Results for “token”

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.

Upload local assets (images, mockups, extracted HTML, design markdown) to a Stitch project. ALWAYS use this skill when you need to upload visual assets, HTML pages, or design docs to Stitch, particularly when direct MCP tool calls fail or truncate due to base64 token limits.

Assistant for newapi (new-api), an open-source unified AI gateway platform (https://github.com/QuantumNous/new-api). Use when the user asks about New API, managing models, groups, balance, or tokens, or securely copying keys, applying them to config files, or using them in commands without exposing secrets.

Donate to charities onchain via Endaoment. Use when the user wants to donate crypto to charity, make a charitable contribution, give to nonprofits, support a cause, or donate to a 501(c)(3). Supports Base, Ethereum, and Optimism. Handles USDC donations directly or swaps ETH/tokens to USDC automatically.

Crawl entire websites using Cloudflare Browser Rendering /crawl API. Initiates async crawl jobs, polls for completion, and saves results as markdown files. Useful for ingesting documentation sites, knowledge bases, or any web content into your project context. Requires CLOUDFLARE_ACCOUNT_ID and CLOUDFLARE_API_TOKEN environment variables.

Adds a complete dark mode to any frontend project: auto-detects the theme system, generates a WCAG-compliant dark palette, adds a toggle with system detection and persistence, migrates hardcoded colors to theme tokens, and verifies contrast ratios.

Builds real-time, bidirectional streaming applications with the Gemini Live API, covering WebSocket audio/video/text streaming, VAD, function calling, session management, ephemeral tokens, and live translation across Python and JavaScript SDKs.

表格全场景处理：本地 Excel/CSV 与在线表格（飞书、doubao.com 的 /sheets/ 链接）的创建、读写、分析、计算、建模、语义处理、可视化与美化。**只要用户输入包含表格类附件——上传 .xlsx/.xls/.csv 文件，或给出 feishu/doubao.com 的 /sheets/ 链接或 token——必须加载本技能。** 此外，用户口述数据要整理成表，或要求计算/统计/建模/预测/透视/可视化/美化/公式等任何表格操作时，也加载本技能。一切与 Excel/表格相关的任务都必须加载。本技能不负责获取外部信息，如需补充数据须先通过其他途径获得。

Create and troubleshoot Ocana agents. Use when creating a new Ocana agent, refreshing/repairing management token auth, diagnosing `ocana_agent_create` failures, checking `gatewayReachable`, handling agents stuck in `provisioning`, debugging `226/NAMESPACE` or missing `/usr/bin/openclaw`, or testing lifecycle/reprovision flows for a newly created agent.

Interact with GitHub via the `gh` CLI. Use for issues (read, comment, file), pull requests (view, comment, check CI status), workflow runs, and `gh api` for queries the subcommands don't cover. Authentication is via the bot's GITHUB_TOKEN (already wired through `gh auth setup-git` at container start).

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

All-in-one fullstack dev engine. /aura: 46 modes (build/fix/clean/deploy/review/spec/lore/ax/experiment/payment/debug/qa/orchestrate/escalate+), 6-layer security with 32 hooks, tiered models (ZERO/ECO/PRO/MAX), 8 languages, 16 specialized agents, SPEC/EARS/TRUST5/XLOOP/RALF/Autopus absorbed. ~55% token savings.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Build a task-aware context bundle (relevant code + applicable standards + related past decisions) via the local RAG index, capped at a token budget. Use at the start of any implementation/refactor/debug task instead of reading files blindly. Replaces "read whole file" with "retrieve the function + callers + rules + prior ADR."

Mine LITCOIN — a proof-of-comprehension and proof-of-research cryptocurrency on Base. Use when the user wants to mine crypto with AI, earn tokens through reading comprehension or solving optimization problems, stake LITCOIN, open vaults, mint LITCREDIT, manage mining guilds, deploy autonomous agents, or interact with the LITCOIN DeFi protocol.

Builds distinctive, production-grade UI by committing to one of 12 named visual directions, implementing a real typography scale, spacing system, and one signature flourish, then gating the result through a measurable anti-slop checklist and contrast/touch-target verification.

Detect lateral movement in Azure AD/Entra ID environments using Microsoft Graph API audit logs, Azure Sentinel KQL hunting queries, and sign-in anomaly correlation to identify privilege escalation, token theft, and cross-tenant pivoting.

Pay HTTP 402 payment challenges issued by OKX's Agent Payments Protocol (APP) on X Layer using tokens from any chain via the Uniswap Trading API. Use this skill whenever the user encounters a 402 challenge whose network resolves to X Layer (chain 196), mentions "APP", "Agent Payments Protocol", "OKX agent payment", "OKX Onchain OS", "OKX agentic wallet", "x402 on X Layer", "USDT0", "x42", "Instant Payment", "Batch Payment", "pay for X Layer API", or wants to pay an OKX-backed merchant. Even when the user does not explicitly say APP, prefer this skill for any 402 challenge whose network resolves to X Layer (chain 196). For 402 challenges on other chains (Ethereum, Base, Arbitrum, Tempo) use pay-with-any-token instead.

Convert the cited draft into a Strapi-ready package — clean markdown body + Strapi-shaped JSON payload + a README with paste/publish instructions. Pushes directly to Strapi via API when STRAPI_API_TOKEN is set. With --auto-publish (or BLOG_AGENT_AUTO_PUBLISH=1), publishes the article live (publishedAt = now) instead of as draft.

Documents Replicate's design system: warm cream canvas, hot orange accent, three-family typography stack (rb-freigeist-neue, basier-square, JetBrains Mono), fully rounded interactive elements, and a section rhythm that alternates between cream, orange hero, dark code-story, and black footer.

Rastreie sites inteiros usando a API /crawl do Cloudflare Browser Rendering. Inicia jobs de rastreamento assíncronos, monitora a conclusão e salva os resultados como arquivos markdown. Útil para ingerir sites de documentação, bases de conhecimento ou qualquer conteúdo web no contexto do seu projeto. Requer variáveis de ambiente CLOUDFLARE_ACCOUNT_ID e CLOUDFLARE_API_TOKEN.

Authentication and credential security assessment. Tests password brute-force, credential stuffing, password spraying, default credential testing, credential harvesting, lockout analysis, MFA bypass, OAuth/OIDC abuse, session token entropy, Kerberos attacks, and intelligent wordlist generation. Uses hydra, john, ncrack, medusa, cewl, crunch, netexec, impacket, kerbrute, and nuclei default-login templates. Covers OWASP A07:2021 Identification and Authentication Failures.

Clinic-architecture-aligned iOS animation craft guidelines for SwiftUI (iOS 26 / Swift 6.2) covering motion tokens, spring physics, gesture continuity, spatial transitions, micro-interactions, and accessibility. Enforces @Equatable on animated views and keeps animation state aligned with Domain/Data feature boundaries. Use when writing, reviewing, or refactoring SwiftUI animation code under the clinic modular MVVM-C architecture.

Routes, controller, Acorn routes, web.php, route:list, Route::get, Route::post, Route::resource, Route::apiResource, middleware, route model binding, API endpoint, RouteServiceProvider, named routes, resource controller, single-action controller, invokable controller, route group, route prefix, JSON response, rate limiting, token auth, Accept application/json, route cache, WP rewrite conflicts — using Acorn's Laravel routing inside WordPress/Sage/Bedrock

Import Figma content into a HyperFrames composition — rendered assets, brand tokens, components, storyboard sections → reconstructed motion (frames read as states, not slides) (REST/CLI), connector-assisted motion when available, and shaders from a connector or native export. Use when the user pastes a figma.com link or asks to bring a Figma design, frame, logo, brand, or animation into a video/composition.

Use when user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana program", "deploy to devnet", or "explain Solana concepts" (rent, accounts, PDAs, CPIs, etc.). Also use for quick on-chain lookups via public RPC + curl — "what's the balance of <wallet>", "look up transaction <sig>", "token balance for <account>", "check this address on mainnet/devnet". End-to-end Solana development playbook covering wallet connection, Anchor/Pinocchio programs, Codama client generation, LiteSVM/Mollusk/Surfpool testing, security checklists, and JSON-RPC curl lookups against public clusters. Integrates with the Solana MCP server for live documentation search. Prefers framework-kit (@solana/client + @solana/react-hooks) for UI, wallet-standard-first connection (incl. ConnectorKit), @solana/kit for client/RPC code, and @solana/web3-compat for legacy boundaries.

Audit and attack session cookies via missing Secure/HttpOnly/SameSite attributes, overly broad Domain/Path scope, non-expiring persistent cookies, absent __Host- and __Secure- prefixes, browser cache leakage (Cache-Control: no-store missing), session token predictability via Burp Sequencer analysis, server-side session not invalidated on logout, and SSO single-logout bypass. Tools: Burp Suite Repeater/Sequencer, OWASP ZAP, EditThisCookie, Tamper Data, Cookiebro.

4-stage funnel that screens all 500+ Hyperliquid perps down to the top trading opportunities. Scores setups 0-400 across smart money, market structure, technicals, and funding. BTC macro filter, hourly trend gate (counter-trend = hard skip), cross-scan momentum tracking. Near-zero LLM tokens — all computation in Python. Use when scanning for new trading opportunities on Hyperliquid, evaluating setups, or checking market conditions.

Use WordPress' HTML API for safe server-side HTML inspection and mutation instead of regex, fragile string replacement, or DOMDocument. Covers WP_HTML_Tag_Processor, WP_HTML_Processor, set_attribute, remove_attribute, add_class, remove_class, set_modifiable_text, serialize_token, custom data attribute name mapping.

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. If the project already has a DESIGN.md, uses its tokens instead of the 12 built-in presets. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

High-fidelity website/app clone design pipeline. Use when asked to clone, replicate, copy, or recreate any existing website or app screen. Captures real assets (images, SVGs, fonts, colors), extracts exact design tokens, generates the clone in Stitch, composites real assets into the output, then runs section-by-section visual comparison against the reference. Produces 90%+ accurate clones by combining Stitch generation with real asset injection.

Expert knowledge for Azure Attestation development including troubleshooting, best practices, security, configuration, and deployment. Use when validating attestation tokens, authoring policies, managing SGX/TPM baselines, or securing private endpoints, and other Azure Attestation related development tasks. Not for Azure Confidential Computing (use azure-confidential-computing), Azure Virtual Enclaves (use azure-virtual-enclaves), Azure Key Vault (use azure-key-vault), Azure Dedicated HSM (use azure-dedicated-hsm).

World-class color theory expertise combining the scientific precision of Josef Albers' "Interaction of Color," the systematic thinking of color systems from Pantone and RAL, and the perceptual psychology insights from researchers like Bevil Conway. Color is not just aesthetics - it's communication, emotion, and usability compressed into wavelengths. Great color work is invisible when done right. Users don't notice "nice colors" - they notice when they can't read text, when buttons don't look clickable, when errors don't feel urgent, or when the interface feels "off" without knowing why. Color theory is the science of making the right thing feel obvious. Use when "color theory, color palette, color scheme, color harmony, complementary colors, analogous colors, contrast ratio, dark mode colors, light mode, color tokens, semantic colors, color accessibility, color blindness, color psychology, color system, brand colors, data visualization colors, color, design, accessibility, contrast, dark-mode, theming, tokens

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST