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.
225 skills found
Aggressively prune grammatical scaffolding and filler text from inputs to optimize LLM token usage while retaining core semantic content.
Review Hyperlane documentation changes against project standards, ensuring compliance with architectural patterns and content guidelines.
Analyze Kubernetes controller code to generate contract-compliant dependency graph artifacts for the Kamera coverage strategy.
A command-line tool and Expo module for interacting with Apple HealthKit, allowing you to seed, query, and verify health data in development.
Expert guidance for Django asynchronous task processing with Celery. Best practices for task design, worker configuration, error handling, periodic tasks, and production monitoring.
Official Mastra framework guide. Master AI agent and workflow development with local documentation lookup, API verification, and TypeScript-based project management.
Optimize agent context windows through KV-caching, observation masking, summarization-based compaction, and context partitioning to reduce costs and latency.
Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.
Implement LlamaExtract for robust structured data extraction from PDF, DOCX, and PPTX files using Pydantic schemas.
A local RAG semantic memory system using Qdrant and Ollama. Ideal for recalling workspace files, notes, project decisions, and user preferences with high-relevance vector search.
Official Sunhat toolkit for end-to-end TRON smart contract lifecycle: development, compilation, cross-framework testing, and deployment.
Neuropixels neural recording analysis toolkit. Provides end-to-end pipelines for SpikeGLX/OpenEphys data, Kilosort4 spike sorting, motion correction, quality metrics, and AI-assisted curation.