Results for “token”

Converts human-written CLAUDE.md files into a structured-label format that improves AI instruction compliance while reducing token usage.

从本地成本追踪数据库追踪并报告 Claude Code 的 Token 用量、花费与预算

Establish clear naming conventions for design assets, components, and tokens to make design systems predictable and maintainable.

Documents the Raycast design system with color tokens, typography hierarchy, and surface modes for building consistent dark-mode interfaces.

Provides the complete design language for Supabase marketing surfaces, including color tokens, typography hierarchy, spacing system, and component styles.

Converts human-written CLAUDE.md files into a structured-label format that AI models follow more reliably while using fewer tokens.

Authenticates to GitHub using a token, SSH key, or the gh CLI, with guidance for troubleshooting common auth failures.

Launch a fixed-supply V3 token on Robinhood Chain (4663) via PonsLaunchFactory (pons.family), reverse-discover the factory from live PonsLauncherToken tokens, prepare launchToken txs, and verify TokenLaunched receipts. Use when the user says "launch on Pons", "pons.family launch", "PonsLaunchFactory", "launchToken", "PonsLauncherToken", "V3 launch on Robinhood", or wants agents to create a Pons token. Does NOT use RH bonding-curve createToken (rh-bonded-launch), does NOT mint Solana $CLAWD, and does NOT use NOXA Fun factories.

Documents Sentri's design language with color tokens, typography hierarchy, and layout patterns for a developer-tools brand.

Converts human-written CLAUDE.md files into a structured-label format that AI models follow more reliably while using fewer tokens.

Converts human-written CLAUDE.md files into a structured-label format that AI models follow more reliably while using fewer tokens.

Solana development patterns used in the Pump SDK — Anchor IDL-based program interaction, SPL Token and Token-2022 management, transaction construction with instruction composition, RPC batching, and cross-program coordination.

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Enumerate Microsoft Entra ID tenants using ROADrecon and acquire/exchange tokens with roadtx for authorized red-team operations.

Define a motion system with duration tokens, easing vocabulary, and reduced-motion handling for consistent animation across a product.

Design a theming architecture that supports brand variants, dark mode, and high-contrast modes with token mapping.

Converts human-written CLAUDE.md files into a structured-label format that AI models follow more reliably while using fewer tokens.

Read, propose, and vote in the Starchild DAO — a hold-to-govern commons for the $STARCHILD token on Base, with gasless EIP-712 signatures.

Documents HP's design language with color tokens, typography hierarchy, and layout patterns for building enterprise-consumer interfaces.

Analyzes and documents Wise's design language, including color palette, typography, spacing, and layout tokens for use in design systems.

Audits a codebase against a multi-layer design system, checking token, primitive, component, and layout drift with automated grep checks and severity ratings.

Converts Stitch screen designs into production React components, fetching and caching assets locally, extracting design tokens, and archiving existing pages before replacement.

Read-only EVM client: wallets, tokens, gas across 8 chains.

Reduces token usage by ~75% by stripping filler words, articles, and pleasantries while preserving full technical accuracy. Activates on user commands like 'caveman mode' or 'be brief'.

Convert human-written CLAUDE.md files into a structured label format that AI models follow more reliably using fewer tokens.

Implement secure JWT signing and verification with HMAC-SHA256, RSA-PSS, and EdDSA, including token expiration, claims validation, and defense against common JWT attacks.

Compress natural language memory files (CLAUDE.md, todos, preferences) into a concise format to save input tokens while preserving technical substance, code, URLs, and structure.

Configure and claim creator fee sharing on Pump.fun tokens

Author/validate/export Google's DESIGN.md token spec files.

GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.

Author/validate/export Google's DESIGN.md token spec files.

GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.

Author/validate/export Google's DESIGN.md token spec files.

Check a screen's brand expression by comparing it against mood, voice, and design token reference files, flagging divergences and suggesting corrections.

Translates between Figma designs and Vue 3 + shadcn-vue code, mapping Auto Layout to Tailwind, extracting design tokens, and pushing components back to Figma via MCP.

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.