the-Middle (AiTM) phishing attacks that use reverse proxy kits like EvilProxy, Evilginx, and Tycoon 2FA to bypass MFA and steal session tokens.

Design and implement accessible UI motion systems for React, Next.js, and frontend interfaces. Use for animation, transitions, gestures, drag and drop, page transitions, staggered reveals, SVG motion, loaders, motion tokens, reduced-motion behavior, or the old motion-foundations/motion-patterns/motion-advanced/motion-ui skills.

Generates custom design system rules for AI coding agents by analyzing a project's codebase and conventions, then saving them to the appropriate rule file (CLAUDE.md, AGENTS.md, or .cursor/rules).

Access blockchain RPC endpoints via Quicknode to read onchain data including balances, token prices, transaction status, gas estimates, and block data across Base, Ethereum, Polygon, Solana, and Unichain. Supports both API key and x402 wallet-based pay-per-request access.

Report AI token usage and estimated costs. Use when: owner asks about costs today/yesterday/this week, per session, or per model. Shows main session, cron jobs, and subagents. Answers: 'how much did today cost?', 'how much was this session?', 'what was last week's spend?'

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.