semantic-compression
Aggressively prune grammatical scaffolding and filler text from inputs to optimize LLM token usage while retaining core semantic content.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
575 skills found
Aggressively prune grammatical scaffolding and filler text from inputs to optimize LLM token usage while retaining core semantic content.
End-to-end startup idea validation using S.E.E.D. niche checks, STREAM 6-layer analysis, and Devil's Advocate inversion to generate PRDs.
Automated PR review agent for Schmock projects ensuring BDD coverage, code quality, TypeScript standards, and conventional commit adherence.
Generate and edit images using the Gemini API via the nanaban CLI. Create illustrations, logos, and icons, or perform photo edits like background removal and style transfer.
Automate macOS applications using the Accessibility API for deterministic UI control, automated testing, and agent-based scripting.
Generate optimized SQL queries from natural language. Supports BigQuery, PostgreSQL, MySQL, and Snowflake. Analyze database schemas, interpret business requirements, and output ready-to-run queries with explanations.
Generate, validate, and refine Mermaid diagrams including flowcharts, sequence diagrams, ERDs, and architecture maps to visualize complex software systems and workflows.
Expert assistant for testing the Raamattu Nyt embeddable Bible widget, validating API responses, testing reference formats, and debugging audio integration.
React Native best practices for Expo and bare workflow. Supports project structure, navigation, NativeWind styling, platform-specific code, and TypeScript integration.
Enforce strict UI adherence to your project's design system tokens, components, and layout patterns for consistent frontend implementation.
A suite of .NET engineering skills for Domain-Driven Design (DDD), EF Core persistence, BDD-style unit testing, and IDE-like semantic code understanding with Serena MCP.
Scaffold complex, multi-step coding tasks into actionable implementation plans and execute them autonomously using a Claude-driven bash loop.