Results for “token”

Documents Airtable's design system including color tokens, typography hierarchy, spacing, and component patterns for building editorial-style marketing interfaces.

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'.

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.

Compresses responses by removing filler words and hedging while preserving code, errors, and technical details. Activates on explicit user request or a trigger token, and persists until released.

Analyze Claude Code token usage, spending, and budgets from a local SQLite cost-tracking database, with breakdowns by project, tool, session, or date.

Analyze Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log. Provides summaries, breakdowns by model, session, or date, and CSV export.

Compresses AI agent output tokens by up to 65% using a terse, article-free communication style while preserving full technical accuracy. Supports multiple intensity levels and auto-disables for security warnings or ambiguous instructions.

Hardens GitHub Actions workflows against supply chain attacks, credential theft, and privilege escalation by pinning actions to SHA digests, minimizing GITHUB_TOKEN permissions, preventing script injection, and implementing workflow change controls.

Search, read, create, and update Confluence pages and spaces using the confluence-cli command-line tool.

Creates, reads, deletes, and lists memos on a Memos instance via its API, using a personal access token.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Extends effective context capacity through strategic compression, masking, caching, and partitioning techniques.

Guarda y consulta información en Engram automáticamente para mantener contexto entre sesiones, optimizando el uso de tokens y delegando exploración compleja.

Analyzes and documents Superhuman's design language, including color palette, typography, layout, and elevation system for implementation.

Create, search, and manage Bear notes on macOS using the grizzly CLI, including token-based operations for appending text and listing tags.

Use when the user explicitly enters TURBO, mode TURBO, enable TURBO, or TURBO for this task, and Codex should optimize for maximum quality without normal token-cost restraint.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than relying on arbitrary auto-compaction.

Generates a comprehensive narrative report analyzing a project's entire development history from claude-mem's persistent memory timeline.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Optimizes long-running agent sessions with structured context compression, summarization, and durable handoff summaries that preserve decisions, files, risks, and next actions.

Manage Jira issues, boards, sprints, and projects via the jira-cli. Search, create, update, and transition issues directly from the command line.

Orchestrate token-heavy research, coding, and testing by delegating bounded tasks to cheaper subagents while reserving Claude Fable for architecture, synthesis, and final review.

Guides project-level decisions for LLM-powered systems: task-model fit, pipeline architecture, token and cost estimation, and agent-assisted iteration.

Machine learning on genomic interval data (BED files) with the geniml Python package — region embeddings (Region2Vec), joint region+metadata embeddings (BEDspace/StarSpace), single-cell ATAC-seq embeddings (scEmbed), consensus peak sets / universes (build-universe), tokenization, BEDshift randomization, and BBClient/BEDbase caching. Use when training or using region/cell embeddings, clustering scATAC-seq, building a tokenization universe from BED collections, or any ML/feature-learning task over genomic regions. NOT for plain interval arithmetic (overlap/intersect/merge counts) — that is gtars, not geniml. Part of the AlterLab Academic Skills suite.

Reduces AI API costs by 30-75% by classifying task complexity, checking prompt quality, and routing tasks to the most cost-efficient model tier before execution.

Use this skill for dark mode tokens, contrast, theme persistence, system preference, color scheme QA. Trigger when the task involves web design work related to Dark Mode Theme System, implementation, audits, debugging, strategy, or validation.

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.

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.

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.