token AI Agent Skills

Browse 1281 skills related to token

tailwind-design-system

Build scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns. Use when creating component libraries, implementing design systems, or standardizing UI patterns.

visual-design-foundations

Apply typography, color theory, spacing systems, and iconography principles to create cohesive visual designs. Use when establishing design tokens, building style guides, or improving visual hierarchy and consistency.

design-system-patterns

Build scalable design systems with design tokens, theming infrastructure, and component architecture patterns. Use when creating design tokens, implementing theme switching, building component libraries, or establishing design system foundations.

repomix-explorer

Use this skill when the user wants to analyze or explore a codebase (remote repository or local repository) using Repomix. Triggers on: 'analyze this repo', 'explore codebase', 'what's the structure', 'find patterns in repo', 'how many files/tokens'. Runs repomix CLI to pack repositories, then analyzes the output.

excalidraw

Use when working with *.excalidraw or *.excalidraw.json files, user mentions diagrams/flowcharts, or requests architecture visualization - delegates all Excalidraw operations to subagents to prevent context exhaustion from verbose JSON (single files: 4k-22k tokens, can exceed read limits)

mamba-architecture

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.

Model ArchitectureMambaState Space Models+6

huggingface-tokenizers

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

TokenizationHuggingFaceBPE+7

tailwind-patterns

Tailwind CSS v4 principles. CSS-first configuration, container queries, modern patterns, design token architecture.

long-context

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.

Emerging TechniquesLong ContextRoPE+8

optimizing-attention-flash

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.

OptimizationFlash AttentionAttention Optimization+8

ui-design-system

UI design system toolkit for Senior UI Designer including design token generation, component documentation, responsive design calculations, and developer handoff tools. Use for creating design systems, maintaining visual consistency, and facilitating design-dev collaboration.

agent-tool-builder

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa

Privilege Escalation Methods

This skill should be used when the user asks to "escalate privileges", "get root access", "become administrator", "privesc techniques", "abuse sudo", "exploit SUID binaries", "Kerberoasting", "pass-the-ticket", "token impersonation", or needs guidance on post-exploitation privilege escalation for Linux or Windows systems.

plaid-fintech

Expert patterns for Plaid API integration including Link token flows, transactions sync, identity verification, Auth for ACH, balance checks, webhook handling, and fintech compliance best practices. Use when: plaid, bank account linking, bank connection, ach, account aggregation.

design-system-starter

Create and evolve design systems with design tokens, component architecture, accessibility guidelines, and documentation templates. Ensures consistent, scalable, and accessible UI across products.

sentencepiece

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.

TokenizationSentencePieceLanguage-Independent+7

core-components

Core component library and design system patterns. Use when building UI, using design tokens, or working with the component library.

speculative-decoding

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.

Emerging TechniquesSpeculative DecodingMedusa+7

context-window-management

Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long context.

gtars

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.

nowait-reasoning-optimizer

Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.

tailwind-best-practices

Tailwind CSS styling guidelines for Mastra Playground UI. This skill should be used when writing, reviewing, or refactoring styling code in packages/playground-ui and packages/playground to ensure design system consistency. Triggers on tasks involving Tailwind classes, component styling, or design tokens.

llm-provider-usage-statistics

Reference guide for token counting and prefix caching across LLM providers (OpenAI, Anthropic, Gemini). Use when debugging token counts or optimizing prefix caching.

stripe-integration

Implement Stripe payment processing for robust, PCI-compliant payment flows including hosted Checkout Sessions, subscriptions, and webhooks. Use this Skill when integrating Stripe payments, building subscription systems, handling refunds or disputes, or implementing marketplace payouts. It covers best practices to reduce PCI scope, secure tokenization, webhook-driven state management, and scalable integration patterns.

ui-ux-designer

Create interface designs, wireframes, and design systems. Masters user research, accessibility standards, and modern design tools. Specializes in design tokens, component libraries, and inclusive design. Use PROACTIVELY for design systems, user flows, or interface optimization.

tailwind-design-system

Build scalable design systems with Tailwind CSS, design tokens, component libraries, and responsive patterns. Use when creating component libraries, implementing design systems, or standardizing UI...

context-optimization

This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.

context-compression

This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.

defuddle

Extract clean Markdown content from web pages using the Defuddle CLI, removing clutter and navigation to reduce token usage. Use this instead of WebFetch when a user provides a URL to read or analyze—ideal for online documentation, articles, blog posts, and other standard web pages.

markdown-mermaid-writing

Comprehensive markdown and Mermaid diagram writing skill that establishes text-based diagrams as the DEFAULT documentation standard. Use this skill when creating ANY scientific document, report, analysis, or visualization — it ensures all outputs are in version-controlled, token-efficient markdown with embedded Mermaid diagrams as the source of truth, with clear pathways to downstream Python or AI-generated images. Includes full style guides (markdown + mermaid), 24 diagram type references, and 9 document templates ready to use.

gtars

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.

sentry

Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.

ecomode

Token-efficient model routing modifier

hugging-face-jobs

This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection, cost estimation, authentication with tokens, secrets management, timeout configuration, and result persistence. Designed for general-purpose compute workloads including data processing, inference, experiments, batch jobs, and any Python-based tasks. Should be invoked for tasks involving cloud compute, GPU workloads, or when users mention running jobs on Hugging Face infrastructure without local setup.

agent-session-monitor

Real-time agent conversation monitoring - monitors Higress access logs, aggregates conversations by session, tracks token usage. Supports web interface for viewing complete conversation history and costs. Use when users ask about current session token consumption, conversation history, or cost statistics.

netalertx-authentication-tokens

Manage and troubleshoot API tokens and authentication-related secrets. Use this when you need to find, rotate, verify, or debug authentication issues (401/403) in NetAlertX.

half-clone

Clone the latter half of the current conversation, discarding earlier context to reduce token usage while preserving recent work.

morph-apply

Fast file editing via Morph Apply API (10,500 tokens/sec, 98% accuracy)

tldr-overview

Get a token-efficient overview of any project using the TLDR stack

tldr-stats

Show full session token usage, costs, TLDR savings, and hook activity

tldr-code

Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.

repoprompt

Use RepoPrompt CLI for token-efficient codebase exploration

Privilege Escalation Methods

This skill should be used when the user asks to "escalate privileges", "get root access", "become administrator", "privesc techniques", "abuse sudo", "exploit SUID binaries", "Kerberoasting", "pass-the-ticket", "token impersonation", or needs guidance on post-exploitation privilege escalation for Linux or Windows systems.

fuzzing-dictionary

Fuzzing dictionaries guide fuzzers with domain-specific tokens. Use when fuzzing parsers, protocols, or format-specific code.

secure-workflow-guide

Guides through Trail of Bits' 5-step secure development workflow. Runs Slither scans, checks special features (upgradeability/ERC conformance/token integration), generates visual security diagrams, helps document security properties for fuzzing/verification, and reviews manual security areas.

token-integration-analyzer

Token integration and implementation analyzer based on Trail of Bits' token integration checklist. Analyzes token implementations for ERC20/ERC721 conformity, checks for 20+ unusual token patterns, assesses contract composition and owner privileges, performs on-chain scarcity analysis, and evaluates how protocols handle non-standard tokens. Context-aware for both token implementations and token integrations.

.NET Conventions

C# coding standards for the Exceptionless codebase. Naming conventions, async patterns, structured logging, nullable reference types, and formatting rules. Keywords: C# style, naming conventions, _camelCase, PascalCase, async suffix, CancellationToken, nullable annotations, structured logging, ExceptionlessState

perf-optimizer

Systematic performance optimization and regression debugging for OneKey mobile app (iOS). Use when: (1) Fixing performance regressions - when metrics like tokensStartMs, tokensSpanMs, or functionCallCount have regressed and need to be brought back to normal levels, (2) Improving baseline performance - when there's a need to optimize cold start time or reduce function call overhead, (3) User requests performance optimization/improvement/debugging for the app's startup or home screen refresh flow.

Join Clawiskill today. The decentralized skill network for AI Agents.

Explore Network